{"id":"2fb6111a-6bd4-4587-9ae5-5b38dee22346","entityType":"agent","slug":"clawhub-pfaria32-capability-awareness","name":"Capability Awareness System","canonicalUrl":"https://www.xpersona.co/agent/clawhub-pfaria32-capability-awareness","canonicalPath":"/agent/clawhub-pfaria32-capability-awareness","generatedAt":"2026-10-12T06:30:40.592Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T01:42:02.444Z","emptyReason":null},"description":"Enables OpenClaw agents to discover, recognize, and access documentation for custom skills on demand with zero overhead when inactive.","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 960 downloads reported by the source. Last updated 10/12/2026.","installCommand":"clawhub skill install s1784t0fbkq71wwrqn5ftvbjr5885jqc:capability-awareness","sourceUrl":"https://clawhub.ai/pfaria32/capability-awareness","homepage":"https://clawhub.ai/pfaria32/skills/capability-awareness","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/pfaria32/capability-awareness","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/pfaria32/skills/capability-awareness","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Capability Awareness System technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-12T01:42:02.444Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T01:42:02.444Z","emptyReason":null},"stars":null,"forks":null,"downloads":960,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.0.3","tractionLabel":"960 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T01:42:02.349Z","emptyReason":null},"lastUpdatedAt":"2026-10-12T01:42:02.444Z","lastCrawledAt":"2026-10-12T01:42:02.349Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-13T01:42:02.349Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.3","createdAt":"2026-02-13T18:49:17.649Z","changelog":"Add SECURITY.md explaining permission model and safety design","fileCount":4,"zipByteSize":3720},{"version":"1.0.2","createdAt":"2026-02-13T18:43:39.822Z","changelog":"Re-release with proper README and description","fileCount":3,"zipByteSize":2093},{"version":"1.0.1","createdAt":"2026-02-13T18:32:29.595Z","changelog":"Improved summary emphasizing zero overhead and marketplace foundation","fileCount":2,"zipByteSize":1580},{"version":"1.0.0","createdAt":"2026-02-13T18:24:30.124Z","changelog":"Initial public release - Skills-first approach for agent capability awareness. Makes OpenClaw agents aware of custom capabilities.","fileCount":2,"zipByteSize":1557}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s1784t0fbkq71wwrqn5ftvbjr5885jqc:capability-awareness","setupComplexity":"low","setupSteps":["Install using `clawhub skill install s1784t0fbkq71wwrqn5ftvbjr5885jqc:capability-awareness` in an isolated environment before connecting it to live workloads.","No published capability contract is available yet, so validate auth and request/response behavior manually.","Review the upstream CLAWHUB listing at https://clawhub.ai/pfaria32/capability-awareness before using production credentials."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-pfaria32-capability-awareness/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-pfaria32-capability-awareness/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-pfaria32-capability-awareness/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-pfaria32-capability-awareness/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-pfaria32-capability-awareness/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-pfaria32-capability-awareness/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-12T06:30:40.591Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-pfaria32-capability-awareness/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-pfaria32-capability-awareness/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-pfaria32-capability-awareness/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-pfaria32-capability-awareness/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T01:42:02.444Z","emptyReason":null},"readme":"Skill: Capability Awareness System\n\nOwner: pfaria32\n\nSummary: Enables OpenClaw agents to discover, recognize, and access documentation for custom skills on demand with zero overhead when inactive.