[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M737PAPCX4CZG2WHRKTCGGZK":3,"skill-same:01M737PAPCX4CZG2WHRKTCGGZK":49},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M737PAPCX4CZG2WHRKTCGGZK","create-hooks",null,"Expert guidance for creating, configuring, and using Claude Code hooks. Use when working with hooks, setting up event listeners, validating commands, automating workflows, adding notifications, or understanding hook types (PreToolUse, PostToolUse, Stop, SessionStart, UserPromptSubmit, etc).","Horonomos-laps\u002FYana-AI","Horonomos-laps","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F355299122?v=4","01M76B3QPXE88ET2SQPDPVATZT"," Horonomos-laps","01M72ZQRJPCYPSSWT4D00VJR2A",13,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftaches--create-hooks\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: create-hooks\ndescription: Expert guidance for creating, configuring, and using Claude Code hooks. Use when working with hooks, setting up event listeners, validating commands, automating workflows, adding notifications, or understanding hook types (PreToolUse, PostToolUse, Stop, SessionStart, UserPromptSubmit, etc).\norigin: \"https:\u002F\u002Fraw.githubusercontent.com\u002Fglittercowboy\u002Ftaches-cc-resources\u002Fmain\u002Fskills\u002Fcreate-hooks\u002FSKILL.md\"\n---\n\n\u003Cobjective>\nHooks are event-driven automation for Claude Code that execute shell commands or LLM prompts in response to tool usage, session events, and user interactions. This skill teaches you how to create, configure, and debug hooks for validating commands, automating workflows, injecting context, and implementing custom completion criteria.\n\nHooks provide programmatic control over Claude's behavior without modifying core code, enabling project-specific automation, safety checks, and workflow customization.\n\u003C\u002Fobjective>\n\n\u003Ccontext>\nHooks are shell commands or LLM-evaluated prompts that execute in response to Claude Code events. They operate within an event hierarchy: events (PreToolUse, PostToolUse, Stop, etc.) trigger matchers (tool patterns) which fire hooks (commands or prompts). Hooks can block actions, modify tool inputs, inject context, or simply observe and log Claude's operations.\n\u003C\u002Fcontext>\n\n\u003Cquick_start>\n\u003Cworkflow>\n1. Create hooks config file:\n   - Project: `.claude\u002Fhooks.json`\n   - User: `~\u002F.claude\u002Fhooks.json`\n2. Choose hook event (when it fires)\n3. Choose hook type (command or prompt)\n4. Configure matcher (which tools trigger it)\n5. Test with `claude --debug`\n\u003C\u002Fworkflow>\n\n\u003Cexample>\n**Log all bash commands**:\n\n`.claude\u002Fhooks.json`:\n```json\n{\n  \"hooks\": {\n    \"PreToolUse\": [\n      {\n        \"matcher\": \"Bash\",\n        \"hooks\": [\n          {\n            \"type\": \"command\",\n            \"command\": \"jq -r '\\\"\\\\(.tool_input.command) - \\\\(.tool_input.description \u002F\u002F \\\\\\\"No description\\\\\\\")\\\"' >> ~\u002F.claude\u002Fbash-log.txt\"\n          }\n        ]\n      }\n    ]\n  }\n}\n```\n\nThis hook:\n- Fires before (`PreToolUse`) every `Bash` tool use\n- Executes a `command` (not an LLM prompt)\n- Logs command + description to a file\n\u003C\u002Fexample>\n\u003C\u002Fquick_start>\n\n\u003Chook_types>\n| Event | When it fires | Can block? |\n|-------|---------------|------------|\n| **PreToolUse** | Before tool execution | Yes |\n| **PostToolUse** | After tool execution | No |\n| **UserPromptSubmit** | User submits a prompt | Yes |\n| **Stop** | Claude attempts to stop | Yes |\n| **SubagentStop** | Subagent attempts to stop | Yes |\n| **SessionStart** | Session begins | No |\n| **SessionEnd** | Session ends | No |\n| **PreCompact** | Before context compaction | Yes |\n| **Notification** | Claude needs input | No |\n\nBlocking hooks can return `\"decision\": \"block\"` to prevent the action. See [references\u002Fhook-types.md](references\u002Fhook-types.md) for detailed use cases.