cc-fix
A structured workflow for fixing bugs or debugging issues. Provides distinct modes for direct fixes versus evidence-based root cause analysis.
Install
mkdir -p .claude/skills/cc-fix && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17468" && unzip -o skill.zip -d .claude/skills/cc-fix && rm skill.zipInstalls to .claude/skills/cc-fix
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
结构化 bug 修复工作流，适用于显式 fix 或 debug 场景；不负责语言规范、正式 review 或运维审批。Key capabilities
- →Confirm expected behavior and current symptoms.
- →Read relevant code paths.
- →Perform minimal effective fixes.
- →Conduct targeted verification on original problem paths.
- →Explain residual risks.
- →Formulate and validate specific hypotheses for debugging.
How it works
This skill provides a structured workflow for bug fixing and debugging, either through a 'Fix Mode' for clear issues or a 'Debug Mode' for unclear root causes, involving hypothesis testing and minimal effective changes.
Inputs & outputs
When to use cc-fix
- →Debugging a persistent application error
- →Fixing a confirmed application bug
- →Performing root cause analysis for production issues
About this skill
Fix
流程主权声明：本技能是用户显式调用的修复/调试工作流，已包含 Fix Mode 和 Debug Mode 两套独立流程。 禁止在本流程执行期间调用任何会接管修复/调试流程的外部 skill；本技能自己就是调试流程，无需再嵌套一层。 业务领域类 skill（如
cc-redis-safety、cc-api-contract-safety、cc-external-system-debugging、cc-payment-callback-safety、cc-time-zone-safety等触发条件匹配的安全/规范类技能）正常按需加载，仅作防御性参考，不接管流程。 本声明依据用户显式指令优先原则：显式调用$cc-fix时，本技能拥有修复/调试主流程控制权。
当用户明确要求修复问题、定位 bug 或进入 debug 流程时，使用本技能。
不要用于：
- 普通功能实现
- 语言或框架风格规范
- 正式 code review
- 环境级风险判断
模式
进入 fix 前，若项目内已有主线任务处于 进行中，且本次 fix 只是临时插入事项，先用 cc-task-state 或直接在主线任务文件里补“中断记录”，写明当前做到哪、为何切出、恢复入口和下一步，再进入修复流程。
Fix Mode
适用于问题边界较清楚、可以直接修复的场景。
- 确认期望行为和当前症状。
- 阅读相关代码路径。
- 做最小有效修复。
- 对原始问题路径做定向验证。
- 说明残余风险。
Debug Mode
适用于症状明确但根因不清楚的场景。
- 复现或描述症状。
- 提出具体假设。
- 用低成本检查验证假设。
- 基于证据做最小修复。
- 回测原始问题路径。
补充检查
- 遇到前后端联调、列表页、分页、筛选项或详情页异常时，补充使用
cc-api-contract-safety - 遇到浏览器、编辑器、CDN/WAF、剪贴板、IM 平台、第三方 SaaS 等外部黑盒系统异常，或连续 2 轮凭代码推理修复 no-op 时，补充使用
cc-external-system-debugging，先抓真实数据再推理 - 若 fix 会打断当前主线任务，优先记录 checkpoint；只有范围独立、可能跨多轮的插入修复才单独建任务
- 先核对真实接口返回、统一成功响应格式和分页结构，再决定修后端根因还是保留前端临时兼容
- 若保留兼容分支，必须说明退出条件，不把双格式兼容长期固化
输出要求
- 明确区分症状、假设、修复和验证。
- 若本次修复打断了主线任务，明确说明是否已补 checkpoint，以及主线如何恢复。
- 没有证据时，不声称已经找到根因。
- 不因调试过程顺手扩大问题范围。
按需展开
- 直接修复：
references/fix-mode.md - 结构化排查：
references/debug-mode.md - 修复后验证：
references/verification-after-fix.md
When not to use it
- →Do not use for ordinary feature implementation.
- →Do not use for language or framework style guidelines.
- →Do not use for formal code review or environment-level risk assessment.
Limitations
- →The skill does not handle language or framework style guidelines.
- →It does not perform formal code reviews.
- →It does not conduct environment-level risk assessments.
How it compares
This skill offers a structured, two-mode approach to bug fixing and debugging with explicit steps for confirmation, minimal changes, and verification, which is more systematic than an ad-hoc repair process.
Compared to similar skills
cc-fix side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| cc-fix (this skill) | 0 | 1mo | No flags | Intermediate |
| python-testing-patterns | 77 | 2mo | Review | Intermediate |
| chrome-devtools | 41 | 6mo | Review | Intermediate |
| bats | 9 | 7mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
python-testing-patterns
wshobson
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.
chrome-devtools
mrgoonie
Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.
bats
OleksandrKucherenko
Bash Automated Testing System (BATS) for TDD-style testing of shell scripts. Use when: (1) Writing unit or integration tests for Bash scripts, (2) Testing CLI tools or shell functions, (3) Setting up test infrastructure with setup/teardown hooks, (4) Mocking external commands (curl, git, docker), (5) Generating JUnit reports for CI/CD, (6) Debugging test failures or flaky tests, (7) Implementing test-driven development for shell scripts.
browser-daemon
noiv
Persistent browser automation via Playwright daemon. Keep a browser window open and send it commands (navigate, execute JS, inspect console). Perfect for interactive debugging, development, and testing web applications. Use when you need to interact with a browser repeatedly without opening/closing it.
performance-profiling
davila7
Performance profiling principles. Measurement, analysis, and optimization techniques.
obsidian-local-dev-loop
jeremylongshore
Configure Obsidian plugin development with hot-reload and fast iteration. Use when setting up development workflow, configuring test vaults, or establishing a rapid development cycle. Trigger with phrases like "obsidian dev loop", "obsidian hot reload", "obsidian development workflow", "develop obsidian plugin".