agentleFS
Sign inStart free
tandregbgtandregbg/core-claude-skills/CLAUDE.md

core-claude-skills

CLAUDE.md4 starsChanged 8 days agoMITView on GitHub

Claude Code skills for operational documentation, transcript processing, task tracking and team coordination, with a knowledge loop (insights corpus, standing rules, knowledge wiki). Start with README.md; the shared contract every skill and companion tool reads is ecosystem.yaml. This repo is public and the vault it runs on is production data: docs/RELEASING.md (CR-026) is the release process and its privacy guardrails, enforced by the pre-push guard. - CRs are CR-nnn here (CS-CR-nnn seen from other repos). The public index is docs/proposals/README.md…

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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. Very specific:

    Commit real names, organisations, hosts, internal addresses or credentials (docs/RELEASING.md).

    line 39
  2. Distinctive:

    Use emojis in code, docs or commit messages.

    line 40

≈ “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

core-skills — project guidelines

Claude Code skills for operational documentation, transcript processing, task tracking and team coordination, with a knowledge loop (insights corpus, standing rules, knowledge wiki). Start with README.md; the shared contract every skill and companion tool reads is ecosystem.yaml. This repo is public and the vault it runs on is production data: docs/RELEASING.md (CR-026) is the release process and its privacy guardrails, enforced by the pre-push guard.

CRs, releases, versions

  • CRs are CR-nnn here (CS-CR-nnn seen from other repos). The public index is docs/proposals/README.md (generic title rows only); full specs stay in the private archive.
  • Releases go in CHANGELOG.md, newest first; README.md Version and ecosystem.yaml core_skills_version match the first entry. Run scripts/check-ecosystem-alignment.sh before a release commit; one release is one commit.
  • This repo's own ops board is docs/ops/ops-status.md (index docs/ops/README.md): what is released, what is configured, what waits. Start here for this product; a release updates it the same day.
  • A checkout may be shared: commit only your own files; never stash, reset or discard someone else's work.

Deep Thought

core-skills is a sibling product family, not a Deep Thought component, and nothing in it is a Deep Thought dependency. It is the other way to use Deep Thought's output: a user who does not want the platform's own processing (its extraction and insights) runs Claude Code with core-skills on Deep Thought's content instead, read over the MCP tools, the Public API or the meeting handover (deep-thought-handover, which runs /transcript on one Deep Thought transcript in an isolated workspace). In Deep Thought's five steps that is step 3 Asked and step 4 Kept.

  • The contract read is Deep Thought's: docs/reference/public-api.md and the MCP tools in the deep-thought-server repository. A change there that breaks a skill is a Deep Thought CR.
  • Deep Thought's state and plan live in that repository too: docs/ops/ops-status.md (what runs now) and the Waves table in docs/change-requests/README.md; the ecosystem map, including this family's row, is docs/architecture/ecosystem-components.md.

Never

  • Commit real names, organisations, hosts, internal addresses or credentials (docs/RELEASING.md).
  • Use emojis in code, docs or commit messages.

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