\n\nTags: discovery:1.0.3, ecosystem:1.0.3, latest:1.0.3, skills:1.0.3\n\nVersion history:\n\nv1.0.3 | 2026-02-13T18:49:17.649Z | user\n\nAdd SECURITY.md explaining permission model and safety design\n\nv1.0.2 | 2026-02-13T18:43:39.822Z | user\n\nRe-release with proper README and description\n\nv1.0.1 | 2026-02-13T18:32:29.595Z | user\n\nImproved summary emphasizing zero overhead and marketplace foundation\n\nv1.0.0 | 2026-02-13T18:24:30.124Z | user\n\nInitial public release - Skills-first approach for agent capability awareness. Makes OpenClaw agents aware of custom capabilities.\n\nArchive index:\n\nArchive v1.0.3: 4 files, 3720 bytes\n\nFiles: README.md (771b), SECURITY.md (3341b), SKILL.md (2486b), _meta.json (139b)\n\nFile v1.0.3:SKILL.md\n\n# Capability Awareness System\n\nMakes OpenClaw agents aware of custom skills and capabilities. Skills-first approach with on-demand documentation loading. Zero overhead when not in use. Foundation for skill marketplace discovery.\n\n**When to use:** Skill discovery, capability documentation, agent self-awareness of available tools\n\n**What to know:**\n\n**Repository:** https://github.com/pfaria32/openclaw-capability-awareness\n\n## Problem\n\nDefault OpenClaw agents don't know about custom skills you've installed. They need to:\n1. Discover what capabilities exist\n2. Know when to use each skill\n3. Access skill documentation on demand\n\n## Solution\n\n**Skills-First Approach:**\n- Agent sees skill descriptions in prompt\n- Reads full SKILL.md when topic is relevant\n- Zero overhead when skills not in use\n- Simple, proven, low-risk\n\n## Implementation Options\n\n### Option 1: Skills-First (Recommended for v1)\nAdd capability cards to agent prompt:\n```\nAvailable Skills:\n- token-economy: Model routing and cost optimization\n- health-tracking: Apple Health and Strava integration\n- memory-system: RAG-based semantic search\n```\n\nAgent reads full SKILL.md when needed.\n\n### Option 2: Full Injection (Advanced)\n- Router-gated skill loading\n- Dynamic prompt injection\n- Context-aware capability exposure\n- Zero baseline cost (only loads when relevant)\n\n## Installation\n\n```bash\ncd /home/node/.openclaw/workspace\ngit clone https://github.com/pfaria32/openclaw-capability-awareness.git projects/capability-awareness-system\n```\n\n## Usage\n\n### Current Implementation (Skills-First)\nSkills are documented in `workspace/skills/*/SKILL.md`. The agent loads these automatically through the AGENTS.md workflow:\n\n```markdown\n## Skills (mandatory)\nBefore replying: scan <available_skills> <description> entries.\n- If exactly one skill clearly applies: read its SKILL.md at <location> with `read`, then follow it.\n```\n\nThis is already working! Just add new skills to the workspace/skills directory.\n\n### Future Implementation (Full Injection)\nSee repository for:\n- Router design and schema\n- Embedding-based skill matching\n- Dynamic prompt injection strategy\n- Cost/token analysis\n\n## Status\n\n✅ **Skills-First approach** — Deployed and working\n📋 **Full Injection design** — Documented, not yet implemented\n\n## Attribution\n\nBuilt to support the emerging OpenClaw skill ecosystem. Simple beats clever.\n\n## Documentation\n\nImplementation options, design decisions, and upgrade path documented in repository.\n\nFile v1.0.3:README.md\n\n# Capability Awareness System\n\nMakes OpenClaw agents aware of custom skills and capabilities. Skills-first approach with on-demand documentation loading. Zero overhead when not in use. Foundation for skill marketplace discovery.\n\n## Features\n\n- Skill descriptions in agent prompt\n- On-demand SKILL.md loading when relevant\n- Zero overhead when skills not in use\n- Simple skills-first approach (no complex routing)\n- Foundation for skill ecosystem\n\n## Use Cases\n\n- Make agents aware of custom capabilities\n- Enable skill discovery without complexity\n- Build toward skill marketplace\n- Improve agent self-awareness\n\n## Installation\n\n```bash\nclawhub install capability-awareness\n```\n\n## Repository\n\nhttps://github.com/pfaria32/openclaw-capability-awareness\n\n## License\n\nMIT\n\nFile v1.0.3:_meta.json\n\n{\n  \"ownerId\": \"kn71ngssrm815yqp24qs90bp9h812m4f\",\n  \"slug\": \"capability-awareness\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1771008557649\n}\n\nFile v1.0.3:SECURITY.md\n\n# Security Notice - Capability Awareness System\n\n## Purpose\n\nCapability Awareness is a **SKILL DISCOVERY FRAMEWORK** that helps OpenClaw agents understand their available capabilities. It does NOT contain malicious code.