{
"agent:main:main": {
"sessionId": "09a99e4e-02ec-4a6a-92d1-abcce871c973",
"updatedAt": 1775011338946,
"systemSent": true,
"abortedLastRun": false,
"authProfileOverride": "openrouter:default",
"authProfileOverrideSource": "auto",
"authProfileOverrideCompactionCount": 0,
"chatType": "direct",
"deliveryContext": {
"to": "heartbeat"
},
"lastTo": "heartbeat",
"origin": {
"label": "heartbeat",
"provider": "heartbeat",
"from": "heartbeat",
"to": "heartbeat"
},
"sessionFile": "/home/node/.openclaw/agents/main/sessions/09a99e4e-02ec-4a6a-92d1-abcce871c973.jsonl",
"compactionCount": 0,
"skillsSnapshot": {
"prompt": "\n\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its description.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n\n \n healthcheck\n Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).\n /usr/local/lib/node_modules/openclaw/skills/healthcheck/SKILL.md\n \n \n node-connect\n Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale, or plugins.entries.device-pair.config.publicUrl.\n /usr/local/lib/node_modules/openclaw/skills/node-connect/SKILL.md\n \n \n skill-creator\n Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".\n /usr/local/lib/node_modules/openclaw/skills/skill-creator/SKILL.md\n \n \n tmux\n Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.\n /usr/local/lib/node_modules/openclaw/skills/tmux/SKILL.md\n \n \n weather\n Get current weather and forecasts via wttr.in or Open-Meteo. Use when: user asks about weather, temperature, or forecasts for any location. NOT for: historical weather data, severe weather alerts, or detailed meteorological analysis. No API key needed.\n /usr/local/lib/node_modules/openclaw/skills/weather/SKILL.md\n \n \n brainstorming\n You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.\n ~/.openclaw/workspace/skills/brainstorming/SKILL.md\n \n \n clawteam-dev\n This skill should be used when the user asks to "run e2e test", "test clawteam", "end-to-end test", "test agent team", "verify clawteam works", "dev test", or wants to validate the full ClawTeam lifecycle. Runs a complete end-to-end test: cleanup → create team → create tasks with dependencies → spawn agents → wait for completion → verify results → cleanup.\n\n ~/.openclaw/workspace/skills/clawteam-dev/SKILL.md\n \n \n ClawTeam Multi-Agent Coordination\n This skill should be used when the user asks to "create a team", "spawn agents", "assign tasks", "coordinate multiple agents", "check team status", "view kanban board", "send messages between agents", "manage team tasks", "monitor team progress", or mentions "clawteam", "multi-agent coordination", "team collaboration", "agent inbox", "task board", "spawn worker". This skill should also be triggered when the current task is complex enough to benefit from splitting into subtasks and delegating to multiple agents — for example when the user asks to "build a full-stack app", "refactor the entire codebase", "implement multiple features in parallel", or when the agent determines that the work scope exceeds what a single agent can efficiently handle alone. Provides comprehensive guidance for using the ClawTeam CLI to orchestrate multi-agent teams with task management, messaging, monitoring, runtime profiles, git context, and recovery tooling.\n\n ~/.openclaw/workspace/skills/clawteam-multi-agent-coordination/SKILL.md\n \n \n executing-plans\n Use when you have a written implementation plan to execute in a separate session with review checkpoints\n ~/.openclaw/workspace/skills/executing-plans/SKILL.md\n \n \n finishing-a-development-branch\n Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup\n ~/.openclaw/workspace/skills/finishing-a-development-branch/SKILL.md\n \n \n frontend-design\n Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.\n ~/.openclaw/workspace/skills/frontend-design/SKILL.md\n \n \n receiving-code-review\n Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation\n ~/.openclaw/workspace/skills/receiving-code-review/SKILL.md\n \n \n requesting-code-review\n Use when completing tasks, implementing major features, or before merging to verify work meets requirements\n ~/.openclaw/workspace/skills/requesting-code-review/SKILL.md\n \n \n systematic-debugging\n Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes\n ~/.openclaw/workspace/skills/systematic-debugging/SKILL.md\n \n \n test-driven-development\n Use when implementing any feature or bugfix, before writing implementation code\n ~/.openclaw/workspace/skills/test-driven-development/SKILL.md\n \n \n using-git-worktrees\n Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification\n ~/.openclaw/workspace/skills/using-git-worktrees/SKILL.md\n \n \n using-superpowers\n Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions\n ~/.openclaw/workspace/skills/using-superpowers/SKILL.md\n \n \n verification-before-completion\n Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always\n ~/.openclaw/workspace/skills/verification-before-completion/SKILL.md\n \n \n writing-plans\n Use when you have a spec or requirements for a multi-step task, before touching code\n ~/.openclaw/workspace/skills/writing-plans/SKILL.md\n \n \n writing-skills\n Use when creating new skills, editing existing skills, or verifying skills work before deployment\n ~/.openclaw/workspace/skills/writing-skills/SKILL.md\n \n \n self-improvement\n Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.\n ~/.openclaw/workspace/skills/self-improving-agent/SKILL.md\n \n",
"skills": [
{
"name": "healthcheck"
},
{
"name": "node-connect"
},
{
"name": "skill-creator"
},
{
"name": "tmux",
"requiredEnv": []
},
{
"name": "weather",
"requiredEnv": []
},
{
"name": "brainstorming"
},
{
"name": "clawteam-dev"
},
{
"name": "ClawTeam Multi-Agent Coordination"
},
{
"name": "executing-plans"
},
{
"name": "finishing-a-development-branch"
},
{
"name": "frontend-design"
},
{
"name": "receiving-code-review"
},
{
"name": "requesting-code-review"
},
{
