claude/skills/bugfix/SKILL.md
bastien ed81d13d76 feat(skills): add /hotfix, /bugfix, and /feat lightweight skills
Fill the gap between direct editing and the full /ship-feature
orchestrator. Three new skills for common everyday tasks:
- /hotfix: superficial bugs (typo, CSS, config), 1-2 files, no plan
- /bugfix: deeper bugs with root cause investigation + fix plan
- /feat: small features 1-5 files, light planning, no subagents

Each skill documents its escalation path to the next level.
Updated plugin-advisor with skill routing table and references.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-13 15:32:55 +02:00

148 lines
4.0 KiB
Markdown

---
name: bugfix
description: |
Structured bug fix with root cause investigation. For bugs where
the cause isn't immediately obvious, spans multiple files, or
requires careful analysis before fixing. Includes hypothesis-driven
investigation and a fix plan.
Trigger: "bugfix", "debug this", "fix this bug", "pourquoi ca marche pas",
"investigate and fix", "find and fix", "root cause + fix".
For obvious 1-2 file fixes → use /hotfix instead.
For bugs that need investigation only (no fix) → use /analyze.
argument-hint: <bug description, error message, or stack trace>
disable-model-invocation: false
allowed-tools:
- Read
- Edit
- Write
- Bash
- Grep
- Glob
- Agent
---
# BUGFIX — Structured Bug Fix
Investigate, understand, plan, fix. No guessing. The iron law:
understand the root cause before writing a single fix.
## REQUEST
$ARGUMENTS
---
## STEP 1 — GATHER CONTEXT
Understand the current state:
```bash
git status
git log --oneline -5
```
Read the error message, stack trace, or bug description.
Identify:
- **What** is broken (symptom)
- **Where** it manifests (file, line, endpoint, UI element)
- **When** it started (recent commit? always? after a deploy?)
```bash
# If the user mentions "it was working before":
git log --oneline -20 --all -- <suspected files>
```
## STEP 2 — INVESTIGATE
Trace the bug from symptom to root cause:
1. Read the code path involved (follow the data flow).
2. Check recent changes to the affected files:
```bash
git log --oneline -10 -- <file>
git diff HEAD~5 -- <file> # if recent regression suspected
```
3. Look for related tests — do they pass? Do they cover
the broken case?
4. Search for similar patterns elsewhere that might have
the same bug:
```bash
# grep for the same pattern to assess blast radius
```
## STEP 3 — HYPOTHESIZE + PLAN
Present findings before fixing:
```
BUGFIX — DIAGNOSIS
BUG : <one-line symptom>
ROOT CAUSE: <what is actually wrong and why>
EVIDENCE: <what confirmed it — test, trace, diff>
BLAST RADIUS: <other places affected, or "isolated">
FIX PLAN:
1. <file:line> — <what to change>
2. <file:line> — <what to change>
[3. <test file> — add/update test for this case]
RISK: <low/medium — what could go wrong>
```
- If the root cause is still unclear after investigation,
say so explicitly. List remaining hypotheses ranked by
probability. Ask the user before proceeding.
- If the fix is trivial after investigation (1-2 lines):
proceed directly — no need to wait for approval on an
obvious fix.
- If the fix is significant (>10 lines, multiple files,
behavior change): wait for user approval.
## STEP 4 — FIX
Apply the fix following the plan:
- Fix the root cause, not the symptom.
- Add or update tests to cover the bug case (regression test).
- If no test framework exists: document what you verified.
- Keep changes minimal — fix the bug, nothing else.
## STEP 5 — VERIFY + COMMIT
1. Run the full relevant test suite:
```bash
# detect and run tests
```
2. If a build step exists, verify it passes.
3. Check for regressions in related functionality.
4. Commit using conventional format:
```
fix(<scope>): <root cause description>
<what was wrong and why>
<what the fix does>
Co-Authored-By: Claude <noreply@anthropic.com>
```
5. Print summary:
```
BUGFIX COMPLETE
BUG : <symptom>
ROOT CAUSE : <one-line>
FILE(S) : <changed files>
TEST(S) : <added/updated tests, or "none verified manually">
REGRESSION : <checked areas>
```
---
## RULES
- No fix without understanding the root cause first.
- No plugin check (lightweight skill, not an orchestrator).
- If investigation reveals a design flaw requiring significant
refactoring → stop, explain, suggest `/ship-feature` for the
proper fix.
- Always add a regression test when possible.
- Keep the fix scoped. No "while we're here" cleanups.
- If >5 files need changes → reconsider if `/ship-feature`
is more appropriate.