AgentSkillsCN

fixing

当您需要修复各类复杂程度的 Bug、错误、问题或故障时，应优先启用此技能。该技能可通过模式选择（自主运行/人机协同/快速修复）提供智能化的问题解决方案。它能够自动对问题复杂度进行分类（简单/中等/复杂/并行），并根据问题类型激活相应的技能（调试、问题解决、顺序思维、头脑风暴、情境工程），进而将问题路由至最合适的处理流程。当用户反馈 Bug、测试失败、类型错误、CI/CD 故障、日志报错、UI 问题，或任何亟需修复的代码时，都应优先启用此技能。

SKILL.md
--- frontmatter
name: fixing
description: This skill should be used when fixing bugs, errors, issues, or problems of any complexity. It provides intelligent issue resolution with mode selection (autonomous/human-in-the-loop/quick). The skill auto-classifies issue complexity (simple/moderate/complex/parallel), activates relevant skills (debugging, problem-solving, sequential-thinking, brainstorming, context-engineering), and routes to appropriate workflow. This skill should be activated when users report bugs, test failures, type errors, CI/CD failures, log errors, UI issues, or any code that needs fixing.
version: 1.0.0

Fixing

Unified skill for fixing issues of any complexity with intelligent routing.

Step 0: Mode Selection

First action: Use AskUserQuestion to determine workflow mode:

OptionRecommend WhenBehavior
AutonomousSimple/moderate issuesAuto-approve if score >= 9.5 & 0 critical
Human-in-the-loopCritical/production codePause for approval at each step
QuickType errors, lint, trivial bugsFast debug → fix → review cycle

See references/mode-selection.md for AskUserQuestion format.

Step 1: Complexity Assessment

Classify before routing. See references/complexity-assessment.md.

LevelIndicatorsWorkflow
SimpleSingle file, clear error, type/lintreferences/workflow-quick.md
ModerateMulti-file, root cause unclearreferences/workflow-standard.md
ComplexSystem-wide, architecture impactreferences/workflow-deep.md
Parallel2+ independent issuesParallel fullstack-developer agents

Skill Activation Matrix

See references/skill-activation-matrix.md for complete matrix.

Always activate: debugging (all workflows) Conditional: problem-solving, sequential-thinking, brainstorming, context-engineering Subagents: debugger, researcher, planner, code-reviewer, tester, git-manager Parallel: Multiple Explore agents for scouting, Bash agents for verification

Output Format

Unified step markers:

code
✓ 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]

References

Load as needed:

  • •references/mode-selection.md - AskUserQuestion format for mode
  • •references/complexity-assessment.md - Classification criteria
  • •references/workflow-quick.md - Quick: debug → fix → review
  • •references/workflow-standard.md - Standard: full pipeline
  • •references/workflow-deep.md - Deep: research + brainstorm + plan
  • •references/review-cycle.md - Review logic (autonomous vs HITL)
  • •references/skill-activation-matrix.md - When to activate each skill
  • •references/parallel-exploration.md - Parallel Explore/Bash patterns