"name": "systematic-debugging"
},
{
"name": "test-driven-development"
},
{
"name": "using-git-worktrees"
},
{
"name": "using-superpowers"
},
{
"name": "verification-before-completion"
},
{
"name": "writing-plans"
},
{
"name": "writing-skills"
},
{
"name": "self-improvement"
}
],
"skillFilter": [
"coding-agent",
"discord",
"eightctl",
"gemini",
"gh-issues",
"gifgrep",
"github",
"gog",
"goplaces",
"healthcheck",
"himalaya",
"imsg",
"mcporter",
"model-usage",
"nano-pdf",
"node-connect",
"notion",
"obsidian",
"openai-whisper",
"openai-whisper-api",
"openhue",
"oracle",
"ordercli",
"peekaboo",
"sag",
"session-logs",
"sherpa-onnx-tts",
"skill-creator",
"slack",
"songsee",
"sonoscli",
"spotify-player",
"summarize",
"things-mac",
"tmux",
"trello",
"video-frames",
"voice-call",
"wacli",
"weather",
"xurl",
"brainstorming",
"clawteam-dev",
"ClawTeam Multi-Agent Coordination",
"executing-plans",
"finishing-a-development-branch",
"frontend-design",
"receiving-code-review",
"requesting-code-review",
"systematic-debugging",
"test-driven-development",
"using-git-worktrees",
"using-superpowers",
"verification-before-completion",
"writing-plans",
"writing-skills",
"self-improvement",
"clawhub",
"camsnap",
"bluebubbles",
"blucli",
"blogwatcher",
"bear-notes",
"apple-reminders",
"apple-notes",
"1password"
],
"resolvedSkills": [
{
"name": "healthcheck",
"description": "Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).",
"filePath": "/usr/local/lib/node_modules/openclaw/skills/healthcheck/SKILL.md",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/healthcheck",
"sourceInfo": {
"path": "/usr/local/lib/node_modules/openclaw/skills/healthcheck/SKILL.md",
"source": "openclaw-bundled",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/healthcheck"
},
"disableModelInvocation": false
},
{
"name": "node-connect",
"description": "Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale, or plugins.entries.device-pair.config.publicUrl.",
"filePath": "/usr/local/lib/node_modules/openclaw/skills/node-connect/SKILL.md",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/node-connect",
"sourceInfo": {
"path": "/usr/local/lib/node_modules/openclaw/skills/node-connect/SKILL.md",
"source": "openclaw-bundled",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/node-connect"
},
"disableModelInvocation": false
},
{
"name": "skill-creator",
"description": "Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like \"create a skill\", \"author a skill\", \"tidy up a skill\", \"improve this skill\", \"review the skill\", \"clean up the skill\", \"audit the skill\".",
"filePath": "/usr/local/lib/node_modules/openclaw/skills/skill-creator/SKILL.md",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/skill-creator",
"sourceInfo": {
"path": "/usr/local/lib/node_modules/openclaw/skills/skill-creator/SKILL.md",
"source": "openclaw-bundled",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/skill-creator"
},
"disableModelInvocation": false
},
{
"name": "tmux",
"description": "Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.",
"filePath": "/usr/local/lib/node_modules/openclaw/skills/tmux/SKILL.md",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/tmux",
"sourceInfo": {
"path": "/usr/local/lib/node_modules/openclaw/skills/tmux/SKILL.md",
"source": "openclaw-bundled",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/tmux"
},
"disableModelInvocation": false
},
{
"name": "weather",
"description": "Get current weather and forecasts via wttr.in or Open-Meteo. Use when: user asks about weather, temperature, or forecasts for any location. NOT for: historical weather data, severe weather alerts, or detailed meteorological analysis. No API key needed.",
"filePath": "/usr/local/lib/node_modules/openclaw/skills/weather/SKILL.md",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/weather",
"sourceInfo": {
"path": "/usr/local/lib/node_modules/openclaw/skills/weather/SKILL.md",
"source": "openclaw-bundled",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/weather"
},
"disableModelInvocation": false
},
{
"name": "brainstorming",
"description": "You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.",
"filePath": "/home/node/.openclaw/workspace/skills/brainstorming/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/brainstorming",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/brainstorming/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/brainstorming"
},
"disableModelInvocation": false
},
{
"name": "clawteam-dev",
"description": "This skill should be used when the user asks to \"run e2e test\", \"test clawteam\", \"end-to-end test\", \"test agent team\", \"verify clawteam works\", \"dev test\", or wants to validate the full ClawTeam lifecycle. Runs a complete end-to-end test: cleanup → create team → create tasks with dependencies → spawn agents → wait for completion → verify results → cleanup.\n",
"filePath": "/home/node/.openclaw/workspace/skills/clawteam-dev/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/clawteam-dev",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/clawteam-dev/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/clawteam-dev"
},
"disableModelInvocation": false
},
{
"name": "ClawTeam Multi-Agent Coordination",
"description": "This skill should be used when the user asks to \"create a team\", \"spawn agents\", \"assign tasks\", \"coordinate multiple agents\", \"check team status\", \"view kanban board\", \"send messages between agents\", \"manage team tasks\", \"monitor team progress\", or mentions \"clawteam\", \"multi-agent coordination\", \"team collaboration\", \"agent inbox\", \"task board\", \"spawn worker\". This skill should also be triggered when the current task is complex enough to benefit from splitting into subtasks and delegating to multiple agents — for example when the user asks to \"build a full-stack app\", \"refactor the entire codebase\", \"implement multiple features in parallel\", or when the agent determines that the work scope exceeds what a single agent can efficiently handle alone. Provides comprehensive guidance for using the ClawTeam CLI to orchestrate multi-agent teams with task management, messaging, monitoring, runtime profiles, git context, and recovery tooling.\n",