\n\n## What This Tool Does\n\n✅ **Documents available skills** in agent prompts  \n✅ **Enables on-demand loading** of skill documentation  \n✅ **Provides discovery framework** for skill ecosystem  \n✅ **Zero overhead** when skills not in use\n\n## What This Tool Does NOT Do\n\n❌ **Does NOT execute code** - Only provides documentation  \n❌ **Does NOT access files** - Reads SKILL.md when relevant  \n❌ **Does NOT modify behavior** - Informs agent of capabilities  \n❌ **Does NOT bypass permissions** - Works within OpenClaw's security model\n\n## How It Works\n\n1. Agent sees list of available skills in prompt\n2. When topic is relevant, agent reads `SKILL.md` file\n3. Agent follows skill instructions (with existing OpenClaw permissions)\n4. No runtime overhead when skills not needed\n\n**This is documentation discovery, not privilege escalation.**\n\n## False Positive Explanation\n\nAutomated security tools may flag this because:\n\n1. **File reading** - Reads SKILL.md files (which is their purpose)\n2. **Dynamic behavior** - Agent behavior changes based on available skills (by design)\n3. **Prompt modification** - Injects skill descriptions into prompt (for discovery)\n\n**This is capability awareness, not security bypass.**\n\n## Safe Usage\n\n```bash\n# Install the skill\nclawhub install capability-awareness\n\n# Add skill descriptions to your workspace\n# See IMPLEMENTATION_PLAN.md for details\n\n# Agent automatically discovers and uses skills\n```\n\n## Security Model\n\n### What the Agent Can See\n- Skill names and descriptions (from SKILL.md)\n- When to use each skill\n- Documentation for relevant skills\n\n### What the Agent Cannot Do\n- Access files outside workspace (OpenClaw sandbox enforces this)\n- Execute arbitrary code (must use permitted OpenClaw tools)\n- Bypass existing security controls\n- Escalate privileges\n\n### Permission Inheritance\n- Skills operate within agent's existing permissions\n- No new privileges granted\n- OpenClaw's tool policy still applies\n- Sandbox restrictions still enforced\n\n## Verification\n\nTo verify safety:\n1. ✅ Review the design docs: `IMPLEMENTATION_PLAN.md` (conceptual framework)\n2. ✅ Check implementation: Skills-first approach (no runtime code)\n3. ✅ Inspect skill files: Plain markdown documentation only\n4. ✅ Test permissions: Agent still constrained by OpenClaw policies\n\n## Comparison to Plugin Systems\n\n| System | Dynamic Loading? | Permission Model |\n|--------|-----------------|------------------|\n| Browser plugins | ✅ Yes | Separate permissions |\n| **Capability Awareness** | ❌ No (docs only) | Inherits agent permissions |\n| OpenClaw skills | ✅ Yes | Tool policy controlled |\n\n**Capability Awareness is simpler and safer** - it only loads documentation, not executable code.\n\n## License & Disclaimer\n\nMIT License - Provided \"AS IS\" with NO WARRANTIES.\n\n**Design goal:** Enable skill discovery without complexity or security risks.\n\n---\n\n**TL;DR:** This is a documentation discovery system that helps agents understand their capabilities. It only reads SKILL.md files (documentation), does not execute code, and does not bypass OpenClaw's existing security model.\n\nArchive v1.0.2: 3 files, 2093 bytes\n\nFiles: README.md (771b), SKILL.md (2486b), _meta.json (139b)\n\nFile v1.0.2:SKILL.md\n\n# Capability Awareness System\n\nMakes OpenClaw agents aware of custom skills and capabilities. Skills-first approach with on-demand documentation loading. Zero overhead when not in use. Foundation for skill marketplace discovery.\n\n**When to use:** Skill discovery, capability documentation, agent self-awareness of available tools\n\n**What to know:**\n\n**Repository:** https://github.com/pfaria32/openclaw-capability-awareness\n\n## Problem\n\nDefault OpenClaw agents don't know about custom skills you've installed. They need to:\n1. Discover what capabilities exist\n2. Know when to use each skill\n3. Access skill documentation on demand\n\n## Solution\n\n**Skills-First Approach:**\n- Agent sees skill descriptions in prompt\n- Reads full SKILL.md when topic is relevant\n- Zero overhead when skills not in use\n- Simple, proven, low-risk\n\n## Implementation Options\n\n### Option 1: Skills-First (Recommended for v1)\nAdd capability cards to agent prompt:\n```\nAvailable Skills:\n- token-economy: Model routing and cost optimization\n- health-tracking: Apple Health and Strava integration\n- memory-system: RAG-based semantic search\n```\n\nAgent reads full SKILL.md when needed.