joshuadavidthomasjoshuadavidthomas/agent-skills/AGENTS.md

agent-skills

AGENTS.md49 starsChanged 6 months agoMITView on GitHub

This repository is the source of truth for @joshuadavidthomas's reusable agent skills. When working in this repository, edit the skill files in this repository only. Do not edit installed copies under ~/.agents/skills/, ~/.pi/agent/skills/, or any other runtime-installed skill directory unless the user explicitly asks to modify the installed copy. If an installed copy differs from this repository, treat this repository as canonical. Make changes here first, then ask before syncing or copying changes to an installed location. Skill README.md files…

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 31,774 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 repository26 other files it gives its agents.
- coding-standardsSkill
- coolify-composeSkill
- crafting-effective-readmesSkill
- diataxisSkill
- english-pleaseSkill
- feature-planning-artifactsSkill
- frontend-design-principlesSkill
- grug-brained-devSkill
- html-artifactsSkill
- improveSkill
- improving-promptsSkill
- jjSkill
- reducing-entropySkill
- researching-codebasesSkill
- roadmapSkill
- roadmap-to-improve-plansSkill
- rustSkill
- salsaSkill
- skill-authoringSkill
- strategic-roadmapSkill
- svelte5Skill
- sveltekitSkill
- writing-cli-skillsSkill
- writing-error-messagesSkill
- writing-plansSkill
- writingSkill

The file

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

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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

Distinctive:
When working in this repository, edit the skill files in this repository only.
line 5
Very specific:
Do not edit installed copies under ~/.agents/skills/, ~/.pi/agent/skills/, or any other runtime-installed skill directory unless the user …
line 7
Distinctive:
If an installed copy differs from this repository, treat this repository as canonical.
line 9
Distinctive:
When adding or updating a skill README, follow the style of existing skill READMEs in this repository: briefly explain what the skill is, …
line 15
Distinctive:
Do not dump skill-authoring provenance templates into a skill README by default.
line 17
Very specific:
Put detailed source summaries, rationale, examples, tradeoffs, and regression cases in focused references/ files linked from SKILL.md or …
line 19

≈ “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

This repository is the source of truth for @joshuadavidthomas's reusable agent skills.

Editing rule

When working in this repository, edit the skill files in this repository only.

Do not edit installed copies under ~/.agents/skills/, ~/.pi/agent/skills/, or any other runtime-installed skill directory unless the user explicitly asks to modify the installed copy.

If an installed copy differs from this repository, treat this repository as canonical. Make changes here first, then ask before syncing or copying changes to an installed location.

Skill README convention

Skill README.md files are human-facing orientation pages, not hidden runtime instruction or synthesis scratchpads.

When adding or updating a skill README, follow the style of existing skill READMEs in this repository: briefly explain what the skill is, when to use it, what files/references it contains, attribution/source notes when relevant, and scope boundaries when useful.

Do not dump skill-authoring provenance templates into a skill README by default. Avoid sections like "Synthesis Decisions", "Coverage and Gaps", "Needs validation", "Maintenance Notes", or "Change Log" unless the existing README already uses that maintainer-record style or the user explicitly asks for it.

Put detailed source summaries, rationale, examples, tradeoffs, and regression cases in focused references/ files linked from SKILL.md or the README.

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