菜单
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| 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. |
why-not-mechanizable: skill workflow guidance; each step requires understanding the surrounding context (repo, task shape, prior state).
Gather requirements - ask user about: (review-time: see section note)
(review-time: see section note)(review-time: see section note)(review-time: see section note)(review-time: see section note)Draft the skill - create: (review-time: see section note)
(review-time: see section note)(review-time: see section note)(review-time: see section note)Review with user - present draft and ask: (review-time: see section note)
(review-time: see section note)(review-time: see section note)(review-time: see section note)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
---
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)]
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:
(review-time: see section note)(review-time: see section note)Format:
(review-time: see section note)(review-time: see section note)(review-time: see section note)(review-time: see section note)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.
Add utility scripts when:
(review-time: see section note)(review-time: see section note)(review-time: see section note)Scripts save tokens and improve reliability vs generated code.
Split into separate files when:
(review-time: see section note)(review-time: see section note)(review-time: see section note)After drafting, verify:
(review-time: see section note)(review-time: see section note)(review-time: see section note)(review-time: see section note)(review-time: see section note)(review-time: see section note)Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "is this over-engineered", or invokes /prune. Complements correctness-focused review; this one only hunts complexity.
Implement code incrementally with quality gates. Use when the user says 'build', 'implement', or when starting the implementation phase of an approved plan.
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Structured production-incident investigation. Forces evidence-first hypothesis ranking before any code change. Use when given an error message, Sentry alert, failing log, or 'investigate <X>' request.
Fetch and digest Sentry issue data (issue summary, tags, stack trace, breadcrumbs, latest event) by short ID, numeric issue ID, or sentry.io URL. Org-agnostic - works for any Sentry org the local token can access. Use when the user mentions a Sentry issue or short ID (e.g. MY-PROJECT-4X2), pastes a sentry.io issue URL, or asks to investigate/debug a Sentry error.
Create or update a diagram. Picks mermaid vs drawio per rules/diagrams.md, writes the source file, previews via MCP. Use when the user says 'diagram', '/diagram', or asks for a flowchart/architecture/sequence/state diagram.