[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71KY41AMD0XSD51EMTN4AVC":3,"skill-same:01M71KY41AMD0XSD51EMTN4AVC":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":6,"updatedAt":56,"install":57,"resources":70},"01M71KY41AMD0XSD51EMTN4AVC","hooks-automation",null,"Set up and use monomind hooks: pre\u002Fpost edit, command and task hooks, sessions, routing, pattern logging, background workers, settings.json and Git hooks.","monoes\u002Fmonomind","monoes","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F276744696?v=4","01M71KWF37AJ2NJBP3KWBVSDGT","01M71KWF4CSF8ADH0M6HA09VD2",23,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhooks-automation\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"Hooks Automation","automation","hooks","settings","json","post","routing","task","workers","use","sessions","logging","git hooks","git","pattern","edit","command","settings.json","up","SET","2026-11-10 10:56:23",false,"---\nname: hooks-automation\ndescription: \"Set up and use monomind hooks: pre\u002Fpost edit, command and task hooks, sessions, routing, pattern logging, background workers, settings.json and Git hooks.\"\n---\n\n# Hooks Automation\n\nCoordinate, validate, and learn from Claude Code operations through the `monomind hooks` command group and the hook handlers that `monomind init` installs into `.claude\u002Fsettings.json`.\n\n## What This Skill Does\n\nThe hooks system records what happens during a session (edits, commands, tasks) and uses that history to suggest agents, assess command risk, and persist session state. It enables:\n\n- **Pre-operation hooks**: context and agent suggestions before an edit, risk assessment before a command, agent suggestions before a task\n- **Post-operation hooks**: record edit, command, and task outcomes in local logs that routing statistics read\n- **Session management**: persist state at session end and restore it later\n- **Routing**: route a task to the best agent (or model) and explain the decision\n- **Pattern store**: log trajectories and search stored patterns (`hooks intelligence`); `hooks pretrain` scans the repository (file types, import lines) into the memory store and local pattern log — no model is trained\n- **Background workers**: run `@monoes\u002Fhooks` workers in-process\n\n## Prerequisites\n\n**Required:**\n- Monomind CLI (`npm install -g monomind@latest`, or use `npx monomind`)\n- Claude Code with hooks enabled in `.claude\u002Fsettings.json`\n\n**Optional:**\n- Git repository (for the Git hook examples)\n- A test framework (for quality gates)\n\n## Quick Start\n\n### Initialize Hooks\n\n```bash\n# Write the hooks configuration into .claude\u002Fsettings.json\nnpx monomind init hooks\n\n# Only the essential hooks\nnpx monomind init hooks --minimal\n```\n\nThis wires Claude Code's `PreToolUse`, `PostToolUse`, and session events to the helper `.claude\u002Fhelpers\u002Fhook-handler.cjs` (installed by `monomind init`), which handles pre-bash, pre-search (Grep\u002FGlob), pre-agent, post-edit, session-restore, session-end, and related events.\n\n### Basic Hook Usage\n\n```bash\n# Record task start and get agent suggestions\nnpx monomind hooks pre-task --description \"Implement authentication\"\n\n# Record an edit outcome\nnpx monomind hooks post-edit --file \"src\u002Fauth.js\" --success true\n\n# End the session and persist state\nnpx monomind hooks session-end\n```\n\n---\n\n## Complete Guide\n\n### Available Hooks\n\nRun `npx monomind hooks --help` for the full list and `npx monomind hooks \u003Csub> --help` for each subcommand's flags.\n\n#### Pre-Operation Hooks\n\n**pre-edit** - Get context and agent suggestions before editing a file\n```bash\nnpx monomind hooks pre-edit [options]\n\nOptions:\n  -f, --file \u003Cpath>         File path to edit\n  -o, --operation \u003Ctype>    create | update | delete | refactor (default: update)\n  -c, --context \u003Ctext>      Additional context about the edit\n\nExamples:\n  npx monomind hooks pre-edit --file \"src\u002Fauth\u002Flogin.js\"\n  npx monomind hooks pre-edit -f \"src\u002Fdb.ts\" -o refactor -c \"split connection pool\"\n```\n\n**pre-command** (alias: `pre-bash`) - Assess risk before executing a command\n```bash\nnpx monomind hooks pre-command --command \u003Ccmd>\n\nOptions:\n  -c, --command \u003Ccmd>       Command to execute (required)\n  -d, --dry-run             Only analyze, do not execute (default: true)\n\nExamples:\n  npx monomind hooks pre-command -c \"rm -rf .\u002Fbuild\"\n  npx monomind hooks pre-bash --command \"docker build .\"\n```\n\n**pre-task** - Record task start and get agent suggestions\n```bash\nnpx monomind hooks pre-task [options]\n\nOptions:\n  -d, --description \u003Ctext>  Task description (required)\n  -i, --task-id \u003Cid>        Task identifier (auto-generated if omitted)\n  -a, --auto-spawn          Auto-spawn suggested agents (default: false)\n\nExamples:\n  npx monomind hooks pre-task --description \"Implement user authentication\"\n  npx monomind hooks pre-task -d \"Refactor codebase\" -i refactor-1\n```\n\nThere is no `pre-search` CLI subcommand. Search-time context (for Grep\u002FGlob) is handled by the installed helper (`hook-handler.cjs pre-search`) that `monomind init hooks` wires up.