skills
AGENTS.md1 starsChanged 9 days agoMITView on GitHub
Use Bun, not Node: bun <file>, bun test, bun run <script>, bunx <package>, bun install. Agents working in this repo load skills from .agents/skills/. Each skill in skills/ is symlinked there, so adding, renaming, or removing a skill means updating its link too: ln -s ../../skills/<name> .agents/skills/<name>. Skills from other repos that these depend on are installed there with npx skills add, tracked in skills-lock.json. Don't run npx skills add on this repo's own skills: it replaces the symlinks with…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository22 other files it gives its agents.
- codebase-designSkill
- code-reviewSkill
- domain-modelingSkill
- grillingSkill
- prSkill
- researchSkill
- tddSkill
- addressing-pr-reviewSkill
- address-pr-reviewSkill
- code-hostSkill
- escalating-to-userSkill
- grill-subagentSkill
- grill-subagent-with-docsSkill
- grill-yourselfSkill
- grill-yourself-with-docsSkill
- internal-grillingSkill
- landingSkill
- landSkill
- land-ticketsSkill
- lane-landingSkill
- setup-ian-pascoe-skillsSkill
- subagent-grillingSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 1
Use Bun, not Node: bun <file>, bun test, bun run <script>, bunx <package>, bun install.
- Very specific: line 13
Every change a skill user would notice gets a changeset: run bun changeset.
≈ “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.
Files
Use Bun, not Node: bun <file>, bun test, bun run <script>, bunx <package>, bun install.
Local skills
Agents working in this repo load skills from .agents/skills/. Each skill in skills/ is symlinked there, so adding, renaming, or removing a skill means updating its link too: ln -s ../../skills/<name> .agents/skills/<name>. Skills from other repos that these depend on are installed there with npx skills add, tracked in skills-lock.json. Don't run npx skills add on this repo's own skills: it replaces the symlinks with copies that go stale.
Claude Code loads skills from .claude/skills/, where every skill in .agents/skills/ has a link: ln -s ../../.agents/skills/<name> .claude/skills/<name>.
Changesets
The repo is versioned as one private package with Changesets; releases are git tags and GitHub releases.
Every change a skill user would notice gets a changeset: run bun changeset. Write it for skill users, naming the skill that changed. A changeset that removes or renames a skill names what replaces it. Changes that only touch repo tooling, CI, or docs need none.
Pick the bump by what a skill user would notice:
major: a skill is removed or renamed, or how it is invoked or what it requires changes incompatibly. While below 1.0, useminorinstead.minor: a new skill.patch: a behaviour change to an existing skill.
CI runs bun run verify. When you edit a skill or a code host reference, its check:references step enforces the rules in scripts/check-references.ts.
Agent skills
Issue tracker
Issues live in GitHub Issues on ian-pascoe/skills, managed with the gh CLI. See docs/agents/issue-tracker.md.
Code host
GitHub, via origin. See docs/agents/code-host.md.
Triage labels
The five default labels are used as-is: needs-triage, needs-info, ready-for-agent, ready-for-human, wontfix. See docs/agents/triage-labels.md.
Domain docs
Single-context: one GLOSSARY.md and docs/adr/ at the repo root. See docs/agents/domain.md.
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
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.