Less-Is-More-Skill
AGENTS.md2 starsChanged 49 days agoMITView on GitHub
skills/less-is-more/SKILL.md is the skill and its only copy. Keep agents/openai.yaml beside it, and the README's summary and always-on rule, consistent with it. When changing the skill:
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 repositoryOne other file it gives its agents.
- less-is-moreSkill
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 5
When changing the skill:
- Distinctive: line 9
Keep a sentence only if it changes what a strong model would otherwise do.
- Distinctive: line 10
Use plain words; agents repeat the skill's vocabulary in their replies.
- Distinctive: line 12
Keep the header valid for strict parsers: no colon followed by a space inside the description.
≈ “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
Editing this repo
skills/less-is-more/SKILL.md is the skill and its only copy. Keep agents/openai.yaml beside it, and the README's summary and always-on rule, consistent with it.
When changing the skill:
- It is a way of working that lets agents delete boldly once they have checked, not a list of bans.
- It applies in full to any change whenever it is invoked; never make it depend on words the user has to say.
- Keep a sentence only if it changes what a strong model would otherwise do.
- Use plain words; agents repeat the skill's vocabulary in their replies.
- Apply it to itself: an edit should not make it longer unless new evidence earns the words.
- Keep the header valid for strict parsers: no colon followed by a space inside the description.
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.