Skill Search

Find and retrieve available skills using keyword search, semantic search, or LLM-powered task matching. Use when the agent needs to discover, search, or inte...

Security Scan

The skill is internally coherent: it implements local keyword/semantic/LLM-style search over other skills by reading SKILL.md files and building a local index — the requested behavior matches the code and instructions.

Purpose & Capability

Name/description (skill discovery/search) match what the code and SKILL.md do: parsing SKILL.md frontmatter, listing skills from system and user skill directories, and performing keyword/semantic/hybrid searches. There are no unrelated credentials, binaries, or heavyweight external dependencies.

Instruction Scope

The runtime instructions and scripts read SKILL.md files from both user (~/.openclaw/workspace/skills) and system (/usr/local/lib/node_modules/openclaw/skills) locations and build a local index. This is expected for a skill indexer, but it means the skill will read the contents (and some metadata) of other skills — if any SKILL.md contains sensitive data, that data will be included in the local index.

Install Mechanism

No install spec; this is instruction/code-only and writes only to its own index directory under the skill folder. No downloads or external installers are used.

Credentials

No environment variables, external API keys, or unrelated credentials are requested. Embedding generation is local/fallback; the code does not require cloud API keys.

Persistence & Privilege

always:false and no code that modifies other skills or global agent config. It creates/updates a local index under its own index folder (expected). Autonomous invocation is enabled by default but is not excessive here given the skill's purpose.

Assessment

This skill is coherent for discovering other skills and builds a local index by reading SKILL.md files from both system and user skill directories. Before installing, review the SKILL.md files in your skills folders (and any existing index file ~/.openclaw/workspace/skills/skill-search/index/) to ensure they don't contain secrets or sensitive strings you don't want indexed. Because the index is stored locally, treat the index file like any other potentially sensitive artifact. If you prefer not to let an agent autonomously index system skills, keep the skill user-invoked only or remove system skill paths from SKILL_DIRS before running.

Skill Search V1.1

Find skills using keyword, semantic, or AI-powered task matching.

Overview

This skill provides three search modes:

1. Keyword Search (Fast BM25) — Match skill names and descriptions
2. Semantic Search (Embeddings) — Find skills by meaning/concept similarity
3. LLM Task Matching (AI-powered) — Describe your task, get skill recommendations

When to Use

• Before starting a new task — check if a relevant skill exists
• When user asks for capabilities — "what can you do with PDFs?"
• To avoid context bloat — find the right skill first, then load only that one
• When unsure which skill applies — use semantic or LLM matching for fuzzy matches

Search Modes

1. Keyword Search (Fast)

./scripts/skill_search.py keyword "weather"
./scripts/skill_search.py keyword "pdf"
./scripts/skill_search.py keyword "image generation"

2. Semantic Search (Meaning-based)

./scripts/skill_search.py semantic "automate web browsing"
./scripts/skill_search.py semantic "create images with AI"
./scripts/skill_search.py semantic "search my past conversations"

3. LLM Task Matching (AI-powered)

./scripts/skill_search.py suggest "I need to transcribe a podcast episode"
./scripts/skill_search.py suggest "Help me generate product photos"
./scripts/skill_search.py suggest "Search through my old emails"

4. List All Skills

./scripts/skill_search.py list

Usage Pattern

1. Search: Find skills matching your need (keyword/semantic/LLM)
2. Preview: Read SKILL.md metadata (description, triggers)
3. Load: If it's the right skill, read full body and execute

Example Workflows

User: "I need to generate some images"

Agent: Uses semantic search

./scripts/skill_search.py semantic "generate images AI"

Output:

Top matches (semantic):
1. openai-image-gen (0.87) — Batch-generate images via OpenAI Images API
2. browser (0.65) — Control web browser via Playwright

Agent: Reads SKILL.md, confirms fit, executes

---

User: "What skill should I use for transcribing audio?"

Agent: Uses LLM suggest

./scripts/skill_search.py suggest "transcribe audio"

Output:

Recommended skills for "transcribe audio":

1. openai-whisper-api — Transcribe audio via OpenAI Audio Transcriptions API (Whisper)
   Confidence: High
   Reason: Task explicitly matches skill purpose

2. sag — ElevenLabs text-to-speech (inverse operation, may be related)
   Confidence: Low
   Reason: Related to audio processing but output not input

Search Index

The skill maintains a local search index at:

• ~/.openclaw/workspace/skills/skill-search/index/skills_index.json — Skill metadata
• ~/.openclaw/workspace/skills/skill-search/index/embeddings.json — Semantic embeddings (lazy-loaded)

Indexing happens automatically on first semantic search if no index exists.

Force reindex:

./scripts/skill_search.py index

Resources

scripts/

• skill_search.py — Main search interface (keyword/semantic/LLM)
• indexer.py — Build/update search index
• embeddings.py — Embedding generation (local miniLM)

index/

• skills_index.json — Searchable skill metadata
• embeddings_cache.json — Pre-computed embeddings for semantic search