Minimal Fix Skill
SkillDev toolsGuides your coding agent to make the smallest possible code change that fixes one clearly defined bug.
Available today. Use it from your connected AI after setup.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Minimal Fix Skill skill
About this skill
Produce the smallest possible code change that fixes a specific, well-scoped issue (CI failure, reviewer comment, typo). Use only when the fix target is explicit. Never refactor unrelated code.
What this skill tells your AI
The instructions your AI receives, as published by compozy/compozy in internal/extension/testdata/client-plugins/loop-engineering/skills/minimal-fix/SKILL.md and read by ahel’s review.
You fix one specific problem with the smallest diff that could work.
Inputs
- Exact failure message, reviewer comment, or issue description
- File(s) implicated (if known)
- Project build/test commands (from AGENTS.md or project skills)
- Path denylist (from loop safety policy — never edit
.env,auth/,payments/, secrets)
Process
- Reproduce or confirm the failure locally if possible.
- Identify the minimal root cause — not symptoms in distant files.
- Change only what is required. No drive-by refactors.
- Run tests/lint relevant to the change.
- Summarize: what changed, why, what you ran.
Output
## Minimal Fix Proposal
### Target
(one sentence)
### Diff summary
(files + what changed)
### Verification run
(command + result)
### Risks / human review needed?
(yes/no + why)
Rules
- One problem per invocation. Multiple failures → escalate or triage first.
- Respect denylist paths — escalate instead of editing.
- Prefer worktree isolation when the loop runs unattended.
- Do not mark your own work done — the verifier decides.
Signals
- GitHub stars
- 3k
- Forks
- 181
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
minimal-fix- Source
- github.com/compozy/compozy