一键导入
skillify
Turn repetitive patterns into reusable skills. If you've done it three times, it should be a 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。
菜单
Turn repetitive patterns into reusable skills. If you've done it three times, it should be a 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 | skillify |
| description | Turn repetitive patterns into reusable skills. If you've done it three times, it should be a skill. |
Turn repetitive patterns into reusable skills. If you've done it three times, it should be a skill.
✅ Good candidates:
❌ Bad candidates:
What triggers this workflow? (user says X, file type Y, domain Z)
What steps are always the same?
What parts vary between uses?
What's the expected output?
Use this template:
---
name: [kebab-case-name]
description: [One sentence describing what this skill does]
when_to_use: "[When the user asks X, works with Y files, or Z domain. NOT for A.]"
allowed-tools: [Read, Write, Edit, Grep, Glob, Bash — only what's needed]
effort: [low | medium | high]
---
# [Skill Name] — [Short Subtitle]
> [One-line philosophy or principle]
## Overview
[2-3 sentences explaining what this skill enables]
## When to Use
✅ Good for: [list]
❌ Not for: [list]
## Protocol
### Step 1: [First Action]
[Instructions]
### Step 2: [Second Action]
[Instructions]
### Step N: [Verification]
[How to verify the skill worked correctly]
## Best Practices
[3-5 key rules]
.agent/skills/[skill-name]/SKILL.md
when_to_use clearly defines triggers AND exclusions| Pattern | Skill Name | Example |
|---|---|---|
| Action-based | [verb]-[noun] | verify-changes, batch-operations |
| Domain-based | [domain]-[aspect] | database-design, api-patterns |
| Tool-based | [tool]-patterns | tailwind-patterns, prisma-expert |
Rules:
Before finalizing a new skill:
| Check | Criteria |
|---|---|
| Uniqueness | No existing skill covers this (grep .agent/skills/) |
| Reusability | Useful across multiple projects, not just one |
| Completeness | Has overview, when to use, protocol, verification |
| Frontmatter | All required fields present and accurate |
| Clarity | A new agent could follow these instructions cold |
Generated by Agent Bridge
Analyzes user's requests, determines tech stack, plans structure, and coordinates agents.
Apply consistent changes across many files at once. One pattern, many targets.
**MANDATORY:** Use for complex/vague requests, new features, updates.
Reduce AI token usage by **6.8x average** (up to **49x** on monorepos) by giving the AI a structural map of your codebase instead of letting it read everything.
Keep sessions productive by compressing completed work while preserving key decisions.
Advanced multi-agent coordination with parallel dispatch and synthesis. Use for complex tasks requiring multiple specialist perspectives.