forgeplan/marketplace (agentic-rag)

Agentic RAG methodology for Claude Code skills — how to structure large knowledge bases using SKILL.md as a thin router, sections/_index.md as a table of contents, and 30-50 line content files as the actual knowledge. Use when building a skill with >300 lines or >5 distinct topics, or when users ask about SKILL.md structure, sections pattern, skill authoring methodology, knowledge base design, or how to write a large Claude Code skill. Методология agentic RAG для навыков Claude Code — как структурировать большие базы знаний, используя SKILL.md как тонкий роутер, sections/_index.md как оглавление и файлы по 30-50 строк как реальные знания. Применяй когда навык >300 строк или охватывает >5 тем.

Claude Skills are markdown + scripts loaded into Claude Code; scanned with the same pipeline.

Source:

github.com/forgeplan/marketplace

Provenance:

Found by crawling (provenance, not a security rating)

We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.

3 critical findings reported by agent-audit-kit. The composite score alone does not reflect this — read the per-scanner reports below.