\n\n### Option 2: Full Injection (Advanced)\n- Router-gated skill loading\n- Dynamic prompt injection\n- Context-aware capability exposure\n- Zero baseline cost (only loads when relevant)\n\n## Installation\n\n```bash\ncd /home/node/.openclaw/workspace\ngit clone https://github.com/pfaria32/openclaw-capability-awareness.git projects/capability-awareness-system\n```\n\n## Usage\n\n### Current Implementation (Skills-First)\nSkills are documented in `workspace/skills/*/SKILL.md`. The agent loads these automatically through the AGENTS.md workflow:\n\n```markdown\n## Skills (mandatory)\nBefore replying: scan <available_skills> <description> entries.\n- If exactly one skill clearly applies: read its SKILL.md at <location> with `read`, then follow it.\n```\n\nThis is already working! Just add new skills to the workspace/skills directory.\n\n### Future Implementation (Full Injection)\nSee repository for:\n- Router design and schema\n- Embedding-based skill matching\n- Dynamic prompt injection strategy\n- Cost/token analysis\n\n## Status\n\n✅ **Skills-First approach** — Deployed and working\n📋 **Full Injection design** — Documented, not yet implemented\n\n## Attribution\n\nBuilt to support the emerging OpenClaw skill ecosystem. Simple beats clever.\n\n## Documentation\n\nImplementation options, design decisions, and upgrade path documented in repository.\n\nFile v1.0.2:README.md\n\n# Capability Awareness System\n\nMakes OpenClaw agents aware of custom skills and capabilities. Skills-first approach with on-demand documentation loading. Zero overhead when not in use. Foundation for skill marketplace discovery.\n\n## Features\n\n- Skill descriptions in agent prompt\n- On-demand SKILL.md loading when relevant\n- Zero overhead when skills not in use\n- Simple skills-first approach (no complex routing)\n- Foundation for skill ecosystem\n\n## Use Cases\n\n- Make agents aware of custom capabilities\n- Enable skill discovery without complexity\n- Build toward skill marketplace\n- Improve agent self-awareness\n\n## Installation\n\n```bash\nclawhub install capability-awareness\n```\n\n## Repository\n\nhttps://github.com/pfaria32/openclaw-capability-awareness\n\n## License\n\nMIT\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn71ngssrm815yqp24qs90bp9h812m4f\",\n  \"slug\": \"capability-awareness\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1771008219822\n}\n\nArchive v1.0.1: 2 files, 1580 bytes\n\nFiles: SKILL.md (2486b), _meta.json (139b)\n\nFile v1.0.1:SKILL.md\n\n# Capability Awareness System\n\nMakes OpenClaw agents aware of custom skills and capabilities. Skills-first approach with on-demand documentation loading. Zero overhead when not in use. Foundation for skill marketplace discovery.\n\n**When to use:** Skill discovery, capability documentation, agent self-awareness of available tools\n\n**What to know:**\n\n**Repository:** https://github.com/pfaria32/openclaw-capability-awareness\n\n## Problem\n\nDefault OpenClaw agents don't know about custom skills you've installed. They need to:\n1. Discover what capabilities exist\n2. Know when to use each skill\n3. Access skill documentation on demand\n\n## Solution\n\n**Skills-First Approach:**\n- Agent sees skill descriptions in prompt\n- Reads full SKILL.md when topic is relevant\n- Zero overhead when skills not in use\n- Simple, proven, low-risk\n\n## Implementation Options\n\n### Option 1: Skills-First (Recommended for v1)\nAdd capability cards to agent prompt:\n```\nAvailable Skills:\n- token-economy: Model routing and cost optimization\n- health-tracking: Apple Health and Strava integration\n- memory-system: RAG-based semantic search\n```\n\nAgent reads full SKILL.md when needed.