Repository
lyonzin/knowledge-rag agent skills
- skills
- 10
- GitHub stars
- 290
GitHub description: “Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools, 20 format parsers. Zero external servers, zero API keys.”
- Stars
- 290 (43 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Feb 2026
- Homepage
- pypi.org/project/knowledge-rag
- claude
- claude-code
- local-ai
- mcp
- rag
- retrieval-augmented-generation
- semantic-search
- vector-database
- knowledge-base
- reranking
- document-search
- hybrid-search
- mcp-server
- antigravity
- claude-code-cli
- codex
Install all skills
npx skills add lyonzin/knowledge-ragAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in lyonzin/knowledge-rag, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Before answering any technical question, code request, architecture decision, or factual claim, call searchknowledge to check the local corpus. | lyonzin/ | 290 | — | ~1.4k | Automated safety check: Pass | MIT | 3 days ago |
| 2 | Every technical claim drawn from the local corpus must ship with a source citation formatted as path:line or path:section. | lyonzin/ | 290 | — | ~1.4k | Automated safety check: Pass | MIT | 3 days ago |
| 3 | When performing code review on a PR, diff, snippet, or "look at this change" request, first consult the corpus for related ADRs, coding standards, prior patterns, and similar files. | lyonzin/ | 290 | — | ~1.8k | Automated safety check: Pass | MIT | 3 days ago |
| 4 | Three-step multi-tool workflow — search the corpus, fetch the most relevant document in full, then find similar documents. | lyonzin/ | 290 | — | ~1.6k | Automated safety check: Pass | MIT | 3 days ago |
| 5 | When the user reports a bug, error message, stack trace, unexpected behavior, or "why is this broken" question, search the corpus first for prior occurrences, known fixes, or related runbooks. | lyonzin/ | 290 | — | ~1.8k | Automated safety check: Pass | MIT | 3 days ago |
| 6 | Measure retrieval quality using evaluateretrieval (MRR@5 and Recall@5) and getindexstats. | lyonzin/ | 290 | — | ~1.4k | Automated safety check: Pass | MIT | 3 days ago |
| 7 | After making a non-obvious architectural decision, solving a novel bug, agreeing on a coding standard, or reaching a conclusion worth remembering, index it back into the knowledge base so the next… | lyonzin/ | 290 | — | ~2k | Automated safety check: Pass | MIT | 3 days ago |
| 8 | At the start of every new session or when the topic shifts significantly, probe the knowledge base to learn what is indexed. | lyonzin/ | 290 | — | ~1.5k | Automated safety check: Pass | MIT | 3 days ago |
| 9 | For any security-related task — threat triage, incident response, MITRE ATT&CK mapping, CVE lookup, exploit analysis, defensive control validation, red/blue/purple team work — always consult the… | lyonzin/ | 290 | — | ~2.3k | Automated safety check: Pass | MIT | 3 days ago |
| 10 | Only reach for external web search when the local corpus comes back empty or clearly insufficient. | lyonzin/ | 290 | — | ~1.4k | Automated safety check: Pass | MIT | 3 days ago |
Questions, answered from the data.
What is the best skill in lyonzin/knowledge-rag?
RAG Check First from lyonzin/knowledge-rag ranks first of the 10 skills in lyonzin/knowledge-rag listed here, with the highest score: its repository has 290 GitHub stars, its SKILL.md loads about 1.4k tokens and it passes the automated safety check with no findings. Next come RAG Cite Sources and RAG Code Review.
Are the skills in lyonzin/knowledge-rag official?
None yet. All 10 skills in lyonzin/knowledge-rag listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from lyonzin/knowledge-rag?
Run npx skills add lyonzin/knowledge-rag in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.