agentleFS
DeepSpaceCartelDeepSpaceCartel/skills/CLAUDE.md

skills

CLAUDE.md2 starsChanged 2 months agoMITView on GitHub

This repo is a pack of project-agnostic Agent Skills (skills/<name>/SKILL.md + optional skills/<name>/references/*.md), published for npx skills add DeepSpaceCartel/skills[/skills/<name>]. Adding a new skill touches three files. It's easy to do only the first and silently leave the pack's own index stale: 1. skills/<name>/SKILL.md (+ references/ if the body would exceed ~500 lines / ~5000 tokens). name in frontmatter must equal the directory name; description must state what it covers and when to use it (that's the entire activation signal —…

The file

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

1 rule. About 0 are common, 0 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Look at semver, keepachangelog, and mkdocs before writing a new skill — they're the clearest examples of the pack's actual voice: terse …

    line 32

≈ “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

DeepSpaceCartel Skills — working notes

This repo is a pack of project-agnostic Agent Skills (skills/<name>/SKILL.md + optional skills/<name>/references/*.md), published for npx skills add DeepSpaceCartel/skills[/skills/<name>].

Adding or renaming a skill — three places, not one

Adding a new skill touches three files. It's easy to do only the first and silently leave the pack's own index stale:

  1. skills/<name>/SKILL.md (+ references/ if the body would exceed ~500 lines / ~5000 tokens). name in frontmatter must equal the directory name; description must state what it covers and when to use it (that's the entire activation signal — see skills/skill/SKILL.md for the full spec).
  2. skills.sh.json — add the skill to an existing groupings[] entry, or add a new grouping if none fits. Validate it's still valid JSON after editing.
  3. README.md — add a row to the matching category's table (README's sections mirror skills.sh.json's groupings[] 1:1, in the same order — add a new ### section if you added a new grouping), alphabetically by skill name within that table, in the existing | [name](skills/name/SKILL.md) | one-line summary (spec link) | format.

Renaming or removing a skill means updating all three the same way, plus checking for cross-skill relative links (e.g. keepachangelog/SKILL.md links to ../semver/SKILL.md).

Style precedent to match

Look at semver, keepachangelog, and mkdocs before writing a new skill — they're the clearest examples of the pack's actual voice: terse rule-first prose, a worked example before/after, and (for larger skills) a "Where to look" table pointing into references/. skills/skill/SKILL.md is the meta-skill describing the format itself — read it when in doubt about frontmatter or directory conventions.

Committing

This repo is the user's own; changes here are otherwise treated like any other git repo — don't commit unless asked.

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.