fitcheck-skill-searchFind and retrieve available skills using keyword search, semantic search, or LLM-powered task matching. Use when the agent needs to discover, search, or inte...
Install via ClawdBot CLI:
clawdbot install at6132/fitcheck-skill-searchFind skills using keyword, semantic, or AI-powered task matching.
This skill provides three search modes:
./scripts/skill_search.py keyword "weather"
./scripts/skill_search.py keyword "pdf"
./scripts/skill_search.py keyword "image generation"./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"./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"./scripts/skill_search.py listUser: "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 PlaywrightAgent: 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 inputThe 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 indexskill_search.py — Main search interface (keyword/semantic/LLM)indexer.py — Build/update search indexembeddings.py — Embedding generation (local miniLM)skills_index.json — Searchable skill metadataembeddings_cache.json — Pre-computed embeddings for semantic searchGenerated Mar 1, 2026
An agency uses the skill to quickly find and load relevant AI skills for client projects, such as generating images or transcribing audio. By searching with natural language task descriptions, they efficiently match skills to specific content needs, reducing setup time and ensuring the right tool is used for each job.
A support team employs the skill to discover skills for automating responses, analyzing customer data, or processing documents like PDFs. Using keyword and semantic search, they identify capabilities to handle common queries, improving response times and reducing manual workload.
Researchers use the skill to explore available AI tools for tasks like data analysis, web scraping, or image generation. The LLM task matching helps them find skills for complex, fuzzy requirements, accelerating experimentation and innovation in projects.
An edtech platform integrates the skill to help educators find and utilize skills for creating learning materials, such as generating images or transcribing lectures. Semantic search allows them to match skills based on educational concepts, enhancing content creation efficiency.
Offer the skill as part of a subscription-based AI platform, where users pay monthly for access to skill discovery and execution. Revenue comes from tiered plans based on search volume, advanced features like LLM matching, and integration with other tools.
Sell licenses to large organizations for internal use, such as automating workflows or enhancing productivity. Revenue is generated through one-time or annual fees, with added value from custom indexing, support, and integration with existing systems.
Provide basic keyword search for free to attract users, while charging for advanced features like semantic search, LLM task matching, and priority indexing. Revenue streams include premium upgrades, API usage fees, and partnerships with skill developers.
💬 Integration Tip
Integrate the skill early in agent workflows to preemptively discover relevant skills, reducing context bloat and improving response accuracy by loading only necessary tools.
Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).
AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.
This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses DuckDuckGo's search API to return results in clean, formatted output (text, markdown, or JSON). Use for research, fact-checking, finding recent information, or gathering web resources.
Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
Search indexed Discord community discussions via Answer Overflow. Find solutions to coding problems, library issues, and community Q&A that only exist in Discord conversations.
Multi search engine integration with 17 engines (8 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and WolframAlpha knowledge queries. No API keys required.