\n\n### Option 2: Full Injection (Advanced)\n- Router-gated skill loading\n- Dynamic prompt injection\n- Context-aware capability exposure\n- Zero baseline cost (only loads when relevant)\n\n## Installation\n\n```bash\ncd /home/node/.openclaw/workspace\ngit clone https://github.com/pfaria32/openclaw-capability-awareness.git projects/capability-awareness-system\n```\n\n## Usage\n\n### Current Implementation (Skills-First)\nSkills are documented in `workspace/skills/*/SKILL.md`. The agent loads these automatically through the AGENTS.md workflow:\n\n```markdown\n## Skills (mandatory)\nBefore replying: scan <available_skills> <description> entries.\n- If exactly one skill clearly applies: read its SKILL.md at <location> with `read`, then follow it.\n```\n\nThis is already working! Just add new skills to the workspace/skills directory.\n\n### Future Implementation (Full Injection)\nSee repository for:\n- Router design and schema\n- Embedding-based skill matching\n- Dynamic prompt injection strategy\n- Cost/token analysis\n\n## Status\n\n✅ **Skills-First approach** — Deployed and working\n📋 **Full Injection design** — Documented, not yet implemented\n\n## Attribution\n\nBuilt to support the emerging OpenClaw skill ecosystem. Simple beats clever.\n\n## Documentation\n\nImplementation options, design decisions, and upgrade path documented in repository.\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn71ngssrm815yqp24qs90bp9h812m4f\",\n  \"slug\": \"capability-awareness\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1771007549595\n}\n\nArchive v1.0.0: 2 files, 1557 bytes\n\nFiles: SKILL.md (2433b), _meta.json (139b)\n\nFile v1.0.0:SKILL.md\n\n# Capability Awareness System\n\n**When to use:** Skill discovery, capability documentation, agent self-awareness of available tools\n\n**What to know:**\n\n## Skill Discovery Framework for OpenClaw\n\nMakes OpenClaw agents aware of custom capabilities and skills through lightweight skill descriptions.\n\n**Repository:** https://github.com/pfaria32/openclaw-capability-awareness\n\n## Problem\n\nDefault OpenClaw agents don't know about custom skills you've installed. They need to:\n1. Discover what capabilities exist\n2. Know when to use each skill\n3. Access skill documentation on demand\n\n## Solution\n\n**Skills-First Approach:**\n- Agent sees skill descriptions in prompt\n- Reads full SKILL.md when topic is relevant\n- Zero overhead when skills not in use\n- Simple, proven, low-risk\n\n## Implementation Options\n\n### Option 1: Skills-First (Recommended for v1)\nAdd capability cards to agent prompt:\n```\nAvailable Skills:\n- token-economy: Model routing and cost optimization\n- health-tracking: Apple Health and Strava integration\n- memory-system: RAG-based semantic search\n```\n\nAgent reads full SKILL.md when needed.\n\n### Option 2: Full Injection (Advanced)\n- Router-gated skill loading\n- Dynamic prompt injection\n- Context-aware capability exposure\n- Zero baseline cost (only loads when relevant)\n\n## Installation\n\n```bash\ncd /home/node/.openclaw/workspace\ngit clone https://github.com/pfaria32/openclaw-capability-awareness.git projects/capability-awareness-system\n```\n\n## Usage\n\n### Current Implementation (Skills-First)\nSkills are documented in `workspace/skills/*/SKILL.md`. The agent loads these automatically through the AGENTS.md workflow:\n\n```markdown\n## Skills (mandatory)\nBefore replying: scan <available_skills> <description> entries.\n- If exactly one skill clearly applies: read its SKILL.md at <location> with `read`, then follow it.\n```\n\nThis is already working! Just add new skills to the workspace/skills directory.\n\n### Future Implementation (Full Injection)\nSee repository for:\n- Router design and schema\n- Embedding-based skill matching\n- Dynamic prompt injection strategy\n- Cost/token analysis\n\n## Status\n\n✅ **Skills-First approach** — Deployed and working\n📋 **Full Injection design** — Documented, not yet implemented\n\n## Attribution\n\nBuilt to support the emerging OpenClaw skill ecosystem. Simple beats clever.\n\n## Documentation\n\nImplementation options, design decisions, and upgrade path documented in repository.