\n\n#### Post-Operation Hooks\n\n**post-edit** - Record an editing outcome in the local feedback log\n```bash\nnpx monomind hooks post-edit [options]\n\nOptions:\n  -f, --file \u003Cpath>         File path that was edited\n  -s, --success             Whether the edit was successful\n  -o, --outcome \u003Ctext>      Outcome description\n  -m, --metrics \u003Clist>      Performance metrics (e.g. \"time:500ms,quality:0.95\")\n\nExamples:\n  npx monomind hooks post-edit --file \"src\u002Fcomponents\u002FButton.jsx\" --success true\n  npx monomind hooks post-edit -f \"api\u002Fauth.js\" -s true -o \"added token refresh\"\n```\n\nThe hook records the outcome; it does not format code. Run your formatter (Prettier, Black, gofmt) as its own hook command if you want auto-formatting.\n\n**post-command** (alias: `post-bash`) - Record command execution outcome\n```bash\nnpx monomind hooks post-command --command \u003Ccmd>\n\nOptions:\n  -c, --command \u003Ccmd>       Command that was executed (required)\n  -s, --success             Whether the command succeeded\n  -e, --exit-code \u003Cn>       Command exit code (default: 0)\n  -d, --duration \u003Cms>       Execution duration in milliseconds\n\nExamples:\n  npx monomind hooks post-command -c \"npm test\" --success true --duration 4200\n```\n\n**post-task** - Record a task outcome against its routed agent\n```bash\nnpx monomind hooks post-task [options]\n\nOptions:\n  -i, --task-id \u003Cid>        Task identifier (required)\n  -s, --success             Whether the task succeeded\n  -d, --duration \u003Cms>       Task duration in milliseconds\n  -o, --outcome \u003Ctext>      Outcome description\n  -r, --route-id \u003Cid>       Route ID from a prior `hooks route` call (joins recommendation to outcome)\n\nExamples:\n  npx monomind hooks post-task --task-id \"auth-implementation\" --success true\n  npx monomind hooks post-task -i \"bug-fix-123\" -s false -o \"flaky test, needs follow-up\"\n```\n\n#### Session Hooks\n\n**session-restore** - Restore a previous session\n```bash\nnpx monomind hooks session-restore [options]\n\nOptions:\n  -i, --session-id \u003Cid>     Session to restore (\"latest\" for most recent; default: latest)\n  -a, --restore-agents      Restore spawned agents (default: true)\n  -t, --restore-tasks       Restore active tasks (default: true)\n\nExamples:\n  npx monomind hooks session-restore\n  npx monomind hooks session-restore --session-id \"feature-auth\"\n```\n\n`session-start` still exists but is deprecated in favor of `session-restore`.\n\n**session-end** - End current session and persist state\n```bash\nnpx monomind hooks session-end [options]\n\nOptions:\n  -s, --save-state          Save session state for later restoration (default: true)\n```\n\nFor named checkpoints, use the `session` command group: `npx monomind session save --name \"feature-auth\"`, `npx monomind session list`, `npx monomind session restore \u003Cid>`.\n\n**notify** - Send a notification message (logged to the session)\n```bash\nnpx monomind hooks notify --message \u003Cmsg>\n\nOptions:\n  -m, --message \u003Ctext>      Notification message (required)\n  -l, --level \u003Clevel>       info | warn | error (default: info)\n  -c, --channel \u003Cname>      Only \"console\" is implemented (default: console)\n\nExamples:\n  npx monomind hooks notify -m \"Task completed\" --level info\n```\n\n#### Routing and Learning\n\n```bash\n# Route a task to the best agent (top 3 suggestions by default)\nnpx monomind hooks route --task \"Fix authentication bug\" --top-k 3\n\n# Explain a routing decision\nnpx monomind hooks explain --task \"Fix authentication bug\" --verbose\n\n# Route to a Claude model (haiku\u002Fsonnet\u002Fopus) by complexity\nnpx monomind hooks model-route --task \"Rename a variable\" --prefer-cost\nnpx monomind hooks model-stats\n\n# Route based on test coverage gaps\nnpx monomind hooks coverage-gaps --critical-only\n\n# Scan the repository (file types, import lines) into the memory store and local pattern log (no model is trained)\nnpx monomind hooks pretrain --depth shallow\n\n# Pattern store: ingest history, list\u002Fsearch patterns\nnpx monomind hooks intelligence train\nnpx monomind hooks intelligence patterns --query \"auth\" --limit 5\nnpx monomind hooks intelligence status\n\n# Copy recorded patterns from another local project\nnpx monomind hooks transfer from-project --source ..\u002Fother-project\n\n# Metrics dashboard\nnpx monomind hooks metrics --period 7d\nnpx monomind hooks metrics --v1-dashboard\n```\n\n#### Background Workers and Utilities\n\n```bash\nnpx monomind hooks list                 # registered hooks\nnpx monomind hooks worker list          # available background workers\nnpx monomind hooks worker run --name \u003Cworker>\nnpx monomind hooks statusline --compact\n```\n\n### Configuration\n\n#### Generated Configuration\n\n`npx monomind init hooks` writes the recommended configuration. Each entry runs the installed helper, which reads Claude Code's hook input JSON from stdin:\n\n```json\n{\n  \"hooks\": {\n    \"PreToolUse\": [\n      {\n        \"matcher\": \"Bash\",\n        \"hooks\": [{\n          \"type\": \"command\",\n          \"command\": \"node \\\"$CLAUDE_PROJECT_DIR\u002F.claude\u002Fhelpers\u002Fhook-handler.cjs\\\" pre-bash\",\n          \"timeout\": 5\n        }]\n      }\n    ],\n    \"PostToolUse\": [\n      {\n        \"matcher\": \"Write|Edit|MultiEdit\",\n        \"hooks\": [{\n          \"type\": \"command\",\n          \"command\": \"node \\\"$CLAUDE_PROJECT_DIR\u002F.claude\u002Fhelpers\u002Fhook-handler.cjs\\\" post-edit\",\n          \"timeout\": 10\n        }]\n      }\n    ]\n  }\n}\n```\n\n(The generated commands also walk up the directory tree to find `.claude\u002Fhelpers`; the version above is simplified.)