\n\u003C\u002Fhook_types>\n\n\u003Chook_anatomy>\n\u003Chook_type name=\"command\">\n**Type**: Executes a shell command\n\n**Use when**:\n- Simple validation (check file exists)\n- Logging (append to file)\n- External tools (formatters, linters)\n- Desktop notifications\n\n**Input**: JSON via stdin\n**Output**: JSON via stdout (optional)\n\n```json\n{\n  \"type\": \"command\",\n  \"command\": \"\u002Fpath\u002Fto\u002Fscript.sh\",\n  \"timeout\": 30000\n}\n```\n\u003C\u002Fhook_type>\n\n\u003Chook_type name=\"prompt\">\n**Type**: LLM evaluates a prompt\n\n**Use when**:\n- Complex decision logic\n- Natural language validation\n- Context-aware checks\n- Reasoning required\n\n**Input**: Prompt with `$ARGUMENTS` placeholder\n**Output**: JSON with `decision` and `reason`\n\n```json\n{\n  \"type\": \"prompt\",\n  \"prompt\": \"Evaluate if this command is safe: $ARGUMENTS\\n\\nReturn JSON: {\\\"decision\\\": \\\"approve\\\" or \\\"block\\\", \\\"reason\\\": \\\"explanation\\\"}\"\n}\n```\n\u003C\u002Fhook_type>\n\u003C\u002Fhook_anatomy>\n\n\u003Cmatchers>\nMatchers filter which tools trigger the hook:\n\n```json\n{\n  \"matcher\": \"Bash\",           \u002F\u002F Exact match\n  \"matcher\": \"Write|Edit\",     \u002F\u002F Multiple tools (regex OR)\n  \"matcher\": \"mcp__.*\",        \u002F\u002F All MCP tools\n  \"matcher\": \"mcp__memory__.*\" \u002F\u002F Specific MCP server\n}\n```\n\n**No matcher**: Hook fires for all tools\n```json\n{\n  \"hooks\": {\n    \"UserPromptSubmit\": [\n      {\n        \"hooks\": [...]  \u002F\u002F No matcher - fires on every user prompt\n      }\n    ]\n  }\n}\n```\n\u003C\u002Fmatchers>\n\n\u003Cinput_output>\nHooks receive JSON via stdin with session info, current directory, and event-specific data. Blocking hooks can return JSON to approve\u002Fblock actions or modify inputs.\n\n**Example output** (blocking hooks):\n```json\n{\n  \"decision\": \"approve\" | \"block\",\n  \"reason\": \"Why this decision was made\"\n}\n```\n\nSee [references\u002Finput-output-schemas.md](references\u002Finput-output-schemas.md) for complete schemas for each hook type.\n\u003C\u002Finput_output>\n\n\u003Cenvironment_variables>\nAvailable in hook commands:\n\n| Variable | Value |\n|----------|-------|\n| `$CLAUDE_PROJECT_DIR` | Project root directory |\n| `${CLAUDE_PLUGIN_ROOT}` | Plugin directory (plugin hooks only) |\n| `$ARGUMENTS` | Hook input JSON (prompt hooks only) |\n\n**Example**:\n```json\n{\n  \"command\": \"$CLAUDE_PROJECT_DIR\u002F.claude\u002Fhooks\u002Fvalidate.sh\"\n}\n```\n\u003C\u002Fenvironment_variables>\n\n\u003Ccommon_patterns>\n**Desktop notification when input needed**:\n```json\n{\n  \"hooks\": {\n    \"Notification\": [\n      {\n        \"hooks\": [\n          {\n            \"type\": \"command\",\n            \"command\": \"osascript -e 'display notification \\\"Claude needs input\\\" with title \\\"Claude Code\\\"'\"\n          }\n        ]\n      }\n    ]\n  }\n}\n```\n\n**Block destructive git commands**:\n```json\n{\n  \"hooks\": {\n    \"PreToolUse\": [\n      {\n        \"matcher\": \"Bash\",\n        \"hooks\": [\n          {\n            \"type\": \"prompt\",\n            \"prompt\": \"Check if this command is destructive: $ARGUMENTS\\n\\nBlock if it contains: 'git push --force', 'rm -rf', 'git reset --hard'\\n\\nReturn: {\\\"decision\\\": \\\"approve\\\" or \\\"block\\\", \\\"reason\\\": \\\"explanation\\\"}\"\n          }\n        ]\n      }\n    ]\n  }\n}\n```\n\n**Auto-format code after edits**:\n```json\n{\n  \"hooks\": {\n    \"PostToolUse\": [\n      {\n        \"matcher\": \"Write|Edit\",\n        \"hooks\": [\n          {\n            \"type\": \"command\",\n            \"command\": \"prettier --write $CLAUDE_PROJECT_DIR\",\n            \"timeout\": 10000\n          }\n        ]\n      }\n    ]\n  }\n}\n```\n\n**Add context at session start**:\n```json\n{\n  \"hooks\": {\n    \"SessionStart\": [\n      {\n        \"hooks\": [\n          {\n            \"type\": \"command\",\n            \"command\": \"echo '{\\\"hookSpecificOutput\\\": {\\\"hookEventName\\\": \\\"SessionStart\\\", \\\"additionalContext\\\": \\\"Current sprint: Sprint 23. Focus: User authentication\\\"}}'\"\n          }\n        ]\n      }\n    ]\n  }\n}\n```\n\u003C\u002Fcommon_patterns>\n\n\u003Cdebugging>\nAlways test hooks with the debug flag:\n```bash\nclaude --debug\n```\n\nThis shows which hooks matched, command execution, and output. See [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for common issues and solutions.