agentleFS
jame-hvjame-hv/brse-toolkit/skills/doc-to-md/SKILL.md

doc-to-md

Skill0 starsChanged 5 days agoMITView on GitHub

Use this when project documents (Word, Excel, PowerPoint, PDF, legacy .doc/.xls, HTML) must be turned into Markdown with deterministic tools — not AI rewriting — and saved in the project so later analysis, test design and review read the same text the client wrote.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run <py> ${CLAUDE_PLUGIN_ROOT}/scripts/brse.py config and read its JSON:

    line 14
  2. Very specific:

    Standard path = ingest: Run <py> ${CLAUDE_PLUGIN_ROOT}/scripts/brse.py kb-ingest (follow commands/ingest.md).

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Before running

<py> below = the Python recorded by /brse-toolkit:setup (runtime.python in ~/.config/brse-toolkit/config.json — read that file directly), else the first of python3, python, py -3 that runs. No Python at all → tell the user to run /brse-toolkit:setup, and continue only with steps that need no script, saying which checks were skipped.

Run <py> ${CLAUDE_PLUGIN_ROOT}/scripts/brse.py config and read its JSON:

  • error → show it to the user and stop; the config file must be fixed first.
  • workspace_root is null → the folder isn't initialized. Ask once: run /brse-toolkit:init first (recommended — memory and knowledge get saved for next time) or continue once without saving. Running as a subagent dispatched by a main agent → the parent already resolved this; proceed.
  • Otherwise use config.paths (sources, templates, outputs — relative to workspace_root), config.style, config.translation, and the files in .brse/memory/long/. Never assume a folder name the config doesn't list.
  • warnings not empty → mention them in one line (likely a typo in the config).

When to use

First step before analysing a spec, designing test cases or reviewing a document set. Not for translation or summarising — this skill never rewrites a word.

Rules

  • Tools only, no AI. Text comes from scripts, never retyped, paraphrased, "cleaned up" or translated. If a conversion is wrong, fix the conversion.
  • One place for converted text: .brse/knowledge/docs/ (the same place /brse-toolkit:ingest uses). Never touch the originals.

Steps

  1. Standard path = ingest. Run <py> ${CLAUDE_PLUGIN_ROOT}/scripts/brse.py kb-ingest (follow commands/ingest.md). It converts every file under paths.sources / internal / deliverables, writes the Markdown copies, manifest.json and the search index, and skips unchanged files.
  2. Fallback for files ingest marks unreadable (legacy .doc/.xls/.ppt, .rtf, .odt, odd PDFs): run <py> ${CLAUDE_PLUGIN_ROOT}/scripts/brse.py doc2md <file> --out <workspace_root>/.brse/knowledge/docs/<its source folder> (MarkItDown, LibreOffice round-trip, pdftotext). Say which files used it. Outside an initialized workspace (one-off), the same script with --out <source folder>/docs-md/ — and say nothing is indexed.
  3. partial files (shapes, images, charts, flow sheets, screen images): read them with excel-analyze / image-analyze; never present the Markdown copy as the complete content.
  4. Scanned PDF with no text → say OCR is needed; never invent the text.

Output

Counts (converted / unchanged / partial / unreadable), the list of partial and unreadable files inline, and the fallback files.

Handoff

Next skills read .brse/knowledge/docs/ and search with brse.py kb-search: scope-analysis, test-design, business-explain, testcase-review-jp. Finish with verify-output on the reply.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.