<kebab-case-folder-name>
Skill1 starsChanged 4 months agoMITView on GitHub
<What this skill covers AND when to consult it. This is the only part the
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/00-harness.mdcCursor rule
- brainstormingSkill
- checkpointing-progressSkill
- executing-plansSkill
- idea-reviewSkill
- initiating-a-projectSkill
- onboardingSkill
- test-driven-developmentSkill
- verifySkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 37
Keep it skimmable: an agent should act after one read.
- Very specific: line 39
After creating a skill folder, add a row to the routing table in ../../../AGENTS.md.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill 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
Skill: <Imperative title — e.g. "Add a thumbnail generator">
<One or two sentences: what this task is and the single most important rule to respect while doing it.>Where things are
<The exact files/types/symbols an agent will touch — link or path them. e.g. src/foo/Bar.ext defines Bar.>
Steps
- <Concrete, ordered steps. Name the interface/function to implement or edit.>
- <Where to register/wire it so it's actually reachable.>
<Any UI or config wiring needed.>
Conventions to keep
- <Project rules this task must honor. Link the relevant invariant in ../../../AGENTS.md.>
Gotchas
- <Non-obvious traps you'd want to have known up front. Encode the lesson, not just the symptom.>
Verify
<How to prove it works: which test to add, and the project's verify gate (see ../verify/SKILL.md).>
Reference
<Point at the closest existing implementation to copy the shape from.><!--
Authoring notes (delete in the real skill):
- The `---` frontmatter MUST be the very first thing in the file (line 1), no blank
line above it. `name` = the folder name; `description` is what gets matched when
deciding to use the skill, so make it specific and a little pushy.
- Keep it skimmable: an agent should act after one read. Aim for <60 lines.
- Reference REAL files/symbols, not aspirations. Verify they exist first.
- After creating a skill folder, add a row to the routing table in ../../../AGENTS.md.
- Folder name = kebab-case verb-phrase (e.g. add-provider, generate-thumbnails).
- Markdown style: no maximum line width. Never hard-wrap a paragraph in the middle to
satisfy a column limit — one paragraph is one continuous line (the editor soft-wraps).
See ../../../AGENTS.md "Documentation conventions".
-->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.