\n\u003C\u002Fdebugging>\n\n\u003Creference_guides>\n**Hook types and events**: [references\u002Fhook-types.md](references\u002Fhook-types.md)\n- Complete list of hook events\n- When each event fires\n- Input\u002Foutput schemas for each\n- Blocking vs non-blocking hooks\n\n**Command vs Prompt hooks**: [references\u002Fcommand-vs-prompt.md](references\u002Fcommand-vs-prompt.md)\n- Decision tree: which type to use\n- Command hook patterns and examples\n- Prompt hook patterns and examples\n- Performance considerations\n\n**Matchers and patterns**: [references\u002Fmatchers.md](references\u002Fmatchers.md)\n- Regex patterns for tool matching\n- MCP tool matching patterns\n- Multiple tool matching\n- Debugging matcher issues\n\n**Input\u002FOutput schemas**: [references\u002Finput-output-schemas.md](references\u002Finput-output-schemas.md)\n- Complete schema for each hook type\n- Field descriptions and types\n- Hook-specific output fields\n- Example JSON for each event\n\n**Working examples**: [references\u002Fexamples.md](references\u002Fexamples.md)\n- Desktop notifications\n- Command validation\n- Auto-formatting workflows\n- Logging and audit trails\n- Stop logic patterns\n- Session context injection\n\n**Troubleshooting**: [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md)\n- Hooks not triggering\n- Command execution failures\n- Prompt hook issues\n- Permission problems\n- Timeout handling\n- Debug workflow\n\u003C\u002Freference_guides>\n\n\u003Csecurity_checklist>\n**Critical safety requirements**:\n\n- **Infinite loop prevention**: Check `stop_hook_active` flag in Stop hooks to prevent recursive triggering\n- **Timeout configuration**: Set reasonable timeouts (default: 60s) to prevent hanging\n- **Permission validation**: Ensure hook scripts have executable permissions (`chmod +x`)\n- **Path safety**: Use absolute paths with `$CLAUDE_PROJECT_DIR` to avoid path injection\n- **JSON validation**: Validate hook config with `jq` before use to catch syntax errors\n- **Selective blocking**: Be conservative with blocking hooks to avoid workflow disruption\n\n**Testing protocol**:\n```bash\n# Always test with debug flag first\nclaude --debug\n\n# Validate JSON config\njq . .claude\u002Fhooks.json\n```\n\u003C\u002Fsecurity_checklist>\n\n\u003Csuccess_criteria>\nA working hook configuration has:\n\n- Valid JSON in `.claude\u002Fhooks.json` (validated with `jq`)\n- Appropriate hook event selected for the use case\n- Correct matcher pattern that matches target tools\n- Command or prompt that executes without errors\n- Proper output schema (decision\u002Freason for blocking hooks)\n- Tested with `--debug` flag showing expected behavior\n- No infinite loops in Stop hooks (checks `stop_hook_active` flag)\n- Reasonable timeout set (especially for external commands)\n- Executable permissions on script files if using file paths\n\u003C\u002Fsuccess_criteria>\n","\u003Cobjective>\nHooks are event-driven automation for Claude Code that execute shell commands or LLM prompts in response to tool usage, session events, and user interactions. This skill teaches you how to create, configure, and debug hooks for validating commands, automating workflows, injecting context, and implementing custom completion criteria.\n\nHooks provide programmatic control over Claude's behavior without modifying core code, enabling project-specific automation, safety checks, and workflow customization.