local-vault
Build and query a local Markdown knowledge base ("vault"). TWO functions — (1) CONVERT raw files (PDF, Word/docx, PowerPoint/pptx, Excel/xlsx, csv/tsv, images, html, md/txt, json/yaml/code, audio/video) into clean Markdown with retrieval-friendly frontmatter; local-first (pandoc / python-pptx / openpyxl / pymupdf4llm / whisper), with cloud OCR (MinerU) only as a fallback. (2) ANSWER questions over the resulting vault with retrieval discipline — self-monitor coverage, flag missing/lossy content, and propose Maps-of-Content (MOCs). Triggers: "build/sync my local knowledge base", "convert these f
npx skills add genli-ai/market-research-skills --skill local-vault --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# local-vault Turn a folder of raw files into a **Markdown vault** that an LLM can grep, and then answer questions over that vault responsibly. **Mental model:** `SOURCE` = raw files (source of truth). `VAULT` = one `.md` per source file, carrying retrieval frontmatter (abstract / tags / synonyms) + a `source` backlink. The vault is the layer the LLM reads; the raw files are where the user goes to verify. There are **two distinct jobs** — figure out which the user wants: - **A. Convert / sync** — they dropped files in and want them in the vault → run the pipeline (`scripts/sync.py`). - **B. Retrieve / answer** — they want answers from an existing vault → follow the *Retrieval & feedback protocol* below. Do **not** run the pipeline for this. --- ## A. Convert / sync ### One-time setup (do this for the user if not already done) 1. **Python deps** (user-level, no venv): ``` python3 -m pip install --user requests python-dotenv pypdf pymupdf4llm openpyxl python-pptx ``` 2. **pandoc** (for docx/rtf/odt/epub): `brew install pandoc` (macOS) / distro pkg. 3. **ffmpeg** (only for audio/video transcription): `brew install ffmpeg` (macOS) / distro pkg. The **whisper engine is auto-selected by
- A. Convert / sync
- One-time setup (do this for the user if not already done)
- Run it
- Routing (which tool per file type)
- PPT smart OCR
- Frontmatter written to every .md
- Tuning (scripts/config.py)
- B. Retrieval & feedback protocol (answering over the vault)
- Startup vault health check (first vault question of a session)
- Self-checks after a complex query (warn only when triggered)
- Topic queries → MOC entry order + evolution
- Do not
- Notes
What does the local-vault skill do?
Build and query a local Markdown knowledge base ("vault"). TWO functions — (1) CONVERT raw files (PDF, Word/docx, PowerPoint/pptx, Excel/xlsx, csv/tsv, images, html, md/txt, json/yaml/code, audio/video) into clean Markdown with retrieval-friendly frontmatter; local-first (pandoc / python-pptx / openpyxl / pymupdf4llm / whisper), with cloud OCR (MinerU) only as a fallback. (2) ANSWER questions over the resulting vault with retrieval discipline — self-monitor coverage, flag missing/lossy content, and propose Maps-of-Content (MOCs). Triggers: "build/sync my local knowledge base", "convert these f
How do I install it?
Run `npx skills add genli-ai/market-research-skills --skill local-vault --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From genli-ai/market-research-skills, a repository with 57 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.