skill-for-lazy-developer
AGENTS.md1 starsChanged 7 days agoMITView on GitHub
This repository distributes instructions, examples, and small validation tools. Keep changes focused on a demonstrated workflow need. The consuming-project snippet is AGENTS.snippet.md; do not confuse it with this maintenance guide. Use the configured Python environment. Required checks after skill or tooling changes: For packaging changes, also run python scripts/build_release.py and inspect its archive contents. Local checks use temporary fixtures and have no production access. Fix failures caused by the requested change and rerun affected checks without seeking confirmation at each…
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 repository16 other files it gives its agents.
- adaptive-workflowSkill
- architecture-mapSkill
- browser-diagnosticsSkill
- domain-modelingSkill
- feature-discoverySkill
- lean-senior-engineeringSkill
- release-readinessSkill
- research-plan-implementSkill
- skill-security-guardSkill
- spec-to-code-verificationSkill
- systematic-debuggingSkill
- transaction-safe-engineeringSkill
- ui-design-intelligenceSkill
- ui-implementationSkill
- ui-quality-verificationSkill
- verification-before-completionSkill
The file
We split this AGENTS.md into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Keep one focused goal and a precise triggering description per skill.
- Distinctive: line 8
Read only relevant supporting references.
- Distinctive: line 11
Do not claim a tool, browser, hook, test result, or integration is available merely because instructions mention it.
- Distinctive: line 16
Use the configured Python environment.
- Very specific: line 29
Keep developer-specific paths, secrets, private source, local artifacts, and build output out of commits.
≈ “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
Maintaining Codex Developer Skills
This repository distributes instructions, examples, and small validation tools. Keep changes focused on a demonstrated workflow need. The consuming-project snippet is AGENTS.snippet.md; do not confuse it with this maintenance guide.
Skill changes
- Keep one focused goal and a precise triggering description per skill.
- Read only relevant supporting references; avoid copying the same procedure into several skills.
- Preserve the user's explicit intent: a diagnosis, review, or planning request must not silently become implementation.
- Preserve useful autonomy for authorized implementation. Do not add routine approval gates.
- Do not claim a tool, browser, hook, test result, or integration is available merely because instructions mention it.
- Cite and retain applicable license notices for imported third-party material.
Verification
Use the configured Python environment. Required checks after skill or tooling changes:
python scripts/validate_skills.py
python -m unittest discover -s tests -vFor packaging changes, also run python scripts/build_release.py and inspect its archive contents. Local checks use temporary fixtures and have no production access. Fix failures caused by the requested change and rerun affected checks without seeking confirmation at each step.
Structural tests do not prove skill quality. For significant workflow changes, try a representative request and record the observed outcome and limitations in the pull request. Do not invent evaluation results or promise efficiency gains.
Scope and artifacts
Keep developer-specific paths, secrets, private source, local artifacts, and build output out of commits. Update documentation and the changelog for user-visible changes. Increment VERSION only for an intended release. Creating or publishing a GitHub release remains a separate action from building an archive.
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.