What makes Capability Awareness System notable?

960 downloads. Trust evidence available

How should Capability Awareness System be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Capability Awareness System

Enables OpenClaw agents to discover, recognize, and access documentation for custom skills on demand with zero overhead when inactive.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

960

Updated

Oct 12, 2026

Version

1.0.3

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 960 downloads reported by the source. Last updated 10/12/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 12, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 12, 2026
Adoption signal: 960 downloadsadoption · observed Oct 12, 2026
Latest release: 1.0.3release · observed Feb 13, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 1.0.3release
Add SECURITY.md explaining permission model and safety design
Observed Feb 13, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s1784t0fbkq71wwrqn5ftvbjr5885jqc:capability-awareness

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: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-pfaria32-capability-awareness/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

16,698 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

# Capability Awareness System

Makes 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.

**When to use:** Skill discovery, capability documentation, agent self-awareness of available tools

**What to know:**

**Repository:** https://github.com/pfaria32/openclaw-capability-awareness

## Problem

Default OpenClaw agents don't know about custom skills you've installed. They need to:
1. Discover what capabilities exist
2. Know when to use each skill
3. Access skill documentation on demand

## Solution

**Skills-First Approach:**
- Agent sees skill descriptions in prompt
- Reads full SKILL.md when topic is relevant
- Zero overhead when skills not in use
- Simple, proven, low-risk

## Implementation Options

### Option 1: Skills-First (Recommended for v1)
Add capability cards to agent prompt:
```
Available Skills:
- token-economy: Model routing and cost optimization
- health-tracking: Apple Health and Strava integration
- memory-system: RAG-based semantic search
```

Agent reads full SKILL.md when needed.

### Option 2: Full Injection (Advanced)
- Router-gated skill loading
- Dynamic prompt injection
- Context-aware capability exposure
- Zero baseline cost (only loads when relevant)

## Installation

```bash
cd /home/node/.openclaw/workspace
git clone https://github.com/pfaria32/openclaw-capability-awareness.git projects/capability-awareness-system
```

## Usage

### Current Implementation (Skills-First)
Skills are documented in `workspace/skills/*/SKILL.md`. The agent loads these automatically through the AGENTS.md workflow:

```markdown
## Skills (mandatory)
Before replying: scan <available_skills> <description> entries.
- If exactly one skill clearly applies: read its SKILL.md at <location> with `read`, then follow it.
```

This is already working! Just add new skills to the workspace/skills directory.

### Future Implementation (Full Injection)
See repository for:
- Router design and schema
- Embedding-based skill matching
- Dynamic prompt injection strategy
- Cost/token analysis

## Status

✅ **Skills-First approach** — Deployed and working
📋 **Full Injection design** — Documented, not yet implemented

## Attribution

Built to support the emerging OpenClaw skill ecosystem. Simple beats clever.

## Documentation

Implementation options, design decisions, and upgrade path documented in repository.

README.md

# Capability Awareness System

Makes 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.

## Features

- Skill descriptions in agent prompt
- On-demand SKILL.md loading when relevant
- Zero overhead when skills not in use
- Simple skills-first approach (no complex routing)
- Foundation for skill ecosystem

## Use Cases

- Make agents aware of custom capabilities
- Enable skill discovery without complexity
- Build toward skill marketplace
- Improve agent self-awareness

## Installation

```bash
clawhub install capability-awareness
```

## Repository

https://github.com/pfaria32/openclaw-capability-awareness

## License

MIT

_meta.json

{
  "ownerId": "kn71ngssrm815yqp24qs90bp9h812m4f",
  "slug": "capability-awareness",
  "version": "1.0.3",
  "publishedAt": 1771008557649
}

SECURITY.md

# Security Notice - Capability Awareness System

## Purpose

Capability Awareness is a **SKILL DISCOVERY FRAMEWORK** that helps OpenClaw agents understand their available capabilities. It does NOT contain malicious code.

## What This Tool Does

✅ **Documents available skills** in agent prompts
✅ **Enables on-demand loading** of skill documentation
✅ **Provides discovery framework** for skill ecosystem
✅ **Zero overhead** when skills not in use

## What This Tool Does NOT Do

❌ **Does NOT execute code** - Only provides documentation
❌ **Does NOT access files** - Reads SKILL.md when relevant
❌ **Does NOT modify behavior** - Informs agent of capabilities
❌ **Does NOT bypass permissions** - Works within OpenClaw's security model

## How It Works

1. Agent sees list of available skills in prompt
2. When topic is relevant, agent reads `SKILL.md` file
3. Agent follows skill instructions (with existing OpenClaw permissions)
4. No runtime overhead when skills not needed

**This is documentation discovery, not privilege escalation.**

## False Positive Explanation

Automated security tools may flag this because:

1. **File reading** - Reads SKILL.md files (which is their purpose)
2. **Dynamic behavior** - Agent behavior changes based on available skills (by design)
3. **Prompt modification** - Injects skill descriptions into prompt (for discovery)

**This is capability awareness, not security bypass.**

## Safe Usage

```bash
# Install the skill
clawhub install capability-awareness

# Add skill descriptions to your workspace
# See IMPLEMENTATION_PLAN.md for details

# Agent automatically discovers and uses skills
```

## Security Model

### What the Agent Can See
- Skill names and descriptions (from SKILL.md)
- When to use each skill
- Documentation for relevant skills

### What the Agent Cannot Do
- Access files outside workspace (OpenClaw sandbox enforces this)
- Execute arbitrary code (must use permitted OpenClaw tools)
- Bypass existing security controls
- Escalate privileges

### Permission Inheritance
- Skills operate within agent's existing permissions
- No new privileges granted
- OpenClaw's tool policy still applies
- Sandbox restrictions still enforced

## Verification

To verify safety:
1. ✅ Review the design docs: `IMPLEMENTATION_PLAN.md` (conceptual framework)
2. ✅ Check implementation: Skills-first approach (no runtime code)
3. ✅ Inspect skill files: Plain markdown documentation only
4. ✅ Test permissions: Agent still constrained by OpenClaw policies

## Comparison to Plugin Systems

| System | Dynamic Loading? | Permission Model |
|--------|-----------------|------------------|
| Browser plugins | ✅ Yes | Separate permissions |
| **Capability Awareness** | ❌ No (docs only) | Inherits agent permissions |
| OpenClaw skills | ✅ Yes | Tool policy controlled |

**Capability Awareness is simpler and safer** - it only loads documentation, not executable code.

## License & Disclaimer

MIT License - Provided "AS IS" with NO WARRANTIES.

Github ReposUpdated 2d agoRank 70

AionUi

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!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

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

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular