[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CRPBXFVES8GP94KHBWVCQF":3,"skill-same:01M6CRPBXFVES8GP94KHBWVCQF":66},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":48,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M6CRPBXFVES8GP94KHBWVCQF","agentflow",null,"Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.","Sam-06060\u002Fjarvis-assistant","Sam-06060","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F208600848?v=4","01M6CRKT7C7FXD21V6HXF293S0","Samson Frank Ganta","01M6CRKTBEKYFD8YX5Z1GT99EE",6,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FSam-06060\u002Fjarvis-assistant\u002Fblob\u002Fmain\u002Fmodules\u002Fagent_skills\u002Fawesome-skills\u002Fplaybooks\u002Fagentflow\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37],"projects","deterministic","task","community","kanban board","kanban","cost","dispatch","autonomous","review","execution","pipeline","orchestrate","linear","code","development","quality gates","github","safe","2026-11-10 10:12:30",false,"---\nname: agentflow\ndescription: \"Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.\"\nrisk: safe\nsource: community\ndate_added: \"2026-04-02\"\n---\n\n# AgentFlow\n\n## Overview\n\nAgentFlow turns your existing Kanban board into a fully autonomous AI development pipeline. Instead of building custom orchestration infrastructure, it treats your project management tool (Asana, GitHub Projects, Linear) as a distributed state machine — tasks move through stages, AI agents read and write state via comments, and humans intervene through the same UI they already use.\n\nThe result is complete pipeline observability from your phone, free crash recovery (state lives in your PM tool, not in memory), and human override at any point by dragging a card.\n\n## When to Use This Skill\n\n- Use when you need to orchestrate multiple Claude Code workers across a full development lifecycle (build, review, test, integrate)\n- Use when you want deterministic quality gates (tsc\u002Feslint\u002Ftests) before AI review on AI-generated code\n- Use when you want full pipeline visibility from your Kanban board or phone\n- Use when running a solo or team project that needs autonomous task dispatch with cost tracking\n- Use when you need crash-proof orchestration that survives session restarts\n\n## Core Concepts\n\n### 7-Stage Kanban Pipeline\n\nTasks flow through: Backlog, Research, Build, Review, Test, Integrate, Done. Each stage has specific gates. The Kanban board IS the orchestration layer — no separate database, no message queue, no custom infrastructure.\n\n### Stateless Orchestrator\n\nA crontab-driven one-shot sweep runs every 15 minutes. No daemon, no session dependency. If it crashes, the next sweep picks up where it left off because all state lives in your PM tool.\n\n### Deterministic Before Probabilistic\n\nHard gates (tsc + eslint + tests) run before any AI review, catching roughly 60% of issues at near-zero cost. AI review comes after, as a second layer.\n\n### Adversarial Review\n\nA different AI agent reviews code and must list 3 things wrong before deciding to pass. This prevents rubber-stamp approvals.\n\n### Transitive Priority Dispatch\n\nTasks that unblock the most downstream work get built first, automatically computing the critical path.\n\n## Skills \u002F Commands\n\n### `\u002Fspec-to-board`\nDecomposes a SPEC.md into atomic tasks on your Kanban board with dependencies mapped.\n\n### `\u002Fsdlc-orchestrate`\nDispatches tasks to workers based on transitive priority and conflict detection. Runs as a crontab sweep.\n\n### `\u002Fsdlc-worker --slot \u003CN>`\nRuns a worker in a terminal slot that picks up tasks, builds code, and creates PRs. Run 3-4 workers in parallel.\n\n### `\u002Fsdlc-health`\nReal-time pipeline status dashboard showing current stage, assigned agent, retry count, and accumulated cost for every task.\n\n### `\u002Fsdlc-stop`\nGraceful shutdown: active workers finish their current task, unstarted tasks return to Backlog.\n\n## Step-by-Step Guide\n\n### 1. Write Your Spec\n\nCreate a `SPEC.md` for your project describing what you want to build.\n\n### 2. Decompose Into Tasks\n\n```\nclaude -p \"\u002Fspec-to-board\"\n```\n\nThis reads your SPEC.md, decomposes it into atomic tasks, maps dependencies, and creates them on your Kanban board.\n\n### 3. Start Workers\n\nOpen 3-4 terminal windows, each as a worker slot:\n\n```bash\n# Terminal 2 — Builder\nclaude -p \"\u002Fsdlc-worker --slot T2\"\n\n# Terminal 3 — Builder\nclaude -p \"\u002Fsdlc-worker --slot T3\"\n\n# Terminal 4 — Reviewer\nclaude -p \"\u002Fsdlc-worker --slot T4\"\n\n# Terminal 5 — Tester\nclaude -p \"\u002Fsdlc-worker --slot T5\"\n```\n\n### 4. Start the Orchestrator\n\n```bash\n# Add to crontab (runs every 15 minutes)\ncrontab -e\n# Add: *\u002F15 * * * * ~\u002F.claude\u002Fsdlc\u002Fagentflow-cron.sh >> \u002Ftmp\u002Fagentflow-orchestrate.log 2>&1\n```\n\n### 5. Monitor and Intervene\n\nOpen your Kanban board on your phone. Watch tasks flow through the pipeline. Drag any card to \"Needs Human\" to intervene. Run `\u002Fsdlc-health` for a terminal dashboard.