from ordinary-claude-skills11
Author Hookify rule files (.claude/hookify.*.local.md) to detect patterns (bash, file, prompt, stop) and show actionable messages — ideal for enforcing safety,
This skill explains how to write Hookify rules — small markdown files with YAML frontmatter — that watch for patterns across bash commands, file edits, prompts, and agent stop events. It guides authors through frontmatter fields (name, enabled, event, pattern, conditions), pattern syntax (Python regex), and composing message bodies that explain why a match matters and what to do instead.
Use this skill when you need to: create warnings or blocks for dangerous shell commands (e.g., rm -rf), detect debug/sensitive code (console.log, API keys, .env edits), add pre-stop checklists, or match prompt content to require extra validation. It's useful during repo hardening, CI guardrails, and agent-run tool safety enforcement.
Agents that run or enforce repo-local rules and support pre-tool hooks (Claude-based agents, local automation pilots) will benefit from these rules. The guidance is tool-agnostic and works wherever hook files are consumed.
A purely documentation skill that guides users in creating Hookify rule files (.claude/hookify.*.local.md) for Claude Code. No scripts or automation — it's a comprehensive reference guide covering YAML frontmatter, regex patterns, event types, and condition syntax. Well-written content but monolithic structure with everything in a single SKILL.md.
Clean skill with no security concerns. Good documentation quality but could benefit from splitting examples into a references/ directory. The skill is essentially a well-organized readme rather than an automated agent skill.