"filePath": "/home/node/.openclaw/workspace/skills/clawteam-multi-agent-coordination/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/clawteam-multi-agent-coordination",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/clawteam-multi-agent-coordination/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/clawteam-multi-agent-coordination"
},
"disableModelInvocation": false
},
{
"name": "executing-plans",
"description": "Use when you have a written implementation plan to execute in a separate session with review checkpoints",
"filePath": "/home/node/.openclaw/workspace/skills/executing-plans/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/executing-plans",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/executing-plans/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/executing-plans"
},
"disableModelInvocation": false
},
{
"name": "finishing-a-development-branch",
"description": "Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup",
"filePath": "/home/node/.openclaw/workspace/skills/finishing-a-development-branch/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/finishing-a-development-branch",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/finishing-a-development-branch/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/finishing-a-development-branch"
},
"disableModelInvocation": false
},
{
"name": "frontend-design",
"description": "Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.",
"filePath": "/home/node/.openclaw/workspace/skills/frontend-design/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/frontend-design",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/frontend-design/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/frontend-design"
},
"disableModelInvocation": false
},
{
"name": "receiving-code-review",
"description": "Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation",
"filePath": "/home/node/.openclaw/workspace/skills/receiving-code-review/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/receiving-code-review",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/receiving-code-review/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/receiving-code-review"
},
"disableModelInvocation": false
},
{
"name": "requesting-code-review",
"description": "Use when completing tasks, implementing major features, or before merging to verify work meets requirements",
"filePath": "/home/node/.openclaw/workspace/skills/requesting-code-review/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/requesting-code-review",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/requesting-code-review/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/requesting-code-review"
},
"disableModelInvocation": false
},
{
"name": "systematic-debugging",
"description": "Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes",
"filePath": "/home/node/.openclaw/workspace/skills/systematic-debugging/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/systematic-debugging",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/systematic-debugging/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/systematic-debugging"
},
"disableModelInvocation": false
},
{
"name": "test-driven-development",
"description": "Use when implementing any feature or bugfix, before writing implementation code",
"filePath": "/home/node/.openclaw/workspace/skills/test-driven-development/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/test-driven-development",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/test-driven-development/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/test-driven-development"
},
"disableModelInvocation": false
},
{
"name": "using-git-worktrees",
"description": "Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification",
"filePath": "/home/node/.openclaw/workspace/skills/using-git-worktrees/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/using-git-worktrees",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/using-git-worktrees/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/using-git-worktrees"
},
"disableModelInvocation": false
},
{
"name": "using-superpowers",
"description": "Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions",
"filePath": "/home/node/.openclaw/workspace/skills/using-superpowers/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/using-superpowers",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/using-superpowers/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/using-superpowers"
},
"disableModelInvocation": false
},
{
"name": "verification-before-completion",
"description": "Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always",
"filePath": "/home/node/.openclaw/workspace/skills/verification-before-completion/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/verification-before-completion",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/verification-before-completion/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/verification-before-completion"
},
"disableModelInvocation": false
},
{
"name": "writing-plans",
"description": "Use when you have a spec or requirements for a multi-step task, before touching code",
"filePath": "/home/node/.openclaw/workspace/skills/writing-plans/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/writing-plans",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/writing-plans/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/writing-plans"
},
"disableModelInvocation": false
},
{
"name": "writing-skills",
"description": "Use when creating new skills, editing existing skills, or verifying skills work before deployment",