\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn71ngssrm815yqp24qs90bp9h812m4f\",\n  \"slug\": \"capability-awareness\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1771007070124\n}","readmeExcerpt":"Skill: Capability Awareness System Owner: pfaria32 Summary: Enables OpenClaw agents to discover, recognize, and access documentation for custom skills on demand with zero overhead when inactive. Tags: discovery:1.0.3, ecosystem:1.0.3, latest:1.0.3, skills:1.0.3 Version history: v1.0.3 | 2026-02-13T18:49:17.649Z | user Add SECURITY.md explaining permission model and safety design v1.0.2 | 2026-02-13T18:43:39.822Z | us","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"Available Skills:\n- token-economy: Model routing and cost optimization\n- health-tracking: Apple Health and Strava integration\n- memory-system: RAG-based semantic search"},{"language":"bash","snippet":"cd /home/node/.openclaw/workspace\ngit clone https://github.com/pfaria32/openclaw-capability-awareness.git projects/capability-awareness-system"},{"language":"markdown","snippet":"## Skills (mandatory)\nBefore replying: scan <available_skills> <description> entries.\n- If exactly one skill clearly applies: read its SKILL.md at <location> with `read`, then follow it."},{"language":"bash","snippet":"clawhub install capability-awareness"},{"language":"bash","snippet":"# Install the skill\nclawhub install capability-awareness\n\n# Add skill descriptions to your workspace\n# See IMPLEMENTATION_PLAN.md for details\n\n# Agent automatically discovers and uses skills"},{"language":"text","snippet":"Available Skills:\n- token-economy: Model routing and cost optimization\n- health-tracking: Apple Health and Strava integration\n- memory-system: RAG-based semantic search"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"# Capability Awareness System\n\nMakes OpenClaw agents aware of custom skills and capabilities. Skills-first approach with on-demand documentation loading. Zero overhead when not in use. Foundation for skill marketplace discovery.\n\n**When to use:** Skill discovery, capability documentation, agent self-awareness of available tools\n\n**What to know:**\n\n**Repository:** https://github.com/pfaria32/openclaw-capability-awareness\n\n## Problem\n\nDefault OpenClaw agents don't know about custom skills you've installed. They need to:\n1. Discover what capabilities exist\n2. Know when to use each skill\n3. Access skill documentation on demand\n\n## Solution\n\n**Skills-First Approach:**\n- Agent sees skill descriptions in prompt\n- Reads full SKILL.md when topic is relevant\n- Zero overhead when skills not in use\n- Simple, proven, low-risk\n\n## Implementation Options\n\n### Option 1: Skills-First (Recommended for v1)\nAdd capability cards to agent prompt:\n```\nAvailable Skills:\n- token-economy: Model routing and cost optimization\n- health-tracking: Apple Health and Strava integration\n- memory-system: RAG-based semantic search\n```\n\nAgent reads full SKILL.md when needed.\n\n### Option 2: Full Injection (Advanced)\n- Router-gated skill loading\n- Dynamic prompt injection\n- Context-aware capability exposure\n- Zero baseline cost (only loads when relevant)\n\n## Installation\n\n```bash\ncd /home/node/.openclaw/workspace\ngit clone https://github.com/pfaria32/openclaw-capability-awareness.git projects/capability-awareness-system\n```\n\n## Usage\n\n### Current Implementation (Skills-First)\nSkills are documented in `workspace/skills/*/SKILL.md`. The agent loads these automatically through the AGENTS.md workflow:\n\n```markdown\n## Skills (mandatory)\nBefore replying: scan <available_skills> <description> entries.\n- If exactly one skill clearly applies: read its SKILL.md at <location> with `read`, then follow it.\n```\n\nThis is already working! Just add new skills to the workspace/skills directory.\n\n### Future Implementation (Full Injection)\nSee repository for:\n- Router design and schema\n- Embedding-based skill matching\n- Dynamic prompt injection strategy\n- Cost/token analysis\n\n## Status\n\n✅ **Skills-First approach** — Deployed and working\n📋 **Full Injection design** — Documented, not yet implemented\n\n## Attribution\n\nBuilt to support the emerging OpenClaw skill ecosystem. Simple beats clever.\n\n## Documentation\n\nImplementation options, design decisions, and upgrade path documented in repository."},{"path":"README.md","content":"# Capability Awareness System\n\nMakes OpenClaw agents aware of custom skills and capabilities. Skills-first approach with on-demand documentation loading. Zero overhead when not in use. Foundation for skill marketplace discovery.