菜单
Transform vague or informal prompts into structured, precise prompts optimized for the researchCodebase agent. Use when preparing to launch codebase research and the user's request needs refinement for better results.
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 | small-to-before-research |
| description | Transform vague or informal prompts into structured, precise prompts optimized for the researchCodebase agent. Use when preparing to launch codebase research and the user's request needs refinement for better results. |
Transform vague prompts into optimized research prompts for the researchCodebase agent.
**Research Prompt:**
[Optimized prompt here]
**Search Targets:**
- [Specific files/patterns/keywords to look for]
**Expected Deliverables:**
- [What the research should produce]
Vague: "how does auth work" Optimized:
Research Prompt:
Document the authentication flow from login to session management. Identify entry points, middleware, token handling, and session storage mechanisms.
Search Targets:
- auth, login, session, token, middleware, jwt, passport
- Files: *auth*, *session*, *login*
Expected Deliverables:
- Authentication entry points and routes
- Token/session lifecycle
- Key files and their relationships
Vague: "find where we handle errors" Optimized:
Research Prompt:
Locate error handling patterns across the codebase. Document centralized error handlers, try-catch patterns, error middleware, and custom error classes.
Search Targets:
- error, catch, throw, ErrorHandler, middleware
- Files: *error*, *exception*, *handler*
Expected Deliverables:
- Error handling entry points
- Custom error classes/types
- Error propagation patterns
Software testing expertise for writing effective tests. Use when writing tests, reviewing test quality, designing test suites, debugging test failures, or implementing TDD. Covers xUnit patterns, test case selection, mocks/fixtures, parametrization, testing stateful systems, BDD, golden/snapshot testing, and LLM output evaluation.
Sync the claudeResources registry in claude-runner.ts with actual files in .claude folder. Use when adding, removing, or renaming skills/agents/commands, or when claudeResources may be out of sync with the .claude directory structure.
Turn rough MyTraining feature requests into testable PRDs (Mutual Persistent Memory + Backend PRD + Frontend PRD) with explicit API contracts, acceptance criteria mapped to tests, and stable `data-testid` selectors for E2E.
Use when running E2E checks or debugging the web app with Playwright MCP, especially when you need to (1) ensure the demo user exists with superadmin permissions via demo.sql, and (2) login via /demoLogin on localhost.
React performance optimization guidelines. This skill should be used when writing, reviewing, or refactoring React code to ensure optimal performance patterns. Triggers on tasks involving React components, data fetching, bundle optimization, or performance improvements.
Guide for creating effective skills. Use when creating a new skill (or updating an existing one) that extends the assistant with specialized knowledge, workflows, or tool integrations.