\n\u003C\u002Fobjective>\n\n\u003Ccontext>\nHooks are shell commands or LLM-evaluated prompts that execute in response to Claude Code events. They operate within an event hierarchy: events (PreToolUse, PostToolUse, Stop, etc.) trigger matchers (tool patterns) which fire hooks (commands or prompts). Hooks can block actions, modify tool inputs, inject context, or simply observe and log Claude's operations.\n\u003C\u002Fcontext>\n\n\u003Cquick_start>\n\u003Cworkflow>\n1. Create hooks config file:\n   - Project: `.claude\u002Fhooks.json`\n   - User: `~\u002F.claude\u002Fhooks.json`\n2. Choose hook event (when it fires)\n3. Choose hook type (command or prompt)\n4. Configure matcher (which tools trigger it)\n5. Test with `claude --debug`\n\u003C\u002Fworkflow>\n\n\u003Cexample>\n**Log all bash commands**:\n\n`.claude\u002Fhooks.json`:\n```json\n{\n  \"hooks\": {\n    \"PreToolUse\": [\n      {\n        \"matcher\": \"Bash\",\n        \"hooks\": [\n          {\n            \"type\": \"command\",\n            \"command\": \"jq -r '\\\"\\\\(.tool_input.command) - \\\\(.tool_input.description \u002F\u002F \\\\\\\"No description\\\\\\\")\\\"' >> ~\u002F.claude\u002Fbash-log.txt\"\n          }\n        ]\n      }\n    ]\n  }\n}\n```\n\nThis hook:\n- Fires before (`PreToolUse`) every `Bash` tool use\n- Executes a `command` (not an LLM prompt)\n- Logs command + description to a file\n\u003C\u002Fexample>\n\u003C\u002Fquick_start>\n\n\u003Chook_types>\n| Event | When it fires | Can block? |\n|-------|---------------|------------|\n| **PreToolUse** | Before tool execution | Yes |\n| **PostToolUse** | After tool execution | No |\n| **UserPromptSubmit** | User submits a prompt | Yes |\n| **Stop** | Claude attempts to stop | Yes |\n| **SubagentStop** | Subagent attempts to stop | Yes |\n| **SessionStart** | Session begins | No |\n| **SessionEnd** | Session ends | No |\n| **PreCompact** | Before context compaction | Yes |\n| **Notification** | Claude needs input | No |\n\nBlocking hooks can return `\"decision\": \"block\"` to prevent the action. See [references\u002Fhook-types.md](references\u002Fhook-types.md) for detailed use cases.\n\u003C\u002Fhook_types>\n\n\u003Chook_anatomy>\n\u003Chook_type name=\"command\">\n**Type**: Executes a shell command\n\n**Use when**:\n- Simple validation (check file exists)\n- Logging (append to file)\n- External tools (formatters, linters)\n- Desktop notifications\n\n**Input**: JSON via stdin\n**Output**: JSON via stdout (optional)\n\n```json\n{\n  \"type\": \"command\",\n  \"command\": \"\u002Fpath\u002Fto\u002Fscript.sh\",\n  \"timeout\": 30000\n}\n```\n\u003C\u002Fhook_type>\n\n\u003Chook_type name=\"prompt\">\n**Type**: LLM evaluates a prompt\n\n**Use when**:\n- Complex decision logic\n- Natural language validation\n- Context-aware checks\n- Reasoning required\n\n**Input**: Prompt with `$ARGUMENTS` placeholder\n**Output**: JSON with `decision` and `reason`\n\n```json\n{\n  \"type\": \"prompt\",\n  \"prompt\": \"Evaluate if this command is safe: $ARGUMENTS\\n\\nReturn JSON: {\\\"decision\\\": \\\"approve\\\" or \\\"block\\\", \\\"reason\\\": \\\"explanation\\\"}\"\n}\n```\n\u003C\u002Fhook_type>\n\u003C\u002Fhook_anatomy>\n\n\u003Cmatchers>\nMatchers filter which tools trigger the hook:\n\n```json\n{\n  \"matcher\": \"Bash\",           \u002F\u002F Exact match\n  \"matcher\": \"Write|Edit\",     \u002F\u002F Multiple tools (regex OR)\n  \"matcher\": \"mcp__.*\",        \u002F\u002F All MCP tools\n  \"matcher\": \"mcp__memory__.*\" \u002F\u002F Specific MCP server\n}\n```\n\n**No matcher**: Hook fires for all tools\n```json\n{\n  \"hooks\": {\n    \"UserPromptSubmit\": [\n      {\n        \"hooks\": [...]  \u002F\u002F No matcher - fires on every user prompt\n      }\n    ]\n  }\n}\n```\n\u003C\u002Fmatchers>\n\n\u003Cinput_output>\nHooks receive JSON via stdin with session info, current directory, and event-specific data. Blocking hooks can return JSON to approve\u002Fblock actions or modify inputs.