Scaffold and validate Claude Code hooks blocks deterministically (scripts/scaffold_hook.py, scripts/validate_hook.py) for event-driven automation: format-on-save, file guards, notifications, quality gates. Use when the user asks to create, validate or fix a hook or a settings.json hooks block; hook-engineering owns the design rationale, this skill owns the emitted JSON. [EXPLICIT]
60
75%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./plugins/claude-native-toolkit/skills/hook-scaffold/SKILL.mdGeneric, brand-neutral engineering capability; sourced playbooks in
references//knowledge/. [DOC]
Create event-driven hooks — deterministic automation that fires at Claude Code lifecycle points. Hooks are programmatic control, NOT LLM judgment [EXPLICIT]
| Situation | Better alternative |
|---|---|
| Complex multi-file analysis | Agent (subagent) |
| User-invoked workflow | Skill |
| Always-on response style | Output style |
| Project-specific rules | CLAUDE.md |
Deep, evidence-tagged playbooks — open the one the task needs (ICM Layer 3, on-demand). [INFERENCE]
| Reference |
|---|
references/full-playbook.md |
references/ playbook. [EXPLICIT]Capas del packet, cargables bajo demanda (disciplina ICM: una capa por vez, nunca todas juntas): references/ guías de profundidad (cargar UNA por etapa) · knowledge/ cuerpo de conocimiento · prompts/ prompts listos · examples/ salida de ejemplo · agents/ subagentes del packet · templates/ plantilla de output · scripts/ automatización local · assets/ recursos estáticos.
e8f986b
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.