\n\n#### Calling the CLI Directly\n\nClaude Code passes hook input as JSON on stdin (for example `tool_input.file_path`, `tool_input.command`). To call `monomind hooks` subcommands directly, extract the fields with `jq`:\n\n```json\n{\n  \"hooks\": {\n    \"PreToolUse\": [\n      {\n        \"matcher\": \"Write|Edit|MultiEdit\",\n        \"hooks\": [{\n          \"type\": \"command\",\n          \"command\": \"sh -c 'f=$(jq -r .tool_input.file_path); npx monomind hooks pre-edit --file \\\"$f\\\"'\",\n          \"timeout\": 10\n        }]\n      },\n      {\n        \"matcher\": \"Bash\",\n        \"hooks\": [{\n          \"type\": \"command\",\n          \"command\": \"sh -c 'c=$(jq -r .tool_input.command); npx monomind hooks pre-command --command \\\"$c\\\"'\",\n          \"timeout\": 10\n        }]\n      }\n    ],\n    \"PostToolUse\": [\n      {\n        \"matcher\": \"Write|Edit|MultiEdit\",\n        \"hooks\": [{\n          \"type\": \"command\",\n          \"command\": \"sh -c 'f=$(jq -r .tool_input.file_path); npx monomind hooks post-edit --file \\\"$f\\\" --success true'\",\n          \"timeout\": 10\n        }]\n      }\n    ],\n    \"SessionEnd\": [\n      {\n        \"hooks\": [{\n          \"type\": \"command\",\n          \"command\": \"npx monomind hooks session-end\"\n        }]\n      }\n    ]\n  }\n}\n```\n\n`npx` startup adds latency to every tool call; the helper-based configuration is faster.\n\n#### Enforcement Gates\n\nTo block destructive commands and secret leaks, wire the guidance gates into the same hooks:\n\n```bash\nnpx monomind guidance setup\n```\n\n#### Automatic Testing\n\nRun tests after file modifications (plain shell, no monomind command needed):\n\n```json\n{\n  \"hooks\": {\n    \"PostToolUse\": [\n      {\n        \"matcher\": \"Write\",\n        \"hooks\": [{\n          \"type\": \"command\",\n          \"command\": \"sh -c 'f=$(jq -r .tool_input.file_path); t=\\\"${f%.js}.test.js\\\"; [ -f \\\"$t\\\" ] && npm test -- \\\"$t\\\" || true'\"\n        }]\n      }\n    ]\n  }\n}\n```\n\n### MCP Tool Equivalents\n\nThe core hooks are also exposed as MCP tools, so agents can call them without a shell: `mcp__monomind__hooks_pre-task`, `mcp__monomind__hooks_post-task`, `mcp__monomind__hooks_pre-edit`, `mcp__monomind__hooks_post-edit`, `mcp__monomind__hooks_pre-command`, `mcp__monomind__hooks_post-command`, `mcp__monomind__hooks_route`, `mcp__monomind__hooks_explain`.\n\nTo share context between agents, store it explicitly in memory:\n\n```bash\nnpx monomind memory store --key \"swarm\u002Fbackend\u002Fauth-api\" --value \"JWT, refresh via \u002Fauth\u002Frefresh\" --namespace coordination\nnpx monomind memory search --query \"auth api\" --namespace coordination\n```\n\n### Git Integration\n\n#### Pre-Commit Hook\n```bash\n#!\u002Fbin\u002Fbash\n# .git\u002Fhooks\u002Fpre-commit (or via husky)\n\n# Risk assessment of the working-tree change against HEAD (informational)\nnpx monomind analyze diff --risk --classify\n\n# Run tests\nnpm test || exit 1\n```\n\n#### Post-Commit Hook\n```bash\n#!\u002Fbin\u002Fbash\n# .git\u002Fhooks\u002Fpost-commit\nCOMMIT_MSG=$(git log -1 --pretty=%s)\nnpx monomind hooks notify --message \"Commit completed: $COMMIT_MSG\" --level info\n```\n\n#### Pre-Push Hook\n```bash\n#!\u002Fbin\u002Fbash\n# .git\u002Fhooks\u002Fpre-push\nnpm test || exit 1\nnpx monomind hooks session-end\n```\n\n### Agent Coordination Workflow\n\n```bash\n# Agent 1: Backend Developer\nnpx monomind hooks pre-task --description \"Implement user authentication API\" --task-id auth-api\nnpx monomind hooks pre-edit --file \"api\u002Fauth.js\"\n# ... edit via Claude Code Edit tool ...\nnpx monomind hooks post-edit --file \"api\u002Fauth.js\" --success true\nnpx monomind memory store --key \"swarm\u002Fbackend\u002Fauth-api\" --value \"endpoints: \u002Flogin, \u002Frefresh\" --namespace coordination\nnpx monomind hooks post-task --task-id auth-api --success true\n\n# Agent 2: Test Engineer\nnpx monomind memory retrieve --key \"swarm\u002Fbackend\u002Fauth-api\" --namespace coordination\nnpx monomind hooks pre-task --description \"Write tests for auth API\" --task-id auth-tests\nnpx monomind hooks post-edit --file \"api\u002Fauth.test.js\" --success true\nnpx monomind hooks post-task --task-id auth-tests --success true\n```\n\n### Real-World Examples\n\n#### Example 1: Full-Stack Feature\n\n```bash\nnpx monomind hooks session-restore\nnpx monomind hooks route --task \"Build user profile feature - frontend + backend + tests\"\nnpx monomind hooks pre-task --description \"Build user profile feature\" --task-id profile\n\nnpx monomind hooks pre-edit --file \"api\u002Fprofile.js\"\n# ... implement backend ...\nnpx monomind hooks post-edit --file \"api\u002Fprofile.js\" --success true\n\nnpx monomind hooks pre-edit --file \"components\u002FProfile.jsx\"\n# ... implement frontend ...