Quality hooks
Skill a5c-ai/babysitter/library/methodologies/pilot-shell/skills/quality-hooks
Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration
npx -y skills add a5c-ai/babysitter --skill quality-hooksAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
SKILL.md
1.7 KB, as published. Nobody here has run it
Auto-Fix Convergence Loop
When quality checks fail:
- Apply all auto-fixable issues
- Re-run quality checks
- Repeat up to 3 times
- Report remaining unfixable issues
Quality Scoring
Composite score = weighted average:
- Lint: 25%
- Format: 15%
- Typecheck: 25%
- Tests: 35%
Target: 85/100 (configurable via targetQuality)
Hook Integration Points
| Pilot Shell Hook | Quality Action |
|---|---|
| PostToolUse (Edit/Write) | Run file_checker on modified files |
| PostToolUse (file creation) | Run full pipeline on new files |
| Pre-merge | Run full pipeline on all changes |