agentleFS
Sign inStart free
sentimonysentimony/skills/AGENTS.md

skills

AGENTS.md7 starsChanged 5 days agoMITView on GitHub

A public collection of agent skills, published on skills.sh. Each skill is a directory skills/<name>/ in the one skills plugin, with SKILL.md and optional references/, scripts/, examples/. The branch, PR, publish, and test workflow lives in CONTRIBUTING.md; read it before changing anything in this repository. The description in each SKILL.md is the authoritative trigger; this table is a map. With skills (all skills, or pick with -s): With skl-x, the same arguments plus a summary table, or symlinks from a…

The file

We split this AGENTS.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:

    All skills ship in the skills plugin.

    line 75

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.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
AGENTS.md

AGENTS.md

A public collection of agent skills, published on skills.sh. Each skill is a directory skills/<name>/ in the one skills plugin, with SKILL.md and optional references/, scripts/, examples/. The branch, PR, publish, and test workflow lives in CONTRIBUTING.md; read it before changing anything in this repository.

Skills

SkillUse when
scope-triagea request needs design decisions before code
plan-craftingan approved design needs a multi-step implementation plan
git-worktree-isolationdeciding whether work needs an isolated workspace or worktree
inline-plan-devexecuting a plan in the current session
subagent-plan-devexecuting a plan through coordinated subagents
parallel-agentsseveral units of work might run concurrently through agents
tddimplementing testable behavior changes, test first
debugginginvestigating bugs, failures, flaky or unexpected behavior
review-requestan implementation needs an independent review against its requirements and diff
cross-reviewa plan or implementation needs review by other agent CLIs (by default the opposite of Codex and Claude Code, plus Antigravity)
review-resolutionreview findings or PR comments need validation before any fix
verification-gatework is about to be called done, fixed, or mergeable
branch-finishverified work is ready to merge, push, open a PR, or discard
scope-checka saved Markdown file needs an HTML preview and README index entry
prose-craftingdrafting or editing English or Ukrainian prose
dashfixwriting prose or auditing typographic dashes
negafixwriting prose or auditing "it's not just X, it's Y" constructions
skill-craftingdesigning, creating, evaluating, or retiring agent skills
echartsbuilding or debugging Apache ECharts charts
frontend-craftingbuilding or reviewing user-facing interfaces
web-debugtesting or debugging a local web app with Playwright
vitestconfiguring, writing, or debugging Vitest tests
typescriptcompiler errors, tsconfig, typing, and module resolution problems
maintaining-agent-contextcreating or auditing AGENTS.md, CLAUDE.md, and other agent instructions
secret-hygieneusing credentials from env files or config with real services
gh-switcha project-scoped gh command is about to run on github.com, or a GitLab API call in a project with a GitLab remote
commit-allthe user asks to commit all current changes without a message
webapp-debuggerslash-only: testing or debugging a local web app with agent-browser

The description in each SKILL.md is the authoritative trigger; this table is a map.

Install

With skills (all skills, or pick with -s):

npx skills add sentimony/skills -a codex claude-code -y
npx skills add sentimony/skills -s tdd cross-review -a codex claude-code -y

With skl-x, the same arguments plus a summary table, or symlinks from a local clone so edits apply without reinstalling:

npx -y skl-x add sentimony/skills -s tdd cross-review -a codex claude-code -y
npx -y skl-x sln <clone>/skills -a codex claude-code -y

As a Claude Code plugin from sentimony/marketplace:

claude plugin marketplace add sentimony/marketplace
claude plugin install skills@sentimony

As a Codex plugin:

codex plugin marketplace add sentimony/marketplace
codex plugin add skills@sentimony

All skills ship in the skills plugin; this repository hosts no marketplace. After a release, sentimony/marketplace bumps the skills entry ref to the new vX.Y.Z tag. Plugin skills are namespaced by their plugin: /skills:scope-triage.

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