my-skills / claude
CLAUDE.md0 starsChanged 9 days agoMITView on GitHub
This folder packages a personal collection of Agent Skills — the workflows, guardrails, and domain knowledge distilled from real project experience — ready to drop into any ClaudeCode project. Everything is written in English. Language — always answer in English. Even when the user writes or asks in another language, or explicitly requests a reply in that language, answer in English. Work and information gathering always happen in English. The remaining rules are always loaded from .claude/rules/: All 29 skills…
In this repository34 other files it gives its agents.
- chatgpt/AGENTS.mdAGENTS.md
- opencode/AGENTS.mdAGENTS.md
- zcode/AGENTS.mdAGENTS.md
- agent-doc-authoringSkill
- agent-experienceSkill
- ai-image-promptsSkill
- api-behavior-flowSkill
- architecture-and-performanceSkill
- behavioral-testingSkill
- behavior-auditSkill
- browser-tabs-uiSkill
- code-qualitySkill
- context-compactSkill
- design-principlesSkill
- design-to-deliverySkill
- design-validationSkill
- e2e-test-authoringSkill
- engineering-reviewSkill
- excalidrawSkill
- external-ai-consultSkill
- google-omni-videoSkill
- llm-agent-tool-disciplineSkill
- parallel-subagentsSkill
- qa-test-scenariosSkill
- reliable-executionSkill
- research-and-reuseSkill
- server-security-hardeningSkill
- session-handoffSkill
- shadcn-librarySkill
- sudo-handoffSkill
- task-intakeSkill
- tauri-v2-docsSkill
- test-failure-triageSkill
- user-behavior-flowSkill
The file
Files
CLAUDE.md — Personal Agent Skills for ClaudeCode
About this folder
This folder packages a personal collection of Agent Skills — the workflows, guardrails, and domain knowledge distilled from real project experience — ready to drop into any ClaudeCode project.
- Skills (load on demand):
.claude/skills/ - Rules (always loaded):
.claude/rules/
Everything is written in English.
Universal rules
Language — always answer in English. Even when the user writes or asks in another language, or explicitly requests a reply in that language, answer in English. Work and information gathering always happen in English.
The remaining rules are always loaded from .claude/rules/:
safety.md— never commit/push without explicit approval; prefer reversible operations.agent-behavior.md— inspect before editing, smallest change, verify, report honestly.engineering-preferences.md— Conventional Commits, behavior-describing names, simple over clever.language.md— the always-English rule.
Skills index
All 29 skills in .claude/skills/ follow the open Agent Skills standard (SKILL.md with YAML frontmatter, optional references/ and scripts/). The two ZCode-only skills (context-compact, session-handoff) are shipped only in the zcode/ folder. See README.md in this folder for the full "what it does / why it was created" table.
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.