菜单
Fix bugs, errors, test failures, CI/CD issues with intelligent routing. Use when reporting bugs, type errors, log errors, UI issues, code problems. Auto-classifies complexity and activates relevant skills.
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。
Optimize end-to-end application performance with profiling, observability, and backend/frontend tuning. Use when coordinating performance optimization across the stack.
Build AI agents using the Azure AI Agents Python SDK (azure-ai-agents). Use when creating agents hosted on Azure AI Foundry with tools (File Search, Code Interpreter, Bing Grounding, Azure AI Search, Function Calling, OpenAPI, MCP), managing threads and messages, implementing streaming responses, or working with vector stores. This is the low-level SDK - for higher-level abstractions, use the agent-framework skill instead.
Orchestrate end-to-end backend feature development from requirements to deployment. Use when coordinating multi-phase feature delivery across teams and services.
Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices.
Generate comprehensive C4 architecture documentation for an existing repository/codebase using a bottom-up analysis approach.
Use when working with comprehensive review full review
| name | fixing |
| description | Fix bugs, errors, test failures, CI/CD issues with intelligent routing. Use when reporting bugs, type errors, log errors, UI issues, code problems. Auto-classifies complexity and activates relevant skills. |
| version | 1.0.0 |
Unified skill for fixing issues of any complexity with intelligent routing.
First action: If there is no "auto" keyword in the request, use AskUserQuestion to determine workflow mode:
| Option | Recommend When | Behavior |
|---|---|---|
| Autonomous | Simple/moderate issues | Auto-approve if score >= 9.5 & 0 critical |
| Human-in-the-loop | Critical/production code | Pause for approval at each step |
| Quick | Type errors, lint, trivial bugs | Fast debug → fix → review cycle |
See references/mode-selection.md for AskUserQuestion format.
Classify before routing. See references/complexity-assessment.md.
| Level | Indicators | Workflow |
|---|---|---|
| Simple | Single file, clear error, type/lint | references/workflow-quick.md |
| Moderate | Multi-file, root cause unclear | references/workflow-standard.md |
| Complex | System-wide, architecture impact | references/workflow-deep.md |
| Parallel | 2+ independent issues | Parallel fullstack-developer agents |
See references/skill-activation-matrix.md for complete matrix.
Always activate: debugging (all workflows)
Conditional: problem-solving, sequential-thinking, brainstorming, context-engineering
Task agents: debugger, researcher, planner, code-reviewer, tester, Bash
Parallel: Multiple Explore agents for scouting, Bash agents for verification
Unified step markers:
✓ Step 0: [Mode] selected - [Complexity] detected
✓ Step 1: Root cause identified - [summary]
✓ Step 2: Fix implemented - [N] files changed
✓ Step 3: Tests [X/X passed]
✓ Step 4: Review [score]/10 - [status]
✓ Step 5: Complete - [action taken]
Load as needed:
references/mode-selection.md - AskUserQuestion format for modereferences/complexity-assessment.md - Classification criteriareferences/workflow-quick.md - Quick: debug → fix → reviewreferences/workflow-standard.md - Standard: full pipelinereferences/workflow-deep.md - Deep: research + brainstorm + planreferences/review-cycle.md - Review logic (autonomous vs HITL)references/skill-activation-matrix.md - When to activate each skillreferences/parallel-exploration.md - Parallel Explore/Bash Task agent patternsSpecialized Workflows:
references/workflow-ci.md - GitHub Actions/CI failuresreferences/workflow-logs.md - Application log analysisreferences/workflow-test.md - Test suite failuresreferences/workflow-types.md - TypeScript type errorsreferences/workflow-ui.md - Visual/UI issues (requires design skills)