"filePath": "/home/node/.openclaw/workspace/skills/writing-skills/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/writing-skills",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/writing-skills/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/writing-skills"
},
"disableModelInvocation": false
},
{
"name": "self-improvement",
"description": "Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.",
"filePath": "/home/node/.openclaw/workspace/skills/self-improving-agent/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/self-improving-agent",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/self-improving-agent/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/self-improving-agent"
},
"disableModelInvocation": false
}
],
"version": 0
},
"status": "failed",
"startedAt": 1775011338134,
"modelProvider": "openrouter",
"model": "stepfun/step-3.5-flash:free",
"contextTokens": 256000,
"systemPromptReport": {
"source": "run",
"generatedAt": 1775011338110,
"sessionId": "09a99e4e-02ec-4a6a-92d1-abcce871c973",
"sessionKey": "agent:main:main",
"provider": "openrouter",
"model": "stepfun/step-3.5-flash:free",
"workspaceDir": "/home/node/.openclaw/workspace",
"bootstrapMaxChars": 20000,
"bootstrapTotalMaxChars": 150000,
"bootstrapTruncation": {
"warningMode": "once",
"warningShown": false,
"truncatedFiles": 0,
"nearLimitFiles": 0,
"totalNearLimit": false
},
"sandbox": {
"mode": "off",
"sandboxed": false
},
"systemPrompt": {
"chars": 35330,
"projectContextChars": 15744,
"nonProjectContextChars": 19586
},
"injectedWorkspaceFiles": [
{
"name": "AGENTS.md",
"path": "/home/node/.openclaw/workspace/AGENTS.md",
"missing": false,
"rawChars": 9002,
"injectedChars": 9002,
"truncated": false
},
{
"name": "SOUL.md",
"path": "/home/node/.openclaw/workspace/SOUL.md",
"missing": false,
"rawChars": 1664,
"injectedChars": 1664,
"truncated": false
},
{
"name": "TOOLS.md",
"path": "/home/node/.openclaw/workspace/TOOLS.md",
"missing": false,
"rawChars": 1752,
"injectedChars": 1752,
"truncated": false
},
{
"name": "IDENTITY.md",
"path": "/home/node/.openclaw/workspace/IDENTITY.md",
"missing": false,
"rawChars": 682,
"injectedChars": 682,
"truncated": false
},
{
"name": "USER.md",
"path": "/home/node/.openclaw/workspace/USER.md",
"missing": false,
"rawChars": 461,
"injectedChars": 461,
"truncated": false
},
{
"name": "HEARTBEAT.md",
"path": "/home/node/.openclaw/workspace/HEARTBEAT.md",
"missing": false,
"rawChars": 192,
"injectedChars": 192,
"truncated": false
},
{
"name": "BOOTSTRAP.md",
"path": "/home/node/.openclaw/workspace/BOOTSTRAP.md",
"missing": false,
"rawChars": 1450,
"injectedChars": 1450,
"truncated": false
}
],
"skills": {
"promptChars": 9822,
"entries": [
{
"name": "healthcheck",
"blockChars": 488
},
{
"name": "node-connect",
"blockChars": 538
},
{
"name": "skill-creator",
"blockChars": 756
},
{
"name": "tmux",
"blockChars": 252
},
{
"name": "weather",
"blockChars": 413
},
{
"name": "brainstorming",
"blockChars": 356
},
{
"name": "clawteam-dev",
"blockChars": 575
},
{
"name": "ClawTeam Multi-Agent Coordination",
"blockChars": 1328
},
{
"name": "executing-plans",
"blockChars": 266
},
{
"name": "finishing-a-development-branch",
"blockChars": 392
},
{
"name": "frontend-design",
"blockChars": 561
},
{
"name": "receiving-code-review",
"blockChars": 408
},
{
"name": "requesting-code-review",
"blockChars": 283
},
{
"name": "systematic-debugging",
"blockChars": 263
},
{
"name": "test-driven-development",
"blockChars": 257
},
{
"name": "using-git-worktrees",
"blockChars": 373
},
{
"name": "using-superpowers",
"blockChars": 325
},
{
"name": "verification-before-completion",
"blockChars": 417
},
{
"name": "writing-plans",
"blockChars": 242
},
{
"name": "writing-skills",
"blockChars": 257
},
{
"name": "self-improvement",
"blockChars": 643
}
]
},
"tools": {
"listChars": 1432,
"schemaChars": 16305,
"entries": [
{
"name": "read",
"summaryChars": 298,
"schemaChars": 574,
"propertiesCount": 6
},
{
"name": "edit",
"summaryChars": 511,
"schemaChars": 2470,
"propertiesCount": 13
},
{
"name": "write",
"summaryChars": 127,
"schemaChars": 497,
"propertiesCount": 5
},
{
"name": "exec",
"summaryChars": 181,
"schemaChars": 1086,
"propertiesCount": 12
},
{
"name": "process",
"summaryChars": 85,
"schemaChars": 961,
"propertiesCount": 12
},
{
"name": "canvas",
"summaryChars": 106,
"schemaChars": 661,
"propertiesCount": 18
},
{
"name": "message",
"summaryChars": 142,
"schemaChars": 6814,
"propertiesCount": 109
},
{
"name": "tts",
"summaryChars": 152,
"schemaChars": 223,
"propertiesCount": 2
},
{
"name": "agents_list",
"summaryChars": 118,
"schemaChars": 33,
"propertiesCount": 0
},
{
"name": "sessions_list",
"summaryChars": 54,
"schemaChars": 212,
"propertiesCount": 4
},
{
"name": "sessions_history",
"summaryChars": 36,
"schemaChars": 161,
"propertiesCount": 3
},
{
"name": "sessions_send",
"summaryChars": 84,
"schemaChars": 274,
"propertiesCount": 5
},
{
"name": "sessions_yield",
"summaryChars": 97,
"schemaChars": 60,
"propertiesCount": 1
},
{
"name": "sessions_spawn",
"summaryChars": 198,
"schemaChars": 1179,
"propertiesCount": 17
},
{
"name": "subagents",
"summaryChars": 105,
"schemaChars": 191,
"propertiesCount": 4
},
{
"name": "session_status",
"summaryChars": 207,
"schemaChars": 89,
"propertiesCount": 2
},
{
"name": "web_search",
"summaryChars": 93,
"schemaChars": 446,
"propertiesCount": 4
},
{
"name": "web_fetch",
"summaryChars": 129,
"schemaChars": 374,
"propertiesCount": 3
}
]
}
},
"totalTokensFresh": false,
"endedAt": 1775011338875,
"runtimeMs": 741
},
"agent:main:telegram:direct:7154306842": {
"sessionId": "e1e12770-4d13-4c53-b642-f9a5ebad5b9a",
"updatedAt": 1774951385080,
"abortedLastRun": false,
"authProfileOverride": "openrouter:default",
"authProfileOverrideSource": "auto",
"authProfileOverrideCompactionCount": 0,
"chatType": "direct",
"deliveryContext": {
"channel": "telegram",
"to": "telegram:7154306842",
"accountId": "default"
},