\nnpx monomind hooks post-edit --file \"components\u002FProfile.jsx\" --success true\n\nnpx monomind hooks post-task --task-id profile --success true\nnpx monomind hooks session-end\n```\n\n#### Example 2: Debugging\n\n```bash\nnpx monomind hooks pre-task --description \"Debug memory leak in event handlers\" --task-id leak\nnpx monomind hooks pre-edit --file \"services\u002Fevents.js\" --operation update -c \"remove listener leak\"\n# ... fix code ...\nnpx monomind hooks post-edit --file \"services\u002Fevents.js\" --success true -o \"listeners removed on dispose\"\nnpx monomind hooks post-command --command \"npm test\" --success true\nnpx monomind hooks post-task --task-id leak --success true\n```\n\n### Debugging Hooks\n\n```bash\n# Verbose output\nnpx monomind hooks pre-edit --file \"test.js\" --verbose\n\n# Registered hooks and learning state\nnpx monomind hooks list\nnpx monomind hooks metrics\n\n# Overall health, including hook configuration\nnpx monomind doctor\n```\n\n`MONOMIND_HOOK_QUIET=1` (set in `.claude\u002Fsettings.json` `env`) silences hook output in Claude Code.\n\n### Best Practices\n\n1. **Initialize early** - run `monomind init hooks` when setting up a project\n2. **Keep hooks lightweight** - prefer the helper over `npx` in hot paths; set `timeout`\n3. **Record outcomes** - `post-edit`, `post-command`, and `post-task` feed routing\n4. **Join routes to outcomes** - pass `--route-id` from `hooks route` to `hooks post-task`\n5. **Use clear memory namespaces** - e.g. `coordination`, `swarm\u002F\u003Crole>\u002F\u003Ctopic>`\n6. **Review metrics** - `hooks metrics` and `hooks model-stats`\n\n### Troubleshooting\n\n#### Hooks Not Executing\n- Verify `.claude\u002Fsettings.json` syntax and matcher patterns\n- Check that `.claude\u002Fhelpers\u002Fhook-handler.cjs` exists (`monomind init hooks` \u002F `monomind init upgrade`)\n- Ensure `monomind` is resolvable via `npx`\n- Run `npx monomind doctor`\n\n#### Hook Timeouts\n- Increase `timeout` for the hook entry\n- Use the helper instead of `npx` for frequent events\n\n### Related Commands\n\n- `npx monomind init hooks` - Initialize hooks configuration\n- `npx monomind hooks list` - List registered hooks\n- `npx monomind hooks \u003Csub> --help` - Flags for a specific hook\n- `npx monomind memory store|search|retrieve` - Shared memory\n- `npx monomind session save|list|restore` - Session checkpoints\n- `npx monomind agent spawn -t \u003Ctype>` - Spawn agents\n\n### Integration with Other Skills\n\n- **Pair Programming** - record outcomes during pairing sessions\n- **Verification Quality** - quality gates alongside hooks\n- **GitHub Toolkit** - Git and PR workflows\n- **Performance Analysis** - metrics collection\n","# Hooks Automation\n\nCoordinate, validate, and learn from Claude Code operations through the `monomind hooks` command group and the hook handlers that `monomind init` installs into `.claude\u002Fsettings.json`.\n\n## What This Skill Does\n\nThe hooks system records what happens during a session (edits, commands, tasks) and uses that history to suggest agents, assess command risk, and persist session state. It enables:\n\n- **Pre-operation hooks**: context and agent suggestions before an edit, risk assessment before a command, agent suggestions before a task\n- **Post-operation hooks**: record edit, command, and task outcomes in local logs that routing statistics read\n- **Session management**: persist state at session end and restore it later\n- **Routing**: route a task to the best agent (or model) and explain the decision\n- **Pattern store**: log trajectories and search stored patterns (`hooks intelligence`); `hooks pretrain` scans the repository (file types, import lines) into the memory store and local pattern log — no model is trained\n- **Background workers**: run `@monoes\u002Fhooks` workers in-process\n\n## Prerequisites\n\n**Required:**\n- Monomind CLI (`npm install -g monomind@latest`, or use `npx monomind`)\n- Claude Code with hooks enabled in `.claude\u002Fsettings.json`\n\n**Optional:**\n- Git repository (for the Git hook examples)\n- A test framework (for quality gates)\n\n## Quick Start\n\n### Initialize Hooks\n\n```bash\n# Write the hooks configuration into .claude\u002Fsettings.json\nnpx monomind init hooks\n\n# Only the essential hooks\nnpx monomind init hooks --minimal\n```\n\nThis wires Claude Code's `PreToolUse`, `PostToolUse`, and session events to the helper `.claude\u002Fhelpers\u002Fhook-handler.cjs` (installed by `monomind init`), which handles pre-bash, pre-search (Grep\u002FGlob), pre-agent, post-edit, session-restore, session-end, and related events.\n\n### Basic Hook Usage\n\n```bash\n# Record task start and get agent suggestions\nnpx monomind hooks pre-task --description \"Implement authentication\"\n\n# Record an edit outcome\nnpx monomind hooks post-edit --file \"src\u002Fauth.js\" --success true\n\n# End the session and persist state\nnpx monomind hooks session-end\n```\n\n---\n\n## Complete Guide\n\n### Available Hooks\n\nRun `npx monomind hooks --help` for the full list and `npx monomind hooks \u003Csub> --help` for each subcommand's flags.