Writing Hookify Rules
anthropics/claude-codeHookify rules let you teach an AI agent what to watch for and how to respond. You write simple markdown files with a few settings. Each rule has a pattern to detect and a message to show. This helps the agent avoid mistakes or follow your preferences.
Anyone building with AI agents can use these rules. You can block dangerous commands like rm -rf or warn about console.log in code. Rules work on bash commands, file edits, or user prompts. You decide if the agent should just warn you or block the action entirely.
The format is easy to learn. You use YAML frontmatter to set the rule name, event type, and pattern. Then write the message in markdown below. Multiple conditions are also supported for more precise matching.
Add Writing Hookify Rules skill to your workflow
Global
mkdir -p ~/.claude/skills/writing-hookify-rulesProject
mkdir -p .claude/skills/writing-hookify-rulesSource Repository
More Prompt Engineering & Context Engineering Claude Code Skills
Cavemanjuliusbrussee/caveman
Talk like a smart caveman to save tokens without losing technical accuracy
Cavemanmattpocock/skills
Caveman mode for AI cuts token count 75% without losing technical accuracy
Enhance Promptgoogle-labs-code/stitch-skills
Turn vague UI ideas into clear, polished prompts with design system consistency
Humanizer Zhop7418/humanizer-zh
Remove AI writing patterns to make your text sound natural and human
Gws Modelarmorgoogleworkspace/cli
Filter harmful user content automatically with Google Model Armor for safety
Prompt Engineering Patternswshobson/agents
Master advanced prompt engineering patterns to get reliable and powerful AI outputs every time
Context Engineeringaddyosmani/agent-skills
Optimize your agent's context to improve output quality and focus
Writetw93/waza
Rewrite your prose to sound human and natural every time