"lastChannel": "telegram",
"origin": {
"provider": "webchat",
"surface": "webchat",
"chatType": "direct",
"label": "Nguyễn Ngọc Trí Vĩ",
"from": "telegram:7154306842",
"to": "telegram:7154306842",
"accountId": "default"
},
"sessionFile": "/home/node/.openclaw/agents/main/sessions/e1e12770-4d13-4c53-b642-f9a5ebad5b9a.jsonl",
"compactionCount": 0,
"skillsSnapshot": {
"prompt": "\n\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its description.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n\n \n healthcheck\n Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).\n /usr/local/lib/node_modules/openclaw/skills/healthcheck/SKILL.md\n \n \n node-connect\n Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale, or plugins.entries.device-pair.config.publicUrl.\n /usr/local/lib/node_modules/openclaw/skills/node-connect/SKILL.md\n \n \n skill-creator\n Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".\n /usr/local/lib/node_modules/openclaw/skills/skill-creator/SKILL.md\n \n \n tmux\n Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.\n /usr/local/lib/node_modules/openclaw/skills/tmux/SKILL.md\n \n \n weather\n Get current weather and forecasts via wttr.in or Open-Meteo. Use when: user asks about weather, temperature, or forecasts for any location. NOT for: historical weather data, severe weather alerts, or detailed meteorological analysis. No API key needed.\n /usr/local/lib/node_modules/openclaw/skills/weather/SKILL.md\n \n \n brainstorming\n You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.\n ~/.openclaw/workspace/skills/brainstorming/SKILL.md\n \n \n clawteam-dev\n This skill should be used when the user asks to "run e2e test", "test clawteam", "end-to-end test", "test agent team", "verify clawteam works", "dev test", or wants to validate the full ClawTeam lifecycle. Runs a complete end-to-end test: cleanup → create team → create tasks with dependencies → spawn agents → wait for completion → verify results → cleanup.\n\n ~/.openclaw/workspace/skills/clawteam-dev/SKILL.md\n \n \n ClawTeam Multi-Agent Coordination\n This skill should be used when the user asks to "create a team", "spawn agents", "assign tasks", "coordinate multiple agents", "check team status", "view kanban board", "send messages between agents", "manage team tasks", "monitor team progress", or mentions "clawteam", "multi-agent coordination", "team collaboration", "agent inbox", "task board", "spawn worker". This skill should also be triggered when the current task is complex enough to benefit from splitting into subtasks and delegating to multiple agents — for example when the user asks to "build a full-stack app", "refactor the entire codebase", "implement multiple features in parallel", or when the agent determines that the work scope exceeds what a single agent can efficiently handle alone. Provides comprehensive guidance for using the ClawTeam CLI to orchestrate multi-agent teams with task management, messaging, monitoring, runtime profiles, git context, and recovery tooling.\n\n ~/.openclaw/workspace/skills/clawteam-multi-agent-coordination/SKILL.md\n \n \n executing-plans\n Use when you have a written implementation plan to execute in a separate session with review checkpoints\n ~/.openclaw/workspace/skills/executing-plans/SKILL.md\n \n \n finishing-a-development-branch\n Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup\n ~/.openclaw/workspace/skills/finishing-a-development-branch/SKILL.md\n \n \n frontend-design\n Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.\n ~/.openclaw/workspace/skills/frontend-design/SKILL.md\n \n \n receiving-code-review\n Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation\n ~/.openclaw/workspace/skills/receiving-code-review/SKILL.md\n \n \n requesting-code-review\n Use when completing tasks, implementing major features, or before merging to verify work meets requirements\n ~/.openclaw/workspace/skills/requesting-code-review/SKILL.md\n \n \n systematic-debugging\n Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes\n ~/.openclaw/workspace/skills/systematic-debugging/SKILL.md\n \n \n test-driven-development\n Use when implementing any feature or bugfix, before writing implementation code\n ~/.openclaw/workspace/skills/test-driven-development/SKILL.md\n \n \n using-git-worktrees\n Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification\n ~/.openclaw/workspace/skills/using-git-worktrees/SKILL.md\n \n \n using-superpowers\n Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions\n ~/.openclaw/workspace/skills/using-superpowers/SKILL.md\n \n \n verification-before-completion\n Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always\n ~/.openclaw/workspace/skills/verification-before-completion/SKILL.md\n \n \n writing-plans\n Use when you have a spec or requirements for a multi-step task, before touching code\n ~/.openclaw/workspace/skills/writing-plans/SKILL.md\n \n \n writing-skills\n Use when creating new skills, editing existing skills, or verifying skills work before deployment\n ~/.openclaw/workspace/skills/writing-skills/SKILL.md\n \n \n self-improvement\n Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.\n ~/.openclaw/workspace/skills/self-improving-agent/SKILL.md\n \n",
"skills": [
{
"name": "healthcheck"
},
{
"name": "node-connect"
},
{
"name": "skill-creator"
},
{
"name": "tmux",
"requiredEnv": []
},
{
"name": "weather",
"requiredEnv": []
},
{
"name": "brainstorming"
},
{
"name": "clawteam-dev"
},
{
"name": "ClawTeam Multi-Agent Coordination"
},
{
"name": "executing-plans"
},
{
"name": "finishing-a-development-branch"
},
{
"name": "frontend-design"
},
{
"name": "receiving-code-review"
},
{
"name": "requesting-code-review"
},
{
"name": "systematic-debugging"
},
{
"name": "test-driven-development"
},
{
"name": "using-git-worktrees"
},
{
"name": "using-superpowers"
},
{
"name": "verification-before-completion"
},
{
"name": "writing-plans"
},
{
"name": "writing-skills"
},
{