\n\n#### Pre-Operation Hooks\n\n**pre-edit** - Get context and agent suggestions before editing a file\n```bash\nnpx monomind hooks pre-edit [options]\n\nOptions:\n  -f, --file \u003Cpath>         File path to edit\n  -o, --operation \u003Ctype>    create | update | delete | refactor (default: update)\n  -c, --context \u003Ctext>      Additional context about the edit\n\nExamples:\n  npx monomind hooks pre-edit --file \"src\u002Fauth\u002Flogin.js\"\n  npx monomind hooks pre-edit -f \"src\u002Fdb.ts\" -o refactor -c \"split connection pool\"\n```\n\n**pre-command** (alias: `pre-bash`) - Assess risk before executing a command\n```bash\nnpx monomind hooks pre-command --command \u003Ccmd>\n\nOptions:\n  -c, --command \u003Ccmd>       Command to execute (required)\n  -d, --dry-run             Only analyze, do not execute (default: true)\n\nExamples:\n  npx monomind hooks pre-command -c \"rm -rf .\u002Fbuild\"\n  npx monomind hooks pre-bash --command \"docker build .\"\n```\n\n**pre-task** - Record task start and get agent suggestions\n```bash\nnpx monomind hooks pre-task [options]\n\nOptions:\n  -d, --description \u003Ctext>  Task description (required)\n  -i, --task-id \u003Cid>        Task identifier (auto-generated if omitted)\n  -a, --auto-spawn          Auto-spawn suggested agents (default: false)\n\nExamples:\n  npx monomind hooks pre-task --description \"Implement user authentication\"\n  npx monomind hooks pre-task -d \"Refactor codebase\" -i refactor-1\n```\n\nThere is no `pre-search` CLI subcommand. Search-time context (for Grep\u002FGlob) is handled by the installed helper (`hook-handler.cjs pre-search`) that `monomind init hooks` wires up.\n\n#### Post-Operation Hooks\n\n**post-edit** - Record an editing outcome in the local feedback log\n```bash\nnpx monomind hooks post-edit [options]\n\nOptions:\n  -f, --file \u003Cpath>         File path that was edited\n  -s, --success             Whether the edit was successful\n  -o, --outcome \u003Ctext>      Outcome description\n  -m, --metrics \u003Clist>      Performance metrics (e.g. \"time:500ms,quality:0.95\")\n\nExamples:\n  npx monomind hooks post-edit --file \"src\u002Fcomponents\u002FButton.jsx\" --success true\n  npx monomind hooks post-edit -f \"api\u002Fauth.js\" -s true -o \"added token refresh\"\n```\n\nThe hook records the outcome; it does not format code. Run your formatter (Prettier, Black, gofmt) as its own hook command if you want auto-formatting.\n\n**post-command** (alias: `post-bash`) - Record command execution outcome\n```bash\nnpx monomind hooks post-command --command \u003Ccmd>\n\nOptions:\n  -c, --command \u003Ccmd>       Command that was executed (required)\n  -s, --success             Whether the command succeeded\n  -e, --exit-code \u003Cn>       Command exit code (default: 0)\n  -d, --duration \u003Cms>       Execution duration in milliseconds\n\nExamples:\n  npx monomind hooks post-command -c \"npm test\" --success true --duration 4200\n```\n\n**post-task** - Record a task outcome against its routed agent\n```bash\nnpx monomind hooks post-task [options]\n\nOptions:\n  -i, --task-id \u003Cid>        Task identifier (required)\n  -s, --success             Whether the task succeeded\n  -d, --duration \u003Cms>       Task duration in milliseconds\n  -o, --outcome \u003Ctext>      Outcome description\n  -r, --route-id \u003Cid>       Route ID from a prior `hooks route` call (joins recommendation to outcome)\n\nExamples:\n  npx monomind hooks post-task --task-id \"auth-implementation\" --success true\n  npx monomind hooks post-task -i \"bug-fix-123\" -s false -o \"flaky test, needs follow-up\"\n```\n\n#### Session Hooks\n\n**session-restore** - Restore a previous session\n```bash\nnpx monomind hooks session-restore [options]\n\nOptions:\n  -i, --session-id \u003Cid>     Session to restore (\"latest\" for most recent; default: latest)\n  -a, --restore-agents      Restore spawned agents (default: true)\n  -t, --restore-tasks       Restore active tasks (default: true)\n\nExamples:\n  npx monomind hooks session-restore\n  npx monomind hooks session-restore --session-id \"feature-auth\"\n```\n\n`session-start` still exists but is deprecated in favor of `session-restore`.\n\n**session-end** - End current session and persist state\n```bash\nnpx monomind hooks session-end [options]\n\nOptions:\n  -s, --save-state          Save session state for later restoration (default: true)\n```\n\nFor named checkpoints, use the `session` command group: `npx monomind session save --name \"feature-auth\"`, `npx monomind session list`, `npx monomind session restore \u003Cid>`.\n\n**notify** - Send a notification message (logged to the session)\n```bash\nnpx monomind hooks notify --message \u003Cmsg>\n\nOptions:\n  -m, --message \u003Ctext>      Notification message (required)\n  -l, --level \u003Clevel>       info | warn | error (default: info)\n  -c, --channel \u003Cname>      Only \"console\" is implemented (default: console)\n\nExamples:\n  npx monomind hooks notify -m \"Task completed\" --level info\n```\n\n#### Routing and Learning\n\n```bash\n# Route a task to the best agent (top 3 suggestions by default)\nnpx monomind hooks route --task \"Fix authentication bug\" --top-k 3\n\n# Explain a routing decision\nnpx monomind hooks explain --task \"Fix authentication bug\" --verbose\n\n# Route to a Claude model (haiku\u002Fsonnet\u002Fopus) by complexity\nnpx monomind hooks model-route --task \"Rename a variable\" --prefer-cost\nnpx monomind hooks model-stats\n\n# Route based on test coverage gaps\nnpx monomind hooks coverage-gaps --critical-only\n\n# Scan the repository (file types, import lines) into the memory store and local pattern log (no model is trained)\nnpx monomind hooks pretrain --depth shallow\n\n# Pattern store: ingest history, list\u002Fsearch patterns\nnpx monomind hooks intelligence train\nnpx monomind hooks intelligence patterns --query \"auth\" --limit 5\nnpx monomind hooks intelligence status\n\n# Copy recorded patterns from another local project\nnpx monomind hooks transfer from-project --source ..