Rapidly fix small bugs and minor improvements in development environment. Use when user mentions バグ修正, 直して, 修正して, fix bug, 不具合. Do NOT use for new feature implementation or large-scale changes (use /code instead).
From shipnpx claudepluginhub thkt/dotclaude --plugin toolkitThis skill is limited to using the following tools:
references/defense-in-depth.mdProvides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Calculates TAM/SAM/SOM using top-down, bottom-up, and value theory methodologies for market sizing, revenue estimation, and startup validation.
Rapidly fix small bugs with root cause analysis and TDD verification.
$1/audit output (e.g., /fix SUG-001)$1 is empty → select fix type via AskUserQuestion| Question | Options |
|---|---|
| Fix type | Bug fix / Error message / Test failure |
| Description | [free text via Other] |
/fix SUG-XXX)| Step | Action |
|---|---|
| 1 | Read latest snapshot from $HOME/.claude/workspace/history/ |
| 2 | Find matching suggestion by ID |
| 3 | Apply fix directly (skip 5 Whys) |
| 4 | Verify tests pass |
| 5 | Suggest targeted re-audit: /audit <modified files> |
| Type | Name | Purpose |
|---|---|---|
| Skill | analyzing-root-causes | 5 Whys methodology |
| Agent | test-generator | Regression test creation (fork) |
| Agent | build-error-resolver | TypeScript/build error fix |
| Reference | defense-in-depth | Post-fix multi-layer validation |
Run project build command (detect from package.json or project config).
| Result | Action |
|---|---|
| Build errors | Task with subagent_type: build-error-resolver |
| No errors | Continue to Step 1 |
| Step | Action |
|---|---|
| 1 | Root cause analysis (5 Whys) |
| 2 | Task with subagent_type: test-generator for reg test (pass symptom + repro steps only) |
| 3 | Fix implementation |
| 4 | Verify all tests pass |
| Confidence | Action |
|---|---|
| [?] <50% | Escalate → /research immediately |
| 50-69% | Ask user: continue with defensive checks or escalate |
| Complex | Multi-file → /code |
| New scope | Feature → /think |
| Error | Action |
|---|---|
| build-error-resolver fails | Present error, ask user for guidance |
| test-generator timeout | Skip regression test, proceed with fix |
| Tests still fail after fix | Re-analyze root cause or escalate |
| ≥3 fix attempts fail | STOP. Escalate to /research with full context |
The ≥3 rule: if three distinct fix attempts fail, the issue is likely architectural, not a local bug. Do not attempt fix #4 without escalating.
| Check | Required |
|---|---|
| Root cause identified? | Yes |
| All tests pass? | Yes |