跳到正文
cccskills
免费在 GitHub 公开

agent-check

Use when mapping audit targets to appropriate config or domain agents. Analyzes file types, patterns, and content to determine which agents should audit each file/target. Returns agents[] needed for audit workflow.

中文简介正在准备中。当前显示原文说明。

实测评分 未实测

查看安装方法

包含的文件(2)

  • SKILL.md8.1 KB
  • metadata.json310 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Agent Check Skill

Purpose: Analyze audit targets and map them to the appropriate domain or config agents needed.

Input: targets (string[]) - File paths or target repositories from scope-check

Output: agents: string[] - List of agent names needed (e.g., ["eslint-agent", "typescript-agent", "react-component-agent"])


How to Execute

This is a FILE CLASSIFICATION task - analyze target files and determine which agents are needed:

  1. Scan each target file/directory for file patterns and content indicators
  2. Match patterns to agent mapping tables below
  3. Collect all matching agents into array
  4. Remove duplicates
  5. Return ONLY: agents: [...]
  6. Complete in under 300 tokens

Expected output format:

agents: ["eslint-agent", "prettier-agent", "typescript-agent"]

File Pattern Matching

Step 1: Detect File Types

Scan target files for these patterns and map to agents:

File PatternAgentCategory
eslint.config.js, .eslintrc*, eslint.jsoneslint-agentConfig
prettier.config.*, .prettierrc*, .prettierignoreprettier-agentConfig
tsconfig.json, tsconfig.*.jsontypescript-agentConfig
vitest.config.*, vitest.workspace.*vitest-agentConfig
vite.config.*vite-agentConfig
turbo.jsonturbo-config-agentConfig
tailwind.config.*tailwind-agentConfig
docker-compose.yml, docker-compose.yamldocker-compose-agentConfig
Dockerfile, .dockerignoredockerignore-agentConfig
.editorconfigeditorconfig-agentConfig
commitlint.config.*commitlint-agentConfig
.gitignore, .gitattributesgitignore-agent, gitattributes-agentConfig
.github/workflows/*.yml, .github/workflows/*.yamlgithub-workflow-agentConfig
.husky/, husky.config.*husky-agentConfig
nodemon.json, nodemon.config.*nodemon-agentConfig
.npmrc.template, .npmrcnpmrc-template-agentConfig
.nvmrcnvmrc-agentConfig
CLAUDE.md, .claude/claude-md-agentConfig
.repomixignore, repomix.jsonrepomix-config-agentConfig
package.json (root)root-package-json-agentConfig
README.md (root)readme-agentConfig
pnpm-workspace.yamlpnpm-workspace-agentConfig
.vscode/, vscode.jsonvscode-agentConfig

Step 2: Detect Code Content

For code files (.ts, .tsx, .js, .jsx), scan content patterns:

PatternAgentTrigger
React hooks, JSX, .tsx filesreact-component-agentuseState, useEffect, JSX, export const Component
Service files, API routesdata-service-agentService, Repository, @POST, @GET, route, handler
Prisma schema referencesprisma-database-agentimport.*Prisma, prisma., schema.prisma
Test filesunit-test-agent.test.ts, .test.js, describe, it(, test(
Integration test patternsintegration-test-agentintegration.test.ts, db.test.ts, api.test.ts
E2E test patternse2e-test-agente2e.test.ts, cypress, playwright, browser, page.

Step 3: Detect Domain Context

Analyze repository structure and content for domain indicators:

ContextAgentDetection
Monorepo workspace setupmonorepo-setup-agentpnpm-workspace.yaml presence + multiple packages
React app structurereact-app-agentpages/, components/, App.tsx, app router patterns
API service setupdata-service-agentcontrollers/, services/, repositories/, API decorators
Database setupprisma-database-agentprisma/schema.prisma, migrations/ directory

Agent Mapping Reference

Config Agents (28 total)

Build Tools (8):

  • docker-compose-agent, dockerignore-agent, pnpm-workspace-agent
  • postcss-agent, tailwind-agent, turbo-config-agent, vite-agent, vitest-agent

Code Quality (3):

  • editorconfig-agent, eslint-agent, prettier-agent

Version Control (5):

  • commitlint-agent, gitattributes-agent, github-workflow-agent
  • gitignore-agent, husky-agent

Workspace (12):

  • claude-md-agent, env-example-agent, monorepo-root-structure-agent
  • nodemon-agent, npmrc-template-agent, nvmrc-agent, readme-agent
  • repomix-config-agent, root-package-json-agent, scripts-agent
  • typescript-agent, vscode-agent

Domain Agents (12 total)

Backend (2):

  • data-service-agent, integration-service-agent

Database (1):

  • prisma-database-agent

Frontend (5):

  • react-app-agent, react-component-agent, mfe-host-agent
  • mfe-remote-agent, shadcn-component-agent

Testing (3):

  • unit-test-agent, integration-test-agent, e2e-test-agent

Monorepo (1):

  • monorepo-setup-agent

Selection Algorithm

agents = []

