agentleFS
Sign inStart free
DRAZYDRAZY/claude-skills/CLAUDE.md

claude-skills

CLAUDE.md1 starsChanged 59 days agoMITView on GitHub

Project-scoped conventions for this repo. These live next to the code they govern rather than in a global config. Skills in this repo are scoped to local, self-directed work where the user stays in the loop and drives each step. Contributions that recommend external or third-party services holding account-level automation access — a tool that acts on someone's social account, for example — are declined as out-of-scope, not as low quality. Say so plainly when declining; the distinction matters to…

The file

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

2 rules. About 0 are common, 2 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never overwrite or clobber skills this repo doesn't own.

    line 23
  2. Distinctive:

    Always offer a preview step before writing changes.

    line 24

≈ “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

claude-skills — project rules

Project-scoped conventions for this repo. These live next to the code they govern rather than in a global config.

Scope

Skills in this repo are scoped to local, self-directed work where the user stays in the loop and drives each step.

Contributions that recommend external or third-party services holding account-level automation access — a tool that acts on someone's social account, for example — are declined as out-of-scope, not as low quality. Say so plainly when declining; the distinction matters to the contributor.

Sync scripts

Sync scripts that update a local install live inside this repo, and they must be surgical:

  • Touch only this repo's own skills within ~/.claude/skills/. A live install carries 50+ unrelated skills alongside them.
  • Never overwrite or clobber skills this repo doesn't own.
  • Always offer a preview step before writing changes.

Blog-writer skill

The blog-writer skill is universal and topic-agnostic, standing alongside the script-writer skill. It is deliberately not security-locked: security is one archetype among several, alongside tutorial walkthroughs, market and industry analysis, commentary, and vulnerability writeups.

It supports variable length, from short posts to in-depth long-form. Publishing homes each carry their own voice and format profile (a personal site and a work blog are different targets). When given only an angle or topic, the skill asks clarifying questions to sharpen context before drafting.

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