agentleFS
youdcodeyoudcode/open-company/.agents/skills/knowledge/SKILL.md

knowledge

Skill2 starsChanged 52 days agoMITView on GitHub

Reads the owner's own documents (a folder added under "Readable folders") and writes a knowledge base in workspace/company/knowledge/: one index plus short digests, every fact carrying the path of its source file. Use when the owner says "read my documents", "learn my company", "use my folder", or when the team keeps missing context.

13 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use status.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check the folder is readable: it must be in the chat's "Readable folders" (the chat note lists them).

    line 11
  2. Very specific:

    Write in workspace/company/knowledge/ (front matter author, updated, source):

    line 16
  3. Distinctive:

    Keep it cheap to use: the index stays under 120 lines, each digest under 200.

    line 27

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “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

Knowledge base

Goal: after this, any role can start working without reading gigabytes again, and every fact can be traced back to the owner's own file.

  1. Check the folder is readable: it must be in the chat's "Readable folders" (the chat note lists them). If not, ask the owner to add it; never guess a path.
  2. Map before reading: list the folders, then open the files that decide things first (a brief, a journal or decision log, the current business plan, the go-to-market, the product doc). Skip code directories, media, and anything over a few hundred kilobytes unless the owner asks.
  3. Write in workspace/company/knowledge/ (front matter author, updated, source):
    • INDEX.md: the map. For each folder: what it is for, which 2 or 3 files to open first, what is out of date. Ends with "Where to find what": one line per subject pointing to a file.
    • Digests, one per subject that matters, for example brief.md (positioning and wording rules, including what must never be said), product.md, market.md, gtm.md, numbers.md (every figure with its status: fact, hypothesis, scenario, external benchmark, and its source), history.md (dated decisions), open-questions.md.
  4. Rules: every fact carries its source file path. Never invent a number. When two files contradict each other, write both with their dates and say which one wins if a file says so. Keep the owner's exact wording for validated sentences (taglines, message templates). Dense lists and tables, no filler. Write in the owner's language.
  5. Keep it cheap to use: the index stays under 120 lines, each digest under 200. At session start the team reads only the index; it opens a digest or a source file when the request needs it.
  6. Tell the owner what you wrote, the contradictions you found, and what you could not read.

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.