"name": "self-improvement"
}
],
"skillFilter": [
"coding-agent",
"discord",
"eightctl",
"gemini",
"gh-issues",
"gifgrep",
"github",
"gog",
"goplaces",
"healthcheck",
"himalaya",
"imsg",
"mcporter",
"model-usage",
"nano-pdf",
"node-connect",
"notion",
"obsidian",
"openai-whisper",
"openai-whisper-api",
"openhue",
"oracle",
"ordercli",
"peekaboo",
"sag",
"session-logs",
"sherpa-onnx-tts",
"skill-creator",
"slack",
"songsee",
"sonoscli",
"spotify-player",
"summarize",
"things-mac",
"tmux",
"trello",
"video-frames",
"voice-call",
"wacli",
"weather",
"xurl",
"brainstorming",
"clawteam-dev",
"ClawTeam Multi-Agent Coordination",
"executing-plans",
"finishing-a-development-branch",
"frontend-design",
"receiving-code-review",
"requesting-code-review",
"systematic-debugging",
"test-driven-development",
"using-git-worktrees",
"using-superpowers",
"verification-before-completion",
"writing-plans",
"writing-skills",
"self-improvement",
"clawhub",
"camsnap",
"bluebubbles",
"blucli",
"blogwatcher",
"bear-notes",
"apple-reminders",
"apple-notes",
"1password"
],
"resolvedSkills": [
{
"name": "healthcheck",
"description": "Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).",
"filePath": "/usr/local/lib/node_modules/openclaw/skills/healthcheck/SKILL.md",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/healthcheck",
"sourceInfo": {
"path": "/usr/local/lib/node_modules/openclaw/skills/healthcheck/SKILL.md",
"source": "openclaw-bundled",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/healthcheck"
},
"disableModelInvocation": false
},
{
"name": "node-connect",
"description": "Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale, or plugins.entries.device-pair.config.publicUrl.",
"filePath": "/usr/local/lib/node_modules/openclaw/skills/node-connect/SKILL.md",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/node-connect",
"sourceInfo": {
"path": "/usr/local/lib/node_modules/openclaw/skills/node-connect/SKILL.md",
"source": "openclaw-bundled",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/node-connect"
},
"disableModelInvocation": false
},
{
"name": "skill-creator",
"description": "Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like \"create a skill\", \"author a skill\", \"tidy up a skill\", \"improve this skill\", \"review the skill\", \"clean up the skill\", \"audit the skill\".",
"filePath": "/usr/local/lib/node_modules/openclaw/skills/skill-creator/SKILL.md",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/skill-creator",
"sourceInfo": {
"path": "/usr/local/lib/node_modules/openclaw/skills/skill-creator/SKILL.md",
"source": "openclaw-bundled",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/skill-creator"
},
"disableModelInvocation": false
},
{
"name": "tmux",
"description": "Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.",
"filePath": "/usr/local/lib/node_modules/openclaw/skills/tmux/SKILL.md",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/tmux",
"sourceInfo": {
"path": "/usr/local/lib/node_modules/openclaw/skills/tmux/SKILL.md",
"source": "openclaw-bundled",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/tmux"
},
"disableModelInvocation": false
},
{
"name": "weather",
"description": "Get current weather and forecasts via wttr.in or Open-Meteo. Use when: user asks about weather, temperature, or forecasts for any location. NOT for: historical weather data, severe weather alerts, or detailed meteorological analysis. No API key needed.",
"filePath": "/usr/local/lib/node_modules/openclaw/skills/weather/SKILL.md",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/weather",
"sourceInfo": {
"path": "/usr/local/lib/node_modules/openclaw/skills/weather/SKILL.md",
"source": "openclaw-bundled",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/usr/local/lib/node_modules/openclaw/skills/weather"
},
"disableModelInvocation": false
},
{
"name": "brainstorming",
"description": "You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.",
"filePath": "/home/node/.openclaw/workspace/skills/brainstorming/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/brainstorming",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/brainstorming/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/brainstorming"
},
"disableModelInvocation": false
},
{
"name": "clawteam-dev",
"description": "This skill should be used when the user asks to \"run e2e test\", \"test clawteam\", \"end-to-end test\", \"test agent team\", \"verify clawteam works\", \"dev test\", or wants to validate the full ClawTeam lifecycle. Runs a complete end-to-end test: cleanup → create team → create tasks with dependencies → spawn agents → wait for completion → verify results → cleanup.\n",
"filePath": "/home/node/.openclaw/workspace/skills/clawteam-dev/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/clawteam-dev",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/clawteam-dev/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/clawteam-dev"
},
"disableModelInvocation": false
},
{
"name": "ClawTeam Multi-Agent Coordination",
"description": "This skill should be used when the user asks to \"create a team\", \"spawn agents\", \"assign tasks\", \"coordinate multiple agents\", \"check team status\", \"view kanban board\", \"send messages between agents\", \"manage team tasks\", \"monitor team progress\", or mentions \"clawteam\", \"multi-agent coordination\", \"team collaboration\", \"agent inbox\", \"task board\", \"spawn worker\". This skill should also be triggered when the current task is complex enough to benefit from splitting into subtasks and delegating to multiple agents — for example when the user asks to \"build a full-stack app\", \"refactor the entire codebase\", \"implement multiple features in parallel\", or when the agent determines that the work scope exceeds what a single agent can efficiently handle alone. Provides comprehensive guidance for using the ClawTeam CLI to orchestrate multi-agent teams with task management, messaging, monitoring, runtime profiles, git context, and recovery tooling.\n",
