Detect oversized projects and propose local semantic search via qmd.
npx skills add https://github.com/tody-agent/codymaster --skill cm-deep-search
Please help me install this Agent Skill. Skill: cm-deep-search Source: https://github.com/tody-agent/codymaster/tree/main/skills/cm-deep-search Command: npx skills add https://github.com/tody-agent/codymaster --skill cm-deep-search
Optional power-up — detects oversized codebases/docs and suggests tobi/qmd for local semantic search. Bridges cm-continuity (working memory) with long-term document retrieval. Zero-config detection, non-intrusive suggestion.
Install qmd globally, index your docs and source code, and run embed to enable semantic search.
High-intent search queries and answers about installing and using this skill.
To set up semantic search for a large codebase, install qmd globally, index your source code and documentation, and run embed. This enables local semantic retrieval across your project files.
Semantic search handles oversized project documentation by applying non-intrusive prompts during planning phases. It detects size thresholds and bridges in-session working memory with long-term document retrieval.
No configuration is needed to detect when a project needs local semantic search. The detection runs automatically during project scans and documentation reviews, providing non-intrusive suggestions when size thresholds are crossed.
The best way to integrate in-session memory with long-term codebase retrieval is by bridging working memory with local document search. This is achieved by installing qmd to index and embed your documentation and source code.
You should avoid using local semantic search when your project does not cross defined size thresholds. It is specifically designed as an optional power-up for oversized codebases and documentation, rather than smaller projects.
Davie521Detect Xiaohongshu trigger words and search local Spider_XHS notes.
iagocavalcanteSearch local Markdown notes using BM25 keyword and semantic similarity search.
hafiznaveedchuhan-ctrlPersist agent memory across sessions with layered working, short-term, and long-term storage.
oxc-projectManage insta snapshot tests non-interactively in the Oxc codebase.