\u002Fother-project\n\n# Metrics dashboard\nnpx monomind hooks metrics --period 7d\nnpx monomind hooks metrics --v1-dashboard\n```\n\n#### Background Workers and Utilities\n\n```bash\nnpx monomind hooks list                 # registered hooks\nnpx monomind hooks worker list          # available background workers\nnpx monomind hooks worker run --name \u003Cworker>\nnpx monomind hooks statusline --compact\n```\n\n### Configuration\n\n#### Generated Configuration\n\n`npx monomind init hooks` writes the recommended configuration. Each entry runs the installed helper, which reads Claude Code's hook input JSON from stdin:\n\n```json\n{\n  \"hooks\": {\n    \"PreToolUse\": [\n      {\n        \"matcher\": \"Bash\",\n        \"hooks\": [{\n          \"type\": \"command\",\n          \"command\": \"node \\\"$CLAUDE_PROJECT_DIR\u002F.claude\u002Fhelpers\u002Fhook-handler.cjs\\\" pre-bash\",\n          \"timeout\": 5\n        }]\n      }\n    ],\n    \"PostToolUse\": [\n      {\n        \"matcher\": \"Write|Edit|MultiEdit\",\n        \"hooks\": [{\n          \"type\": \"command\",\n          \"command\": \"node \\\"$CLAUDE_PROJECT_DIR\u002F.claude\u002Fhelpers\u002Fhook-handler.cjs\\\" post-edit\",\n          \"timeout\": 10\n        }]\n      }\n    ]\n  }\n}\n```\n\n(The generated commands also walk up the directory tree to find `.claude\u002Fhelpers`; the version above is simplified.)\n\n#### Calling the CLI Directly\n\nClaude Code passes hook input as JSON on stdin (for example `tool_input.file_path`, `tool_input.command`). To call `monomind hooks` subcommands directly, extract the fields with `jq`:\n\n```json\n{\n  \"hooks\": {\n    \"PreToolUse\": [\n      {\n        \"matcher\": \"Write|Edit|MultiEdit\",\n        \"hooks\": [{\n          \"type\": \"command\",\n          \"command\": \"sh -c 'f=$(jq -r .tool_input.file_path); npx monomind hooks pre-edit --file \\\"$f\\\"'\",\n          \"timeout\": 10\n        }]\n      },\n      {\n        \"matcher\": \"Bash\",\n        \"hooks\": [{\n          \"type\": \"command\",\n          \"command\": \"sh -c 'c=$(jq -r .tool_input.command); npx monomind hooks pre-command --command \\\"$c\\\"'\",\n          \"timeout\": 10\n        }]\n      }\n    ],\n    \"PostToolUse\": [\n      {\n        \"matcher\": \"Write|Edit|MultiEdit\",\n        \"hooks\": [{\n          \"type\": \"command\",\n          \"command\": \"sh -c 'f=$(jq -r .tool_input.file_path); npx monomind hooks post-edit --file \\\"$f\\\" --success true'\",\n          \"timeout\": 10\n        }]\n      }\n    ],\n    \"SessionEnd\": [\n      {\n        \"hooks\": [{\n          \"type\": \"command\",\n          \"command\": \"npx monomind hooks session-end\"\n        }]\n      }\n    ]\n  }\n}\n```\n\n`npx` startup adds latency to every tool call; the helper-based configuration is faster.\n\n#### Enforcement Gates\n\nTo block destructive commands and secret leaks, wire the guidance gates into the same hooks:\n\n```bash\nnpx monomind guidance setup\n```\n\n#### Automatic Testing\n\nRun tests after file modifications (plain shell, no monomind command needed):\n\n```json\n{\n  \"hooks\": {\n    \"PostToolUse\": [\n      {\n        \"matcher\": \"Write\",\n        \"hooks\": [{\n          \"type\": \"command\",\n          \"command\": \"sh -c 'f=$(jq -r .tool_input.file_path); t=\\\"${f%.js}.test.js\\\"; [ -f \\\"$t\\\" ] && npm test -- \\\"$t\\\" || true'\"\n        }]\n      }\n    ]\n  }\n}\n```\n\n### MCP Tool Equivalents\n\nThe core hooks are also exposed as MCP tools, so agents can call them without a shell: `mcp__monomind__hooks_pre-task`, `mcp__monomind__hooks_post-task`, `mcp__monomind__hooks_pre-edit`, `mcp__monomind__hooks_post-edit`, `mcp__monomind__hooks_pre-command`, `mcp__monomind__hooks_post-command`, `mcp__monomind__hooks_route`, `mcp__monomind__hooks_explain`.\n\nTo share context between agents, store it explicitly in memory:\n\n```bash\nnpx monomind memory store --key \"swarm\u002Fbackend\u002Fauth-api\" --value \"JWT, refresh via \u002Fauth\u002Frefresh\" --namespace coordination\nnpx monomind memory search --query \"auth api\" --namespace coordination\n```\n\n### Git Integration\n\n#### Pre-Commit Hook\n```bash\n#!\u002Fbin\u002Fbash\n# .git\u002Fhooks\u002Fpre-commit (or via husky)\n\n# Risk assessment of the working-tree change against HEAD (informational)\nnpx monomind analyze diff --risk --classify\n\n# Run tests\nnpm test || exit 1\n```\n\n#### Post-Commit Hook\n```bash\n#!