"filePath": "/home/node/.openclaw/workspace/skills/clawteam-multi-agent-coordination/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/clawteam-multi-agent-coordination",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/clawteam-multi-agent-coordination/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/clawteam-multi-agent-coordination"
},
"disableModelInvocation": false
},
{
"name": "executing-plans",
"description": "Use when you have a written implementation plan to execute in a separate session with review checkpoints",
"filePath": "/home/node/.openclaw/workspace/skills/executing-plans/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/executing-plans",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/executing-plans/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/executing-plans"
},
"disableModelInvocation": false
},
{
"name": "finishing-a-development-branch",
"description": "Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup",
"filePath": "/home/node/.openclaw/workspace/skills/finishing-a-development-branch/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/finishing-a-development-branch",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/finishing-a-development-branch/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/finishing-a-development-branch"
},
"disableModelInvocation": false
},
{
"name": "frontend-design",
"description": "Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.",
"filePath": "/home/node/.openclaw/workspace/skills/frontend-design/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/frontend-design",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/frontend-design/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/frontend-design"
},
"disableModelInvocation": false
},
{
"name": "receiving-code-review",
"description": "Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation",
"filePath": "/home/node/.openclaw/workspace/skills/receiving-code-review/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/receiving-code-review",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/receiving-code-review/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/receiving-code-review"
},
"disableModelInvocation": false
},
{
"name": "requesting-code-review",
"description": "Use when completing tasks, implementing major features, or before merging to verify work meets requirements",
"filePath": "/home/node/.openclaw/workspace/skills/requesting-code-review/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/requesting-code-review",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/requesting-code-review/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/requesting-code-review"
},
"disableModelInvocation": false
},
{
"name": "systematic-debugging",
"description": "Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes",
"filePath": "/home/node/.openclaw/workspace/skills/systematic-debugging/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/systematic-debugging",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/systematic-debugging/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/systematic-debugging"
},
"disableModelInvocation": false
},
{
"name": "test-driven-development",
"description": "Use when implementing any feature or bugfix, before writing implementation code",
"filePath": "/home/node/.openclaw/workspace/skills/test-driven-development/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/test-driven-development",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/test-driven-development/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/test-driven-development"
},
"disableModelInvocation": false
},
{
"name": "using-git-worktrees",
"description": "Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification",
"filePath": "/home/node/.openclaw/workspace/skills/using-git-worktrees/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/using-git-worktrees",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/using-git-worktrees/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/using-git-worktrees"
},
"disableModelInvocation": false
},
{
"name": "using-superpowers",
"description": "Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions",
"filePath": "/home/node/.openclaw/workspace/skills/using-superpowers/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/using-superpowers",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/using-superpowers/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/using-superpowers"
},
"disableModelInvocation": false
},
{
"name": "verification-before-completion",
"description": "Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always",
"filePath": "/home/node/.openclaw/workspace/skills/verification-before-completion/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/verification-before-completion",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/verification-before-completion/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/verification-before-completion"
},
"disableModelInvocation": false
},
{
"name": "writing-plans",
"description": "Use when you have a spec or requirements for a multi-step task, before touching code",
"filePath": "/home/node/.openclaw/workspace/skills/writing-plans/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/writing-plans",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/writing-plans/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/writing-plans"
},
"disableModelInvocation": false
},
{
"name": "writing-skills",
"description": "Use when creating new skills, editing existing skills, or verifying skills work before deployment",
"filePath": "/home/node/.openclaw/workspace/skills/writing-skills/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/writing-skills",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/writing-skills/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/writing-skills"