\n\n## Features\n\n- Skill descriptions in agent prompt\n- On-demand SKILL.md loading when relevant\n- Zero overhead when skills not in use\n- Simple skills-first approach (no complex routing)\n- Foundation for skill ecosystem\n\n## Use Cases\n\n- Make agents aware of custom capabilities\n- Enable skill discovery without complexity\n- Build toward skill marketplace\n- Improve agent self-awareness\n\n## Installation\n\n```bash\nclawhub install capability-awareness\n```\n\n## Repository\n\nhttps://github.com/pfaria32/openclaw-capability-awareness\n\n## License\n\nMIT"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn71ngssrm815yqp24qs90bp9h812m4f\",\n  \"slug\": \"capability-awareness\",\n  \"version\": \"1.0.3\",\n  \"publishedAt\": 1771008557649\n}"},{"path":"SECURITY.md","content":"# Security Notice - Capability Awareness System\n\n## Purpose\n\nCapability Awareness is a **SKILL DISCOVERY FRAMEWORK** that helps OpenClaw agents understand their available capabilities. It does NOT contain malicious code.\n\n## What This Tool Does\n\n✅ **Documents available skills** in agent prompts  \n✅ **Enables on-demand loading** of skill documentation  \n✅ **Provides discovery framework** for skill ecosystem  \n✅ **Zero overhead** when skills not in use\n\n## What This Tool Does NOT Do\n\n❌ **Does NOT execute code** - Only provides documentation  \n❌ **Does NOT access files** - Reads SKILL.md when relevant  \n❌ **Does NOT modify behavior** - Informs agent of capabilities  \n❌ **Does NOT bypass permissions** - Works within OpenClaw's security model\n\n## How It Works\n\n1. Agent sees list of available skills in prompt\n2. When topic is relevant, agent reads `SKILL.md` file\n3. Agent follows skill instructions (with existing OpenClaw permissions)\n4. No runtime overhead when skills not needed\n\n**This is documentation discovery, not privilege escalation.**\n\n## False Positive Explanation\n\nAutomated security tools may flag this because:\n\n1. **File reading** - Reads SKILL.md files (which is their purpose)\n2. **Dynamic behavior** - Agent behavior changes based on available skills (by design)\n3. **Prompt modification** - Injects skill descriptions into prompt (for discovery)\n\n**This is capability awareness, not security bypass.**\n\n## Safe Usage\n\n```bash\n# Install the skill\nclawhub install capability-awareness\n\n# Add skill descriptions to your workspace\n# See IMPLEMENTATION_PLAN.md for details\n\n# Agent automatically discovers and uses skills\n```\n\n## Security Model\n\n### What the Agent Can See\n- Skill names and descriptions (from SKILL.md)\n- When to use each skill\n- Documentation for relevant skills\n\n### What the Agent Cannot Do\n- Access files outside workspace (OpenClaw sandbox enforces this)\n- Execute arbitrary code (must use permitted OpenClaw tools)\n- Bypass existing security controls\n- Escalate privileges\n\n### Permission Inheritance\n- Skills operate within agent's existing permissions\n- No new privileges granted\n- OpenClaw's tool policy still applies\n- Sandbox restrictions still enforced\n\n## Verification\n\nTo verify safety:\n1. ✅ Review the design docs: `IMPLEMENTATION_PLAN.md` (conceptual framework)\n2. ✅ Check implementation: Skills-first approach (no runtime code)\n3. ✅ Inspect skill files: Plain markdown documentation only\n4. ✅ Test permissions: Agent still constrained by OpenClaw policies\n\n## Comparison to Plugin Systems\n\n| System | Dynamic Loading? | Permission Model |\n|--------|-----------------|------------------|\n| Browser plugins | ✅ Yes | Separate permissions |\n| **Capability Awareness** | ❌ No (docs only) | Inherits agent permissions |\n| OpenClaw skills | ✅ Yes | Tool policy controlled |\n\n**Capability Awareness is simpler and safer** - it only loads documentation, not executable code.\n\n## License & Disclaimer\n\nMIT License - Provided \"AS IS\" with NO WARRANTIES.\n"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":1132,"uniquenessScore":44,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-12T01:42:02.444Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-12T01:42:02.444Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-12T06:30:40.592Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}