skills
CLAUDE.md6 starsChanged 6 months agoMITView on GitHub
This is the kinhluan-skills plugin and a portable Agent Skills repository. Install development dependencies with python3 -m pip install -r requirements-dev.txt. The portable UserPromptSubmit hook in hooks/hooks.json runs scripts/skill_router.py. Router suggestions are hints; skill metadata and the actual task remain authoritative.
- Installs packages
In this repository75 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-browserSkill
- agent-desktopSkill
- agent-expertise-protocolSkill
- ai-figure-generationSkill
- api-securitySkill
- architecture-decision-recordsSkill
- architecture-reviewSkill
- art-of-war-software-engineeringSkill
- browser-automationSkill
- business-product-leadershipSkill
- c4-level1-contextSkill
- c4-level2-containerSkill
- c4-level3-componentSkill
- c4-level4-codeSkill
- c4-modelSkill
- clean-architectureSkill
- cloud-securitySkill
- code-quality-gateSkill
- collaborative-engineering-agentSkill
- conference-paperSkill
- container-securitySkill
- database-designSkill
- ddd-coreSkill
- ddd-patternsSkill
- ddd-tacticalSkill
- defense-prepSkill
- dependency-managementSkill
- diffusion-release-trackingSkill
- docker-containerizationSkill
- dora-coreSkill
- evolutionary-architectureSkill
- exam-rubricSkill
- experiment-trackingSkill
- federated-learning-dqnSkill
- git-workflowSkill
- golang-developmentSkill
- internal-critiqueSkill
- javascript-typescriptSkill
- journal-q1-polishSkill
- kinhluan-routerSkill
- kubernetes-orchestrationSkill
- merge-request-reviewSkill
- milestone-trackerSkill
- paper-auditSkill
- paper-writingSkill
- pastureSkill
- payment-systemsSkill
- penetration-testingSkill
- phd-proposalSkill
- problem-discoverySkill
- product-analyticsSkill
- product-ux-researchSkill
- progress-reportSkill
- proposal-defenseSkill
- publication-strategySkill
- python-developmentSkill
- research-designSkill
- research-questionSkill
- research-watchSkill
- The first 60 shown.
The file
We split this CLAUDE.md into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Very specific: line 10
Do not recreate SKILL.toon or commit installer-generated skills-lock.json.
- Very specific: line 26
Keep SKILL.md below 500 lines.
- Distinctive: line 27
Add a route and regression test for every published skill.
- Distinctive: line 28
Keep release versions synchronized across all four manifests.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
Claude Code Repository Context
This is the kinhluan-skills plugin and a portable Agent Skills repository.
Source of Truth
- Edit
skills/<name>/SKILL.mdand its directly linked resources. skills/is a real directory so plugin discovery works across operating systems.skills.jsonanddist/*.skillare generated release surfaces.- Do not recreate
SKILL.toonor commit installer-generatedskills-lock.json.
Commands
make sync-manifest
make validate
make test
make package
make checkInstall development dependencies with python3 -m pip install -r requirements-dev.txt.
Change Rules
- Keep
SKILL.mdbelow 500 lines; use directly linkedreferences/for details. - Add a route and regression test for every published skill.
- Keep release versions synchronized across all four manifests.
- Rebuild and commit deterministic packages after source changes.
- Preserve unrelated work and do not publish external changes unless requested.
The portable UserPromptSubmit hook in hooks/hooks.json runs scripts/skill_router.py. Router suggestions are hints; skill metadata and the actual task remain authoritative.
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.

