AGENT SKILL

write-a-skill

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

License 许可
MIT
最近更新
2026-09-14
Stars
★ 68
Forks
15

01 前言 Front Matter

name
write-a-skill
description
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

03 SKILL.md 正文

Writing Skills

Process

  1. Gather requirements - ask user about:

    • What task/domain does the skill cover?
    • What specific use cases should it handle?
    • Does it need executable scripts or just instructions?
    • Any reference materials to include?
  2. Draft the skill - create:

    • SKILL.md with concise instructions
    • Additional reference files if content exceeds 500 lines
    • Utility scripts if deterministic operations needed
  3. Review with user - present draft and ask:

    • Does this cover your use cases?
    • Anything missing or unclear?
    • Should any section be more/less detailed?

Skill Structure

skill-name/
├── SKILL.md           # Main instructions (required)
├── REFERENCE.md       # Detailed docs (if needed)
├── EXAMPLES.md        # Usage examples (if needed)
└── scripts/           # Utility scripts (if needed)
    └── helper.js

SKILL.md Template

---
name: skill-name
description: Brief description of capability. Use when [specific triggers].
---

# Skill Name

## Quick start

[Minimal working example]

## Workflows

[Step-by-step processes with checklists for complex tasks]

## Advanced features

[Link to separate files: See [REFERENCE.md](REFERENCE.md)]

Description Requirements

The description is the only thing your agent sees when deciding which skill to load. It's surfaced in the system prompt alongside all other installed skills. Your agent reads these descriptions and picks the relevant skill based on the user's request.

Goal: Give your agent just enough info to know:

  1. What capability this skill provides
  2. When/why to trigger it (specific keywords, contexts, file types)

Format:

  • Max 1024 chars
  • Write in third person
  • First sentence: what it does
  • Second sentence: "Use when [specific triggers]"

Good example:

Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when user mentions PDFs, forms, or document extraction.

Bad example:

Helps with documents.

The bad example gives your agent no way to distinguish this from other document skills.

When to Add Scripts

Add utility scripts when:

  • Operation is deterministic (validation, formatting)
  • Same code would be generated repeatedly
  • Errors need explicit handling

Scripts save tokens and improve reliability vs generated code.

When to Split Files

Split into separate files when:

  • SKILL.md exceeds 100 lines
  • Content has distinct domains (finance vs sales schemas)
  • Advanced features are rarely needed

Review Checklist

After drafting, verify:

  • [ ] Description includes triggers ("Use when...")
  • [ ] SKILL.md under 100 lines
  • [ ] No time-sensitive info
  • [ ] Consistent terminology
  • [ ] Concrete examples included
  • [ ] References one level deep

04 同仓库更多 Skills

RaheesAhmed
RaheesAhmed/SajiCode

demo-skill

Demo plugin skill for tests.

Skill与智能体开发
★ 68
RaheesAhmed
RaheesAhmed/SajiCode

web-research

Deep web research and data extraction skill. Systematically research ANY topic by fetching URLs, reading documentation, crawling API docs, evaluating npm/pypi packages, comparing technologies, and synthesizing findings into actionable recommendations. Use when researching libraries, frameworks, APIs, solutions, or any topic requiring web investigation.

资料检索与研究
★ 68
RaheesAhmed
RaheesAhmed/SajiCode

testing

Design and implement comprehensive test suites. Covers unit testing, integration testing, E2E testing with Playwright, API testing, mocking strategies, test data factories, TDD workflow, snapshot testing, coverage targets, and CI integration. Use when writing tests, designing test architecture, or debugging test failures.

测试与质量
★ 68
RaheesAhmed
RaheesAhmed/SajiCode

superpowers

Core engineering workflow that activates on EVERY task. Enforces systematic plan-before-code methodology, multi-file refactoring safety, dependency-aware changes, pre-flight verification, and zero-placeholder quality standards. Use PROACTIVELY on all coding tasks.

★ 68
RaheesAhmed
RaheesAhmed/SajiCode

styling

Implement production styling systems with Tailwind CSS, vanilla CSS, or CSS-in-JS. Covers CSS architecture (BEM, utility-first, modules), design tokens, responsive patterns, animation systems, dark mode, container queries, print styles, and performance optimization. Use when implementing designs or building CSS architectures.

视觉设计
★ 68
RaheesAhmed
RaheesAhmed/SajiCode

shadcn-ui

Build premium interfaces with shadcn/ui components, Radix primitives, and Tailwind CSS. Covers installation, component customization, theming, dark mode, form patterns with react-hook-form + Zod, data tables with sorting/filtering/pagination, command palette, toast patterns, and composable component architecture. Use when building UI with shadcn/ui.

设计师数据分析师前端开发
★ 68