FOR each target file/directory:
    1. Check file patterns (Step 1) -> add matching agents
    2. If code file: check content patterns (Step 2) -> add matching agents
    3. Check domain context (Step 3) -> add matching agents

REMOVE duplicates from agents array
RETURN agents

Examples

Example 1: ESLint Config File

Target: /home/user/code/metasaver-com/eslint.config.js

Analysis:
  - File pattern: "eslint.config.js" -> eslint-agent
  - Content: ESLint config -> code-quality context

Output: ["eslint-agent"]

Example 2: React Component Files

Target: /home/user/code/metasaver-com/src/components/

Analysis:
  - Files: *.tsx files with JSX/React hooks
  - Content patterns: useState, useEffect, export const Component
  - Domain: React component library

Output: ["react-component-agent", "typescript-agent", "eslint-agent"]

Example 3: Full Package Audit

Target: /home/user/code/multi-mono/packages/utils/

Analysis:
  - tsconfig.json -> typescript-agent
  - eslint.config.js -> eslint-agent
  - *.test.ts files -> unit-test-agent
  - package.json -> root-package-json-agent
  - pnpm-workspace.yaml (parent) -> pnpm-workspace-agent

Output: ["typescript-agent", "eslint-agent", "unit-test-agent", "root-package-json-agent", "pnpm-workspace-agent"]

Example 4: Prisma Database Setup

Target: /home/user/code/metasaver-com/prisma/

Analysis:
  - schema.prisma -> prisma-database-agent
  - migrations/ directory -> prisma-database-agent
  - Database service files -> data-service-agent

Output: ["prisma-database-agent", "data-service-agent"]

Example 5: Multi-Domain Repository

Target: /home/user/code/metasaver-com/ (full repo)

Analysis:
  - Root configs: eslint.config.js, tsconfig.json, prettier.config.js
  - App structure: React components in src/components
  - API routes: src/app/api/
  - Database: prisma/schema.prisma
  - Tests: src/**/*.test.ts

Output: [
  "eslint-agent", "typescript-agent", "prettier-agent",
  "react-component-agent", "data-service-agent",
  "prisma-database-agent", "unit-test-agent"
]

Special Cases

CaseLogic
Root package.jsonAlways include root-package-json-agent (not consumed by workspace agents)
Monorepo workspaceInclude pnpm-workspace-agent for workspace configuration
Config-only targetReturn only config agents (ESLint, Prettier, TypeScript, etc.)
Code-only targetInclude code-domain agents + code-quality agents (ESLint, TypeScript)
Mixed targetInclude ALL matching agents (config + domain)
Empty/no matchesReturn empty array []

Integration

This skill is referenced by:

  • agent-check-agent - Intelligent routing to appropriate agents for audit workflow
  • /audit command - Phase 2 (agent selection) uses this skill output
  • /build command - Feature/component building phase uses this skill

The output agents[] is used to spawn multiple agents in parallel for comprehensive audit coverage.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Use when you need to install the embedded robot agents into either .cursor/agents or .claude/agents, selecting the destination interactively and copying the embedded agent definitions from project assets. This should trigger for requests such as Install embedded agents; Bootstrap .cursor/agents; Bootstrap .claude/agents; Copy robot agents. Part of cursor-rules-java project

中文简介正在准备中。当前显示原文说明。

majiayu000/claude-skill-registry-data272026年10月22日 更新

Use when you need to generate an AGENTS.md file for a Java repository — covering project conventions, tech stack, file structure, commands, Git workflow, and contributor boundaries — through a modular, step-based interactive process that adapts to your specific project needs. This should trigger for requests such as Create AGENTS.md; Update AGENTS.md file; Add agent instructions. Part of cursor-rules-java project

中文简介正在准备中。当前显示原文说明。

majiayu000/claude-skill-registry-data272026年10月22日 更新

Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape. Activate on "find expungement data", "scrape state laws", "legal research", "court URLs", "statute sources", "Clean Slate laws", "automatic expungement research". NOT for interpreting laws (use national-expungement-expert), building UI, or legal advice.

中文简介正在准备中。当前显示原文说明。

majiayu000/claude-skill-registry-data272026年10月22日 更新

Generated by Gremlin Forge Meta-Agent 🍆👾⚡

中文简介正在准备中。当前显示原文说明。

majiayu000/claude-skill-registry-data272026年10月22日 更新

Work autonomously without waiting for hand-holding — complete tasks end-to-end without asking for permission at every step.

中文简介正在准备中。当前显示原文说明。

majiayu000/claude-skill-registry-data272026年10月22日 更新

abmahnung

免费

Entwurf einer BAG-konformen Abmahnung im Arbeitsrecht – konkrete Schilderung der Pflichtverletzung, klare Verhaltenserwartung, ausdrückliche Sanktionsandrohung. Use when AG eine verhaltensbedingte Sanktion vor einer Kündigung dokumentieren muss oder AN die Wirksamkeit einer empfangenen Abmahnung prüft.

中文简介正在准备中。当前显示原文说明。

majiayu000/claude-skill-registry-data272026年10月22日 更新

查看 majiayu000 的全部技能

报告此技能的问题