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.
npx skills add https://github.com/majiayu000/claude-skill-registry --skill agent-check
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"])
This is a FILE CLASSIFICATION task - analyze target files and determine which agents are needed:
agents: [...]Expected output format:
agents: ["eslint-agent", "prettier-agent", "typescript-agent"]
Scan target files for these patterns and map to agents:
| File Pattern | Agent | Category |
| ------------ | ----- | -------- |
| eslint.config.js, .eslintrc*, eslint.json | eslint-agent | Config |
| prettier.config.*, .prettierrc*, .prettierignore | prettier-agent | Config |
| tsconfig.json, tsconfig.*.json | typescript-agent | Config |
| vitest.config.*, vitest.workspace.* | vitest-agent | Config |
| vite.config.* | vite-agent | Config |
| turbo.json | turbo-config-agent | Config |
| tailwind.config.* | tailwind-agent | Config |
| docker-compose.yml, docker-compose.yaml | docker-compose-agent | Config |
| Dockerfile, .dockerignore | dockerignore-agent | Config |
| .editorconfig | editorconfig-agent | Config |
| commitlint.config.* | commitlint-agent | Config |
| .gitignore, .gitattributes | gitignore-agent, gitattributes-agent | Config |
| .github/workflows/*.yml, .github/workflows/*.yaml | github-workflow-agent | Config |
| .husky/, husky.config.* | husky-agent | Config |
| nodemon.json, nodemon.config.* | nodemon-agent | Config |
| .npmrc.template, .npmrc | npmrc-template-agent | Config |
| .nvmrc | nvmrc-agent | Config |
| CLAUDE.md, .claude/ | claude-md-agent | Config |
| .repomixignore, repomix.json | repomix-config-agent | Config |
| package.json (root) | root-package-json-agent | Config |
| README.md (root) | readme-agent | Config |
| pnpm-workspace.yaml | pnpm-workspace-agent | Config |
| .vscode/, vscode.json | vscode-agent | Config |
For code files (.ts, .tsx, .js, .jsx), scan content patterns:
| Pattern | Agent | Trigger |
| ------- | ----- | ------- |
| React hooks, JSX, .tsx files | react-component-agent | useState, useEffect, JSX, export const Component |
| Service files, API routes | data-service-agent | Service, Repository, @POST, @GET, route, handler |
| Prisma schema references | prisma-database-agent | import.*Prisma, prisma., schema.prisma |
| Test files | unit-test-agent | .test.ts, .test.js, describe, it(, test( |
| Integration test patterns | integration-test-agent | integration.test.ts, db.test.ts, api.test.ts |
| E2E test patterns | e2e-test-agent | e2e.test.ts, cypress, playwright, browser, page. |
Analyze repository structure and content for domain indicators:
| Context | Agent | Detection |
| ------- | ----- | --------- |
| Monorepo workspace setup | monorepo-setup-agent | pnpm-workspace.yaml presence + multiple packages |
| React app structure | react-app-agent | pages/, components/, App.tsx, app router patterns |
| API service setup | data-service-agent | controllers/, services/, repositories/, API decorators |
| Database setup | prisma-database-agent | prisma/schema.prisma, migrations/ directory |
Build Tools (8):
docker-compose-agent, dockerignore-agent, pnpm-workspace-agentpostcss-agent, tailwind-agent, turbo-config-agent, vite-agent, vitest-agentCode Quality (3):
editorconfig-agent, eslint-agent, prettier-agentVersion Control (5):
commitlint-agent, gitattributes-agent, github-workflow-agentgitignore-agent, husky-agentWorkspace (12):
claude-md-agent, env-example-agent, monorepo-root-structure-agentnodemon-agent, npmrc-template-agent, nvmrc-agent, readme-agentrepomix-config-agent, root-package-json-agent, scripts-agenttypescript-agent, vscode-agentBackend (2):
data-service-agent, integration-service-agentDatabase (1):
prisma-database-agentFrontend (5):
react-app-agent, react-component-agent, mfe-host-agentmfe-remote-agent, shadcn-component-agentTesting (3):
unit-test-agent, integration-test-agent, e2e-test-agentMonorepo (1):
monorepo-setup-agentagents = []
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
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"]
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"]
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"]
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"]
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"
]
| Case | Logic |
| ---- | ----- |
| Root package.json | Always include root-package-json-agent (not consumed by workspace agents) |
| Monorepo workspace | Include pnpm-workspace-agent for workspace configuration |
| Config-only target | Return only config agents (ESLint, Prettier, TypeScript, etc.) |
| Code-only target | Include code-domain agents + code-quality agents (ESLint, TypeScript) |
| Mixed target | Include ALL matching agents (config + domain) |
| Empty/no matches | Return empty array [] |
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 skillThe output agents[] is used to spawn multiple agents in parallel for comprehensive audit coverage.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Replace with description of the skill and when Claude should use it.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Take majiayu000/claude-skill-registry-agent-check from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.