skills
AGENTS.md1 starsChanged 4 months agoApache-2.0View on GitHub
This repository stores skills used to automate development workflows. These skills are meant for AI agents to execute, not for human readers. Keep instructions agent-facing, explicit, and operational rather than human-facing narrative documentation or diagrams. OBSIDIAN_PROJECT=${OBSIDIAN_ROOT}/projects/Skills The repository root README.md must include: Do not add inventory tables, per-skill install commands, update timestamps, or duplicate skill descriptions. Whenever a skill is added, removed, renamed, or modified, update the README.md in the same change. When updating skills in this repository, do not…
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 repository19 other files it gives its agents.
- agent-aeoSkill
- agent-memorySkill
- beanquerySkill
- ci-repairbaySkill
- delegated-developmentSkill
- ghSkill
- issue-blueprintSkill
- issue-workbenchSkill
- minifluxSkill
- og-imageSkill
- opSkill
- pencil-to-figma-migrationSkill
- pr-comment-sweepSkill
- pr-launchpadSkill
- repo-surveyorSkill
- review-checkpointSkill
- review-repairbaySkill
- shipyardSkill
- skill-optimizerSkill
The file
We split this AGENTS.md into the rules it gives an agent
9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Keep each skill in its own subfolder with its instruction file(s) and related assets.
- Very specific: line 14
When creating or updating skills, keep instructions compact, accurate, stable, and token-efficient.
- Distinctive: line 15
Prefer durable operational rules over verbose narrative, examples, or implementation details that agents can infer from the repository.
- Distinctive: line 25
Do not add inventory tables, per-skill install commands, update timestamps, or duplicate skill descriptions.
- Very specific: line 30
When updating skills in this repository, do not preserve backward compatibility for legacy internal function interfaces in skill code.
- Distinctive: line 39
Add, remove, rename, or revise the affected skill introduction.
- Distinctive: line 40
Keep the skill in the correct group and preserve A-Z ordering.
- Distinctive: line 41
Keep workflow guidance short and reference skill names instead of repeating each skill's role.
- Distinctive: line 43
Do not leave README updates for a later commit.
≈ “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
Repository Maintenance Instructions
This repository stores skills used to automate development workflows. These skills are meant for AI agents to execute, not for human readers. Keep instructions agent-facing, explicit, and operational rather than human-facing narrative documentation or diagrams.
OBSIDIAN_PROJECT=${OBSIDIAN_ROOT}/projects/Skills
Organization
- Keep each skill in its own subfolder with its instruction file(s) and related assets.
Skill Quality
- When creating or updating skills, keep instructions compact, accurate, stable, and token-efficient.
- Prefer durable operational rules over verbose narrative, examples, or implementation details that agents can infer from the repository.
Root README Requirement
The repository root README.md must include:
- One installation section near the top with
npx skills add HenryQW/skills. - One linked heading and short, plain-language introduction for every skill.
Workflow skillsandSupporting skillsgroups, each sorted A-Z by skill name.
Do not add inventory tables, per-skill install commands, update timestamps, or duplicate skill descriptions.
Change Policy (Mandatory)
Whenever a skill is added, removed, renamed, or modified, update the README.md in the same change.
When updating skills in this repository, do not preserve backward compatibility for legacy internal function interfaces in skill code. Specifically, do not preserve compatibility with:
- Previous function names.
- Previous variable names.
- Previous function signatures.
This rule applies to internal implementation APIs, not user-facing CLI or operational interfaces. CLI compatibility may be retained when required for safe rollout or existing workflows.
At minimum, update the root README.md:
- Add, remove, rename, or revise the affected skill introduction.
- Keep the skill in the correct group and preserve A-Z ordering.
- Keep workflow guidance short and reference skill names instead of repeating each skill's role.
Do not leave README updates for a later commit.
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.