latch

Solid

Proposing, configuring, debugging, and maintaining Claude Code hooks (PreToolUse/PostToolUse/Stop and other lifecycle events). Use for workflow automation or quality gates via hooks.

AI & Automation 72 stars 14 forks Updated today MIT

Install

View on GitHub

Quality Score: 85/100

Stars 20%
62
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

<!-- CAPABILITIES_SUMMARY: - hook_design: Propose hook sets with event, matcher, type, and justification - hook_configuration: Configure settings.json hook entries with backup and validation - hook_debugging: Diagnose hook failures, timing issues, and misfires - event_selection: Choose from 26 lifecycle events (tool, permission, task, config, file, worktree, compaction, elicitation) - matcher_design: Exact, OR, wildcard, and regex tool-name matching - blocking_hook_management: Justify and configure exit-2 / permissionDecision deny hooks - command_hook_scripting: Shell hooks with stdin parsing, PID-scoped temp files, timeouts - prompt_hook_design: Context-aware prompt hooks for policy decisions - hook_maintenance: Review false positives, matcher width, timeout cost, lifecycle fit - hook_type_selection: command vs prompt vs http vs agent by latency and verification depth - mcp_governance: Hooks that audit and verify MCP tool actions deterministically - hook_performance: Latency optimization, matcher consolidation, per-event caps, async hooks - input_modification: `updatedInput` hooks for path correction, secret redaction, dry-run injection - conditional_filtering: `if` field for fine-grained filtering within matchers - plugin_hook_design: Plugin hooks via hooks/hooks.json with persistent data dirs and runtime merging - frontmatter_hooks: Component-scoped hooks in skill/agent frontmatter with auto-cleanup - dependency_safety: Fail-open/fail-closed strategies for hooks with exter...

Details

Author
simota
Repository
simota/agent-skills
Created
7 months ago
Last Updated
today
Language
HTML
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

hook-development

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

1 Updated 1 weeks ago
mostwise
AI & Automation Solid

hook-development

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

5 Updated 2 days ago
ValorVie
AI & Automation Featured

hook-development

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

33,765 Updated today
anthropics