agentleFS
Sign inStart free
devnu11devnu11/claude-skills/.team/CLAUDE.md

claude-skills

CLAUDE.md1 starsChanged 20 days agoMITView on GitHub

Every role reads this file, right after the repo instructions (.claude/CLAUDE.md, shown above as "Repo instructions"). Those rules apply to the team as written and are not repeated here. This file holds only what is about the team. Keep it short. claude-skills holds Claude Code skills. You are working on the agile-team skill: its runner (agile-team/runner/, Python, uv) is the program that runs you. Read agile-team/reference/protocol.md for how it works today. - Run every tool from the repo root through…

The file

We split this CLAUDE.md into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Every role reads this file, right after the repo instructions (.claude/CLAUDE.md, shown above as "Repo instructions").

    line 3
  2. Very specific:

    Run every tool from the repo root through the configured commands (uv run --directory agile-team/runner …).

    line 17
  3. Distinctive:

    No new runtime dependencies without an ADR.

    line 24
  4. Very specific:

    Product Backlog: every open story not committed to a sprint (sprint is null in state.json).

    line 36
  5. Distinctive:

    Always say Product Backlog or Sprint Backlog, never just "backlog".

    line 41

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
CLAUDE.md

Team charter

Every role reads this file, right after the repo instructions (.claude/CLAUDE.md, shown above as "Repo instructions"). Those rules apply to the team as written and are not repeated here. This file holds only what is about the team. Keep it short.

What this repo is

claude-skills holds Claude Code skills. You are working on the agile-team skill: its runner (agile-team/runner/, Python, uv) is the program that runs you. Read agile-team/reference/protocol.md for how it works today.

House rules

  • Run every tool from the repo root through the configured commands (uv run --directory agile-team/runner …); never cd.
  • Functions: one job, ideally under 8 lines, at most 2 parameters (constructors excepted). No boolean parameters or flags; use an enum.
  • Docstrings on public functions, brief. Comments inside functions only for non-obvious pitfalls.
  • Coverage is currently 100%; keep it there.
  • No new runtime dependencies without an ADR. The dashboard uses the stdlib only (http.server, SSE).
  • Docs move in the same story as the code.
  • The test suite points AGILE_TEAM_HOME at a scratch dir.

Domain vocabulary

  • story: a unit of work in .team/stories/<id>.md; AC = acceptance criterion.
  • requirement: agile-team/docs/requirements/REQ-NNN.md.
  • liaison: the interactive Claude session relaying to the human.
  • snapshot: the JSON the dashboard renders; its contract is agile-team/runner/agile_team/dashboard/fixtures/snapshot.json.
  • Product Backlog: every open story not committed to a sprint (sprint is null in state.json). The runner, the docs and the dashboard still call this "the backlog".
  • Sprint Backlog: the stories committed to the current sprint that are not done.
  • Always say Product Backlog or Sprint Backlog, never just "backlog". When anyone, the human included, says only "backlog" and it matters which one, ask which they mean before acting.

Do not touch

  • install.sh, tests/install_test.sh, example-skill/.
  • .claude/ (the human's repo instructions; you read them, never write them).

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.

Check your setup, free