\u002Fbin\u002Fbash\n# .git\u002Fhooks\u002Fpost-commit\nCOMMIT_MSG=$(git log -1 --pretty=%s)\nnpx monomind hooks notify --message \"Commit completed: $COMMIT_MSG\" --level info\n```\n\n#### Pre-Push Hook\n```bash\n#!\u002Fbin\u002Fbash\n# .git\u002Fhooks\u002Fpre-push\nnpm test || exit 1\nnpx monomind hooks session-end\n```\n\n### Agent Coordination Workflow\n\n```bash\n# Agent 1: Backend Developer\nnpx monomind hooks pre-task --description \"Implement user authentication API\" --task-id auth-api\nnpx monomind hooks pre-edit --file \"api\u002Fauth.js\"\n# ... edit via Claude Code Edit tool ...\nnpx monomind hooks post-edit --file \"api\u002Fauth.js\" --success true\nnpx monomind memory store --key \"swarm\u002Fbackend\u002Fauth-api\" --value \"endpoints: \u002Flogin, \u002Frefresh\" --namespace coordination\nnpx monomind hooks post-task --task-id auth-api --success true\n\n# Agent 2: Test Engineer\nnpx monomind memory retrieve --key \"swarm\u002Fbackend\u002Fauth-api\" --namespace coordination\nnpx monomind hooks pre-task --description \"Write tests for auth API\" --task-id auth-tests\nnpx monomind hooks post-edit --file \"api\u002Fauth.test.js\" --success true\nnpx monomind hooks post-task --task-id auth-tests --success true\n```\n\n### Real-World Examples\n\n#### Example 1: Full-Stack Feature\n\n```bash\nnpx monomind hooks session-restore\nnpx monomind hooks route --task \"Build user profile feature - frontend + backend + tests\"\nnpx monomind hooks pre-task --description \"Build user profile feature\" --task-id profile\n\nnpx monomind hooks pre-edit --file \"api\u002Fprofile.js\"\n# ... implement backend ...\nnpx monomind hooks post-edit --file \"api\u002Fprofile.js\" --success true\n\nnpx monomind hooks pre-edit --file \"components\u002FProfile.jsx\"\n# ... implement frontend ...\nnpx monomind hooks post-edit --file \"components\u002FProfile.jsx\" --success true\n\nnpx monomind hooks post-task --task-id profile --success true\nnpx monomind hooks session-end\n```\n\n#### Example 2: Debugging\n\n```bash\nnpx monomind hooks pre-task --description \"Debug memory leak in event handlers\" --task-id leak\nnpx monomind hooks pre-edit --file \"services\u002Fevents.js\" --operation update -c \"remove listener leak\"\n# ... fix code ...\nnpx monomind hooks post-edit --file \"services\u002Fevents.js\" --success true -o \"listeners removed on dispose\"\nnpx monomind hooks post-command --command \"npm test\" --success true\nnpx monomind hooks post-task --task-id leak --success true\n```\n\n### Debugging Hooks\n\n```bash\n# Verbose output\nnpx monomind hooks pre-edit --file \"test.js\" --verbose\n\n# Registered hooks and learning state\nnpx monomind hooks list\nnpx monomind hooks metrics\n\n# Overall health, including hook configuration\nnpx monomind doctor\n```\n\n`MONOMIND_HOOK_QUIET=1` (set in `.claude\u002Fsettings.json` `env`) silences hook output in Claude Code.\n\n### Best Practices\n\n1. **Initialize early** - run `monomind init hooks` when setting up a project\n2. **Keep hooks lightweight** - prefer the helper over `npx` in hot paths; set `timeout`\n3. **Record outcomes** - `post-edit`, `post-command`, and `post-task` feed routing\n4. **Join routes to outcomes** - pass `--route-id` from `hooks route` to `hooks post-task`\n5. **Use clear memory namespaces** - e.g. `coordination`, `swarm\u002F\u003Crole>\u002F\u003Ctopic>`\n6. **Review metrics** - `hooks metrics` and `hooks model-stats`\n\n### Troubleshooting\n\n#### Hooks Not Executing\n- Verify `.claude\u002Fsettings.json` syntax and matcher patterns\n- Check that `.claude\u002Fhelpers\u002Fhook-handler.cjs` exists (`monomind init hooks` \u002F `monomind init upgrade`)\n- Ensure `monomind` is resolvable via `npx`\n- Run `npx monomind doctor`\n\n#### Hook Timeouts\n- Increase `timeout` for the hook entry\n- Use the helper instead of `npx` for frequent events\n\n### Related Commands\n\n- `npx monomind init hooks` - Initialize hooks configuration\n- `npx monomind hooks list` - List registered hooks\n- `npx monomind hooks \u003Csub> --help` - Flags for a specific hook\n- `npx monomind memory store|search|retrieve` - Shared memory\n- `npx monomind session save|list|restore` - Session checkpoints\n- `npx monomind agent spawn -t \u003Ctype>` - Spawn agents\n\n### Integration with Other Skills\n\n- **Pair Programming** - record outcomes during pairing sessions\n- **Verification Quality** - quality gates alongside hooks\n- **GitHub Toolkit** - Git and PR workflows\n- **Performance Analysis** - metrics collection\n",{"name":5,"description":7},"main","f7cd4595d0f8959822163e14f9787117765c931a",".claude\u002Fskills\u002Fhooks-automation",2,"https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind","https:\u002F\u002Fmonoes.github.io\u002Fmonomind\u002F","https:\u002F\u002Fgithub.com\u002Fmonoes","https:\u002F\u002Fmonoes.me","2026-11-10 01:53:48",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add monoes\u002Fmonomind --skill hooks-automation",{"tool":63,"command":64},"bunx","bunx skills add monoes\u002Fmonomind --skill hooks-automation",{"tool":66,"command":67},"pnpm","pnpm dlx skills add monoes\u002Fmonomind --skill hooks-automation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhooks-automation\u002FSKILL.md",true,[],[72,100,135,161,186,210],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":99},"01M71PB3SHWKMNJM6MD65VX8D6","zk-steward","Org