65 lines
2.2 KiB
Markdown
65 lines
2.2 KiB
Markdown
---
|
|
name: ck-fixing
|
|
description: Fix bugs, errors, test failures, CI/CD issues with intelligent complexity routing. Use when reporting bugs, type errors, log errors, UI issues, code problems. Auto-classifies complexity and activates relevant skills.
|
|
---
|
|
|
|
# ck-fixing
|
|
|
|
Unified skill for fixing issues of any complexity with intelligent routing. Lightweight alias of `ck-fix` with the same workflow.
|
|
|
|
## When to Use
|
|
|
|
- Bugs, errors, test failures reported by users or CI
|
|
- Type errors, lint failures
|
|
- UI visual issues
|
|
- Code problems of any kind
|
|
|
|
## Don't Use When
|
|
|
|
- Task is a new feature — use `ck-cook` or `ck-planning`
|
|
- You need only diagnosis, not a fix — use `ck-debug`
|
|
|
|
## Step 0: Mode Selection
|
|
|
|
Ask user to select workflow mode (unless `auto` is in the request):
|
|
|
|
| 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 |
|
|
|
|
## Step 1: Complexity Assessment
|
|
|
|
| Level | Indicators | Workflow |
|
|
|-------|------------|----------|
|
|
| **Simple** | Single file, clear error, type/lint | Quick workflow |
|
|
| **Moderate** | Multi-file, root cause unclear | Standard workflow |
|
|
| **Complex** | System-wide, architecture impact | Deep workflow |
|
|
| **Parallel** | 2+ independent issues | Parallel developer agents |
|
|
|
|
## Skill Activation Matrix
|
|
|
|
**Always activate:** `ck-debug`
|
|
**Conditional:** `ck-sequential-thinking`, `ck-brainstorm`
|
|
**Parallel agents:** Exploration agents for scouting; verification agents for confirming fixes
|
|
|
|
## Output Format
|
|
|
|
```
|
|
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]
|
|
```
|
|
|
|
## Specialized Scenarios
|
|
|
|
- **CI/CD failures**: Fetch logs via `gh` command
|
|
- **Log errors**: Parse and correlate with code changes
|
|
- **Test failures**: Run suite, analyze, bisect if needed
|
|
- **Type errors**: Trace TypeScript compiler output
|
|
- **UI issues**: Visual comparison with reference screenshots
|