},
"disableModelInvocation": false
},
{
"name": "self-improvement",
"description": "Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.",
"filePath": "/home/node/.openclaw/workspace/skills/self-improving-agent/SKILL.md",
"baseDir": "/home/node/.openclaw/workspace/skills/self-improving-agent",
"sourceInfo": {
"path": "/home/node/.openclaw/workspace/skills/self-improving-agent/SKILL.md",
"source": "openclaw-workspace",
"scope": "temporary",
"origin": "top-level",
"baseDir": "/home/node/.openclaw/workspace/skills/self-improving-agent"
},
"disableModelInvocation": false
}
],
"version": 0
},
"status": "done",
"startedAt": 1774951372397,
"modelProvider": "openrouter",
"model": "stepfun/step-3.5-flash:free",
"systemPromptReport": {
"source": "run",
"generatedAt": 1774951372360,
"sessionId": "e1e12770-4d13-4c53-b642-f9a5ebad5b9a",
"sessionKey": "agent:main:telegram:direct:7154306842",
"provider": "openrouter",
"model": "stepfun/step-3.5-flash:free",
"workspaceDir": "/home/node/.openclaw/workspace",
"bootstrapMaxChars": 20000,
"bootstrapTotalMaxChars": 150000,
"bootstrapTruncation": {
"warningMode": "once",
"warningShown": false,
"truncatedFiles": 0,
"nearLimitFiles": 0,
"totalNearLimit": false
},
"sandbox": {
"mode": "off",
"sandboxed": false
},
"systemPrompt": {
"chars": 36513,
"projectContextChars": 15744,
"nonProjectContextChars": 20769
},
"injectedWorkspaceFiles": [
{
"name": "AGENTS.md",
"path": "/home/node/.openclaw/workspace/AGENTS.md",
"missing": false,
"rawChars": 9002,
"injectedChars": 9002,
"truncated": false
},
{
"name": "SOUL.md",
"path": "/home/node/.openclaw/workspace/SOUL.md",
"missing": false,
"rawChars": 1664,
"injectedChars": 1664,
"truncated": false
},
{
"name": "TOOLS.md",
"path": "/home/node/.openclaw/workspace/TOOLS.md",
"missing": false,
"rawChars": 1752,
"injectedChars": 1752,
"truncated": false
},
{
"name": "IDENTITY.md",
"path": "/home/node/.openclaw/workspace/IDENTITY.md",
"missing": false,
"rawChars": 682,
"injectedChars": 682,
"truncated": false
},
{
"name": "USER.md",
"path": "/home/node/.openclaw/workspace/USER.md",
"missing": false,
"rawChars": 461,
"injectedChars": 461,
"truncated": false
},
{
"name": "HEARTBEAT.md",
"path": "/home/node/.openclaw/workspace/HEARTBEAT.md",
"missing": false,
"rawChars": 192,
"injectedChars": 192,
"truncated": false
},
{
"name": "BOOTSTRAP.md",
"path": "/home/node/.openclaw/workspace/BOOTSTRAP.md",
"missing": false,
"rawChars": 1450,
"injectedChars": 1450,
"truncated": false
}
],
"skills": {
"promptChars": 9822,
"entries": [
{
"name": "healthcheck",
"blockChars": 488
},
{
"name": "node-connect",
"blockChars": 538
},
{
"name": "skill-creator",
"blockChars": 756
},
{
"name": "tmux",
"blockChars": 252
},
{
"name": "weather",
"blockChars": 413
},
{
"name": "brainstorming",
"blockChars": 356
},
{
"name": "clawteam-dev",
"blockChars": 575
},
{
"name": "ClawTeam Multi-Agent Coordination",
"blockChars": 1328
},
{
"name": "executing-plans",
"blockChars": 266
},
{
"name": "finishing-a-development-branch",
"blockChars": 392
},
{
"name": "frontend-design",
"blockChars": 561
},
{
"name": "receiving-code-review",
"blockChars": 408
},
{
"name": "requesting-code-review",
"blockChars": 283
},
{
"name": "systematic-debugging",
"blockChars": 263
},
{
"name": "test-driven-development",
"blockChars": 257
},
{
"name": "using-git-worktrees",
"blockChars": 373
},
{
"name": "using-superpowers",
"blockChars": 325
},
{
"name": "verification-before-completion",
"blockChars": 417
},
{
"name": "writing-plans",
"blockChars": 242
},
{
"name": "writing-skills",
"blockChars": 257
},
{
"name": "self-improvement",
"blockChars": 643
}
]
},
"tools": {
"listChars": 1892,
"schemaChars": 18153,
"entries": [
{
"name": "read",
"summaryChars": 298,
"schemaChars": 574,
"propertiesCount": 6
},
{
"name": "edit",
"summaryChars": 511,
"schemaChars": 2470,
"propertiesCount": 13
},
{
"name": "write",
"summaryChars": 127,
"schemaChars": 497,
"propertiesCount": 5
},
{
"name": "exec",
"summaryChars": 181,
"schemaChars": 1086,
"propertiesCount": 12
},
{
"name": "process",
"summaryChars": 85,
"schemaChars": 961,
"propertiesCount": 12
},
{
"name": "canvas",
"summaryChars": 106,
"schemaChars": 661,
"propertiesCount": 18
},
{
"name": "nodes",
"summaryChars": 122,
"schemaChars": 1800,
"propertiesCount": 37
},
{
"name": "cron",
"summaryChars": 3420,
"schemaChars": 690,
"propertiesCount": 13
},
{
"name": "message",
"summaryChars": 142,
"schemaChars": 5675,
"propertiesCount": 107
},
{
"name": "tts",
"summaryChars": 152,
"schemaChars": 223,
"propertiesCount": 2
},
{
"name": "gateway",
"summaryChars": 464,
"schemaChars": 497,
"propertiesCount": 12
},
{
"name": "agents_list",
"summaryChars": 118,
"schemaChars": 33,
"propertiesCount": 0
},
{
"name": "sessions_list",
"summaryChars": 54,
"schemaChars": 212,
"propertiesCount": 4
},
{
"name": "sessions_history",
"summaryChars": 36,
"schemaChars": 161,
"propertiesCount": 3
},
{
"name": "sessions_send",
"summaryChars": 84,
"schemaChars": 274,
"propertiesCount": 5
},
{
"name": "sessions_yield",
"summaryChars": 97,
"schemaChars": 60,
"propertiesCount": 1
},
{
"name": "sessions_spawn",
"summaryChars": 198,
"schemaChars": 1179,
"propertiesCount": 17
},
{
"name": "subagents",
"summaryChars": 105,
"schemaChars": 191,
"propertiesCount": 4
},
{
"name": "session_status",
"summaryChars": 207,
"schemaChars": 89,
"propertiesCount": 2
},
{
"name": "web_search",
"summaryChars": 93,
"schemaChars": 446,
"propertiesCount": 4
},
{
"name": "web_fetch",
"summaryChars": 129,
"schemaChars": 374,
"propertiesCount": 3
}
]
}
},
"totalTokensFresh": true,
"cacheRead": 45696,
"cacheWrite": 0,
"systemSent": true,
"contextTokens": 256000,
"inputTokens": 616,
"outputTokens": 1421,
"lastTo": "telegram:7154306842",
"lastAccountId": "default",
"thinkingLevel": "adaptive",
"estimatedCostUsd": 0,
"totalTokens": 46312,
"endedAt": 1774951384960,
"runtimeMs": 12563
}
}