writing-skills
Use when creating, updating, or improving agent skills.
- License 许可
- Apache-2.0
- 最近更新
- 2026-06-23
- Stars
- ★ 6
- Forks
- 0
01 前言 Front Matter
- name
- writing-skills
- risk
- unknown
- source
- community
- category
- meta
- date_added
- 2026-02-27
- description
- Use when creating, updating, or improving agent skills.
02 资源文件 20
- 参考文档anthropic-best-practices.md44.5 KB
- 参考文档examples.md4.0 KB
- 参考文档gotchas.md3.7 KB
- 其他graphviz-conventions.dot5.8 KB
- 参考文档persuasion-principles.md5.8 KB
- 参考文档references/anti-rationalization/README.md7.1 KB
- 参考文档references/cso/README.md6.2 KB
- 参考文档references/standards/metadata-standard.md1.4 KB
- 参考文档references/standards/README.md3.5 KB
- 参考文档references/templates/discipline.md934 B
- 参考文档references/templates/pattern.md635 B
- 参考文档references/templates/reference.md466 B
- 参考文档references/templates/technique.md779 B
- 参考文档references/templates/tier-3-platform.md463 B
- 参考文档references/testing/README.md5.7 KB
- 参考文档references/tier-1-simple/README.md1.4 KB
- 参考文档references/tier-2-expanded/README.md1.8 KB
- 参考文档references/tier-3-platform/README.md2.7 KB
- 脚本render-graphs.js4.7 KB
- 参考文档testing-skills-with-subagents.md12.3 KB
03 SKILL.md 正文
Writing Skills (Excellence)
Dispatcher for skill creation excellence. Use the decision tree below to find the right template and standards.
⚡ Quick Decision Tree
What do you need to do?
-
Create a NEW skill:
- Is it simple (single file, <200 lines)? → Tier 1 Architecture
- Is it complex (multi-concept, 200-1000 lines)? → Tier 2 Architecture
- Is it a massive platform (10+ products, AWS, Convex)? → Tier 3 Architecture
-
Improve an EXISTING skill:
- Fix "it's too long" -> Modularize (Tier 3)
- Fix "AI ignores rules" -> Anti-Rationalization
- Fix "users can't find it" -> CSO (Search Optimization)
-
Verify Compliance:
- Check metadata/naming -> Standards
- Add tests -> Testing Guide
? Component Index
| Component | Purpose |
|---|---|
| CSO | "SEO for LLMs". How to write descriptions that trigger. |
| Standards | File naming, YAML frontmatter, directory structure. |
| Anti-Rationalization | How to write rules that agents won't ignore. |
| Testing | How to ensure your skill actually works. |
?️ Templates
- Technique Skill (How-to)
- Reference Skill (Docs)
- Discipline Skill (Rules)
- Pattern Skill (Design Patterns)
When to Use
- Creating a NEW skill from scratch
- Improving an EXISTING skill that agents ignore
- Debugging why a skill isn't being triggered
- Standardizing skills across a team
How It Works
- Identify goal → Use decision tree above
- Select template → From
references/templates/ - Apply CSO → Optimize description for discovery
- Add anti-rationalization → For discipline skills
- Test → RED-GREEN-REFACTOR cycle
Quick Example
---
name: my-technique
description: Use when [specific symptom occurs].
metadata:
category: technique
triggers: error-text, symptom, tool-name
---
# My Technique
## When to Use
- [Symptom A]
- [Error message]
Common Mistakes
| Mistake | Fix |
|---|---|
| Description summarizes workflow | Use "Use when..." triggers only |
No metadata.triggers |
Add 3+ keywords |
| Generic name ("helper") | Use gerund (creating-skills) |
| Long monolithic SKILL.md | Split into references/ |
See gotchas.md for more.
✅ Pre-Deploy Checklist
Before deploying any skill:
- [ ]
namefield matches directory name exactly - [ ]
SKILL.mdfilename is ALL CAPS - [ ] Description starts with "Use when..."
- [ ]
metadata.triggershas 3+ keywords - [ ] Total lines < 500 (use
references/for more) - [ ] No
@force-loading in cross-references - [ ] Tested with real scenarios
? Related Skills
- opencode-expert: For OpenCode environment configuration
- Use
/write-skillcommand for guided skill creation
Examples
Create a Tier 1 skill:
mkdir -p ~/.config/opencode/skills/my-technique
touch ~/.config/opencode/skills/my-technique/SKILL.md
Create a Tier 2 skill:
mkdir -p ~/.config/opencode/skills/my-skill/references/core
touch ~/.config/opencode/skills/my-skill/{SKILL.md,gotchas.md}
touch ~/.config/opencode/skills/my-skill/references/core/README.md
04 同仓库更多 Skills
test_skill
暂无简介
zustand-store-ts
Create Zustand stores following established patterns with proper TypeScript types and middleware.
zoom-automation
Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.
zoho-crm-automation
Automate Zoho CRM tasks via Rube MCP (Composio): create/update records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.
zod-validation-expert
Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.
zeroize-audit
Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C/C++/Rust code handling secrets, keys, passwords, or other sensitive data.