role guidance for a ZK steward: engineer zero-knowledge proof systems with circuit design, SNARK vs STARK choice and security review. This is zero-knowledge cryptography, not Zettelkasten note-taking.","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fzk-steward\u002FSKILL.md",[],[79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98],"zk","zk steward","steward","zero-knowledge","engineer","choice","design","knowledge","impact","query","snark","review","monomind","security review","stark","zettelkasten","cryptography","security","org","blockchain","2026-11-10 13:02:02",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":104,"licenseFileUrl":105,"sourceHtmlUrl":106,"categories":107,"keywords":116,"publishedAt":99},"01M71PB18SDG28WBKPKJNB814K","writing-plans","Use when you have a spec or requirements for a multi-step coding task and must write an implementation plan before touching code. Produces bite-sized TDD tasks with exact file paths, code and commands for an engineer with zero context.","MIT","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fwriting-plans\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fwriting-plans\u002FSKILL.md",[108,111],{"categoryNo":109,"categoryName":110,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":112,"categoryName":113,"taxonomyType":114,"taxonomyTypeDesc":115},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[117,118,119,83,120,121,122,123,88,124,125,126,127,128,129,130,131,132,133,134],"writing","writing plans","plans","superpowers","implementation plan","when","you","code","tasks","plan","product","write","commands","paths","suggest","coding","context","ZeRO",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":139,"sourceHtmlUrl":140,"categories":141,"keywords":145,"publishedAt":99},"01M71PAXFM488X9ARXK0T04TF5","write-spec","Write a feature spec or PRD from a problem statement or feature idea. Use when turning a vague idea or user request into a structured document, scoping a feature with goals and non-goals, defining success metrics and acceptance criteria, or breaking a big ask into a phased spec.","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fwrite-spec\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fwrite-spec\u002FSKILL.md",[142],{"categoryNo":143,"categoryName":144,"taxonomyType":114,"taxonomyTypeDesc":115},"01JBSEEDCAT000000000000031","产品经理",[128,146,147,148,149,86,150,122,151,152,153,127,154,155,156,157,158,159,32,160],"write spec","spec","user request","problem","acceptance","ask","vague","work","request","scoping","idea","metrics","feature","problem statement","document",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":165,"sourceHtmlUrl":166,"categories":167,"keywords":171,"publishedAt":99},"01M71PASSZY800C0RPEARBS918","write-query","Write optimized SQL for your dialect with best practices. Use when translating a natural-language data need into SQL, building a multi-CTE query with joins and aggregations, optimizing a query against a large partitioned table, or getting dialect-specific syntax for Snowflake, BigQuery, Postgres, etc.","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fwrite-query\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fwrite-query\u002FSKILL.md",[168],{"categoryNo":169,"categoryName":170,"taxonomyType":114,"taxonomyTypeDesc":115},"01JBSEEDCAT000000000000033","数据分析师",[88,128,172,173,174,175,86,32,122,176,177,178,179,153,180,181,182,183,184,185],"write query","postgres","for","snowflake","best practices","natural-language","with","multi","github","sql","https","syntax","plugins","data",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":196,"publishedAt":99},"01M71PAPTX0T3PF6ETFVR96SJJ","workflow-automation","Org role guidance for workflow automation: build and maintain CI\u002FCD definitions in GitHub Actions or equivalent: triggers, jobs, matrices, caching. Covers path filters, dependency caching, parallel jobs, timeouts and fail-fast ordering.","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fworkflow-automation\u002FSKILL.md",[192,195],{"categoryNo":193,"categoryName":194,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[197,24,198,199,174,200,201,202,203,87,204,205,206,88,91,180,207,208,209,182],"Workflow Automation","workflow","parallel","actions","ci","triggers","github actions","maintain","filters","caching","build","dependency","devops",{"skillNo":211,"name":212,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":214,"categories":215,"keywords":217,"publishedAt":99},"01M71PAM19Z1XTV9NPCFSE2MY8","workflow-architect","Org role guidance for a workflow architect: map full workflow trees for systems, user journeys and agents, covering every branch and failure. Covers discovering workflows from code, handoff contracts, timeouts, recovery paths and observable state.","https:\u002F\u002Fgithub.com\u002Fmonoes\u002Fmonomind\u002Fblob\u002Fmain\u002Fpackages\u002F@monomind\u002Fcli\u002Forg-skills\u002Fworkflow-architect\u002FSKILL.md",[216],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[198,218,219,220,221,222,223,174,224,225,124,226,227,228,91,180,229,230,182,231],"workflow architect","architect","trees","user journeys","branch","planning","map","workflows","architecture","state","leadership","recovery","operations","systems"]