\n\n**Example output** (blocking hooks):\n```json\n{\n  \"decision\": \"approve\" | \"block\",\n  \"reason\": \"Why this decision was made\"\n}\n```\n\nSee [references\u002Finput-output-schemas.md](references\u002Finput-output-schemas.md) for complete schemas for each hook type.\n\u003C\u002Finput_output>\n\n\u003Cenvironment_variables>\nAvailable in hook commands:\n\n| Variable | Value |\n|----------|-------|\n| `$CLAUDE_PROJECT_DIR` | Project root directory |\n| `${CLAUDE_PLUGIN_ROOT}` | Plugin directory (plugin hooks only) |\n| `$ARGUMENTS` | Hook input JSON (prompt hooks only) |\n\n**Example**:\n```json\n{\n  \"command\": \"$CLAUDE_PROJECT_DIR\u002F.claude\u002Fhooks\u002Fvalidate.sh\"\n}\n```\n\u003C\u002Fenvironment_variables>\n\n\u003Ccommon_patterns>\n**Desktop notification when input needed**:\n```json\n{\n  \"hooks\": {\n    \"Notification\": [\n      {\n        \"hooks\": [\n          {\n            \"type\": \"command\",\n            \"command\": \"osascript -e 'display notification \\\"Claude needs input\\\" with title \\\"Claude Code\\\"'\"\n          }\n        ]\n      }\n    ]\n  }\n}\n```\n\n**Block destructive git commands**:\n```json\n{\n  \"hooks\": {\n    \"PreToolUse\": [\n      {\n        \"matcher\": \"Bash\",\n        \"hooks\": [\n          {\n            \"type\": \"prompt\",\n            \"prompt\": \"Check if this command is destructive: $ARGUMENTS\\n\\nBlock if it contains: 'git push --force', 'rm -rf', 'git reset --hard'\\n\\nReturn: {\\\"decision\\\": \\\"approve\\\" or \\\"block\\\", \\\"reason\\\": \\\"explanation\\\"}\"\n          }\n        ]\n      }\n    ]\n  }\n}\n```\n\n**Auto-format code after edits**:\n```json\n{\n  \"hooks\": {\n    \"PostToolUse\": [\n      {\n        \"matcher\": \"Write|Edit\",\n        \"hooks\": [\n          {\n            \"type\": \"command\",\n            \"command\": \"prettier --write $CLAUDE_PROJECT_DIR\",\n            \"timeout\": 10000\n          }\n        ]\n      }\n    ]\n  }\n}\n```\n\n**Add context at session start**:\n```json\n{\n  \"hooks\": {\n    \"SessionStart\": [\n      {\n        \"hooks\": [\n          {\n            \"type\": \"command\",\n            \"command\": \"echo '{\\\"hookSpecificOutput\\\": {\\\"hookEventName\\\": \\\"SessionStart\\\", \\\"additionalContext\\\": \\\"Current sprint: Sprint 23. Focus: User authentication\\\"}}'\"\n          }\n        ]\n      }\n    ]\n  }\n}\n```\n\u003C\u002Fcommon_patterns>\n\n\u003Cdebugging>\nAlways test hooks with the debug flag:\n```bash\nclaude --debug\n```\n\nThis shows which hooks matched, command execution, and output. See [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) for common issues and solutions.\n\u003C\u002Fdebugging>\n\n\u003Creference_guides>\n**Hook types and events**: [references\u002Fhook-types.md](references\u002Fhook-types.md)\n- Complete list of hook events\n- When each event fires\n- Input\u002Foutput schemas for each\n- Blocking vs non-blocking hooks\n\n**Command vs Prompt hooks**: [references\u002Fcommand-vs-prompt.md](references\u002Fcommand-vs-prompt.md)\n- Decision tree: which type to use\n- Command hook patterns and examples\n- Prompt hook patterns and examples\n- Performance considerations\n\n**Matchers and patterns**: [references\u002Fmatchers.md](references\u002Fmatchers.md)\n- Regex patterns for tool matching\n- MCP tool matching patterns\n- Multiple tool matching\n- Debugging matcher issues\n\n**Input\u002FOutput schemas**: [references\u002Finput-output-schemas.md](references\u002Finput-output-schemas.md)\n- Complete schema for each hook type\n- Field descriptions and types\n- Hook-specific output fields\n- Example JSON for each event\n\n**Working examples**: [references\u002Fexamples.md](references\u002Fexamples.md)\n- Desktop notifications\n- Command validation\n- Auto-formatting workflows\n- Logging and audit trails\n- Stop logic patterns\n- Session context injection\n\n**Troubleshooting**: [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md)\n- Hooks not triggering\n- Command execution failures\n- Prompt hook issues\n- Permission problems\n- Timeout handling\n- Debug workflow\n\u003C\u002Freference_guides>\n\n\u003Csecurity_checklist>\n**Critical safety requirements**:\n\n- **Infinite loop prevention**: Check `stop_hook_active` flag in Stop hooks to prevent recursive triggering\n- **Timeout configuration**: Set reasonable timeouts (default: 60s) to prevent hanging\n- **Permission validation**: Ensure hook scripts have executable permissions (`chmod +x`)\n- **Path safety**: Use absolute paths with `$CLAUDE_PROJECT_DIR` to avoid path injection\n- **JSON validation**: Validate hook config with `jq` before use to catch syntax errors\n- **Selective blocking**: Be conservative with blocking hooks to avoid workflow disruption\n\n**Testing protocol**:\n```bash\n# Always test with debug flag first\nclaude --debug\n\n# Validate JSON config\njq . .claude\u002Fhooks.json\n```\n\u003C\u002Fsecurity_checklist>\n\n\u003Csuccess_criteria>\nA working hook configuration has:\n\n- Valid JSON in `.claude\u002Fhooks.json` (validated with `jq`)\n- Appropriate hook event selected for the use case\n- Correct matcher pattern that matches target tools\n- Command or prompt that executes without errors\n- Proper output schema (decision\u002Freason for blocking hooks)\n- Tested with `--debug` flag showing expected behavior\n- No infinite loops in Stop hooks (checks `stop_hook_active` flag)\n- Reasonable timeout set (especially for external commands)\n- Executable permissions on script files if using file paths\n\u003C\u002Fsuccess_criteria>\n",{"name":5,"origin":24,"description":7},"https:\u002F\u002Fraw.githubusercontent.com\u002Fglittercowboy\u002Ftaches-cc-resources\u002Fmain\u002Fskills\u002Fcreate-hooks\u002FSKILL.md","main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa",".claude\u002Fskills\u002Ftaches--create-hooks",2,"https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI","https:\u002F\u002Fyana.vutam.link\u002F","https:\u002F\u002Fgithub.com\u002FHoronomos-laps","https:\u002F\u002Fyana.vutam.link","An open-source governed runtime & execution environment for multi-agent AI systems.","2026-11-14 13:24:09",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add Horonomos-laps\u002FYana-AI --skill create-hooks",{"tool":41,"command":42},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill create-hooks",{"tool":44,"command":45},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill create-hooks","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftaches--create-hooks\u002FSKILL.md",true,[],[50,58,65,73,81,89],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":54,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M735GKET5YVYKAY62W2P5YXB","openai--sentry--sentry","Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.","MIT","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fopenai--sentry--sentry\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M73DCAP83T17HY7SMGK7MGFE","ito-basket-compare","Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fito-basket-compare\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":69,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M734CYEMZFDR3KH6SW0JP8TD","implementing-network-traffic-baselining","Build network traffic baselines from NetFlow\u002FIPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly\u002Fdaily traffic pattern profiling","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":77,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M73ASZ6NJRJM44Z2P84NGQ3Q","detecting-evasion-techniques-in-endpoint-logs","Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M734AFNXD06Z78QRK0VKGT7Q","implementing-microsegmentation-with-guardicore","Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M736TK27QMCXK0DVCH25SJN5","ramdisk-tmpfs-patterns","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Framdisk-tmpfs-patterns\u002FSKILL.md",[],[]]