swe-workflow-skills
AGENTS.md1 starsChanged 4 days agoMITView on GitHub
Read these before working in this repository, in this order: Before opening a PR: node scripts/verify.mjs and node scripts/build-plugins.mjs --check.
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 repository68 other files it gives its agents.
- accessibility-designSkill
- ai-evaluationSkill
- api-designSkill
- architecture-designSkill
- architecture-documentationSkill
- brainstormingSkill
- browser-verificationSkill
- bug-investigatingSkill
- build-vs-buySkill
- cicd-pipelineSkill
- code-archaeologySkill
- code-reviewingSkill
- code-slop-cleanupSkill
- compliance-privacySkill
- configuration-strategySkill
- containerizationSkill
- data-modelingSkill
- data-pipeline-designSkill
- data-qualitySkill
- dependency-impact-analysisSkill
- dependency-managementSkill
- deployment-checklistSkill
- deployment-repoSkill
- dx-auditSkill
- effort-estimationSkill
- exploratory-data-analysisSkill
- feature-planningSkill
- finops-cost-optimizationSkill
- frontend-architectureSkill
- gitops-deliverySkill
- git-workflowSkill
- incident-responseSkill
- infrastructure-as-codeSkill
- llm-app-engineeringSkill
- metrics-and-okrsSkill
- ml-experiment-trackingSkill
- ml-model-deploymentSkill
- ml-pipeline-designSkill
- mobile-architectureSkill
- mobile-releaseSkill
- notebook-to-productionSkill
- observability-designSkill
- performance-optimizationSkill
- plan-executionSkill
- prd-writingSkill
- project-documentationSkill
- project-proposalSkill
- project-reviewSkill
- refactoringSkill
- release-managementSkill
- research-methodologySkill
- resilience-engineeringSkill
- retrospectiveSkill
- rollback-strategySkill
- security-auditSkill
- skill-routerSkill
- statistical-analysisSkill
- strategic-reviewSkill
- subagent-orchestrationSkill
- tdd-workflowSkill
- The first 60 shown.
The file
We split this AGENTS.md 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 3
Read these before working in this repository, in this order:
- Very specific: line 10
Before opening a PR: node scripts/verify.mjs and node scripts/build-plugins.mjs --check.
≈ “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
Guide for coding agents
Read these before working in this repository, in this order:
- docs/HOW-WE-WORK.md: how issues, PRs and releases are run, what counts as done, and what an agent may post without approval.
- docs/AUTHORING.md: how a skill is written, including Adding a skill.
- docs/EVALS.md: how skills are measured. What counts as done, evals included, is HOW-WE-WORK → Closing.
- docs/ROLES.md: the activation model, roles, and the generated files (
plugins/,catalog.json,.claude-plugin/marketplace.json). Editroles.jsonand the skills, never the generated files, then runnode scripts/build-plugins.mjs.
Before opening a PR: node scripts/verify.mjs and node scripts/build-plugins.mjs --check.
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.