skills
AGENTS.md3 starsChanged 25 days agoMITView on GitHub
This file holds the rules every agent follows when it works in this repo. Issues live in this repo's GitHub issues, in yahyabedirhan/skills, through the gh CLI. There are no triage labels: label a new issue enhancement or bug, whichever fits. This repo is single-context, with one GLOSSARY.md at the root and the decision records in docs/decisions/. See docs/agents/domain.md. Before maintaining the repo, read GLOSSARY.md, which defines the words this repo uses for its skills, forks and their origins. Before…
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 repository33 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- calendarSkill
- cli-designSkill
- continue-sessionSkill
- emailSkill
- handoffSkill
- handoverSkill
- handover-to-herdrSkill
- i-am-afkSkill
- i-am-backSkill
- implementSkill
- init-effortSkill
- low-level-designSkill
- maintain-environmentSkill
- orchestrate-effortSkill
- orchestrate-with-handoffSkill
- orchestratingSkill
- retire-machineSkill
- settle-effortSkill
- settle-sessionSkill
- set-up-machineSkill
- set-up-projectSkill
- show-me-artifactSkill
- show-me-diagramSkill
- show-meSkill
- skill-recapSkill
- swift-performanceSkill
- system-designSkill
- to-prSkill
- to-specSkill
- to-ticketsSkill
- treehouseSkill
- wispr-flow-dictionarySkill
The file
We split this AGENTS.md into the rules it gives an agent
5 rules. About 0 are common, 0 are distinctive, and 5 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.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 19
Before maintaining the repo, read GLOSSARY.md, which defines the words this repo uses for its skills, forks and their origins.
- Very specific: line 23
Before writing or changing a skill, read docs/decisions/skill-writing.md: the shape, the language and what a skill leaves out and keeps.
- Very specific: line 27
Before writing or changing anything under docs/, such as research, guides, decision records and agent docs, read …
- Very specific: line 29
Before changing a skill, read its decision file in docs/decisions/: why the skill is shaped as it is.
- Very specific: line 32
Before changing maintain-environment, set-up-machine or set-up-project, read its design in docs/design/.
≈ “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
Agent instructions
This file holds the rules every agent follows when it works in this repo.
Agent skills
Issue tracker
Issues live in this repo's GitHub issues, in yahyabedirhan/skills, through the gh CLI.
There are no triage labels: label a new issue enhancement or bug, whichever fits.
Domain docs
This repo is single-context, with one GLOSSARY.md at the root and the decision records in docs/decisions/.
See docs/agents/domain.md.
Glossary
Before maintaining the repo, read GLOSSARY.md, which defines the words this repo uses for its skills, forks and their origins.
Writing skills
Before writing or changing a skill, read docs/decisions/skill-writing.md: the shape, the language and what a skill leaves out and keeps.
Writing docs
Before writing or changing anything under docs/, such as research, guides, decision records and agent docs, read docs/decisions/technical-writing.md: a light version of ASD-STE100 for every sentence, and one folder per research topic.
Before changing a skill, read its decision file in docs/decisions/: why the skill is shaped as it is.
A decision entry has five fields, as docs/decisions/index.md shows.
Before changing maintain-environment, set-up-machine or set-up-project, read its design in docs/design/.
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.