\n\n### 6. Stop the Pipeline\n\n```\nclaude -p \"\u002Fsdlc-stop\"\n```\n\n## Quality Gates\n\nEach stage enforces specific gates before promotion:\n\n- **Build to Review**: `tsc` + `eslint` + `npm test` must all pass (deterministic)\n- **Review to Test**: Adversarial reviewer must list 3 issues before passing\n- **Test to Integrate**: 80% coverage threshold on new files\n- **Integrate to Done**: Full test suite on main after merge; auto-reverts on failure\n\n## Cost Tracking\n\nPer-task cost tracking with stage ceilings (Sonnet defaults):\n\n- Research: ~$0.10\n- Build: ~$0.40\n- Review: ~$0.10\n- Test: ~$0.05\n- Integrate: ~$0.03\n\nAutomatic guardrails: warning at $3\u002F$8, hard stop at $10\u002F$20 (Sonnet\u002FOpus) with human escalation.\n\n## Safety and Recovery\n\n- **Auto-revert**: Integration failures trigger `git revert` (new commit, never force-push)\n- **Blocked tasks**: After 2 failed attempts, tasks escalate to human review\n- **Dead agent detection**: Heartbeat every 5 min, reassign after 10 min timeout\n- **Graceful shutdown**: `\u002Fsdlc-stop` drains workers, returns unstarted tasks to backlog\n- **Scope creep detection**: PR diff files compared against predicted files list\n- **Spec drift detection**: SHA-256 hash comparison catches requirement changes mid-sprint\n\n## Installation\n\n```bash\n# Clone the repo\ngit clone https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow.git\n\n# Copy skills and prompts to your Claude Code config\ncp -r agentflow\u002Fskills\u002F* ~\u002F.claude\u002Fskills\u002F\ncp -r agentflow\u002Fprompts\u002F* ~\u002F.claude\u002Fsdlc\u002Fprompts\u002F\ncp agentflow\u002Fconventions.md ~\u002F.claude\u002Fsdlc\u002Fconventions.md\n```\n\nOr install as a Claude Code plugin:\n\n```bash\n\u002Fplugin marketplace add UrRhb\u002Fagentflow\n\u002Fplugin install agentflow\n```\n\n## Best Practices\n\n- Do: Write a clear SPEC.md before running `\u002Fspec-to-board`\n- Do: Start with 3-4 workers for a typical project\n- Do: Monitor from your Kanban board and drag cards to \"Needs Human\" when needed\n- Do: Review LEARNINGS.md periodically — it captures common failure patterns\n- Don't: Skip the deterministic quality gates — they catch most issues cheaply\n- Don't: Force-push to main — AgentFlow uses `git revert` for safety\n- Don't: Run more workers than your project's parallelism supports\n\n## Troubleshooting\n\n### Problem: Worker appears stuck or dead\n**Symptoms:** Task card hasn't moved in 15+ minutes, no new comments\n**Solution:** The orchestrator detects dead agents via heartbeat and reassigns after 10 minutes. If the issue persists, run `\u002Fsdlc-health` to check status and manually drag the card back to Backlog.\n\n### Problem: Cost guardrail triggered\n**Symptoms:** Task moved to \"Needs Human\" with COST:CRITICAL tag\n**Solution:** Review the task's comment thread for accumulated context. Decide whether to increase the budget, simplify the task, or split it into smaller pieces.\n\n### Problem: Integration test failure after merge\n**Symptoms:** Task auto-reverted from main\n**Solution:** The auto-revert preserves main stability. Check the task's retry context in comments, which carries what was tried and what failed. The next worker assigned will use this context.\n\n## Related Skills\n\n- `@brainstorming` - Use before AgentFlow to design your SPEC.md\n- `@writing-plans` - Complements spec writing for task decomposition\n- `@test-driven-development` - Works well with AgentFlow's quality gates\n- `@subagent-driven-development` - Alternative approach to multi-agent coordination\n\n## Additional Resources\n\n- [AgentFlow Repository](https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow)\n- [Architecture Documentation](https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow\u002Fblob\u002Fmain\u002Fdocs\u002Farchitecture.md)\n- [Gap Registry (45 failure modes)](https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow\u002Fblob\u002Fmain\u002Fdocs\u002Fgap-registry.md)\n- [Getting Started Guide](https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow\u002Fblob\u002Fmain\u002Fdocs\u002Fgetting-started.md)\n","# AgentFlow\n\n## Overview\n\nAgentFlow turns your existing Kanban board into a fully autonomous AI development pipeline. Instead of building custom orchestration infrastructure, it treats your project management tool (Asana, GitHub Projects, Linear) as a distributed state machine — tasks move through stages, AI agents read and write state via comments, and humans intervene through the same UI they already use.\n\nThe result is complete pipeline observability from your phone, free crash recovery (state lives in your PM tool, not in memory), and human override at any point by dragging a card.\n\n## When to Use This Skill\n\n- Use when you need to orchestrate multiple Claude Code workers across a full development lifecycle (build, review, test, integrate)\n- Use when you want deterministic quality gates (tsc\u002Feslint\u002Ftests) before AI review on AI-generated code\n- Use when you want full pipeline visibility from your Kanban board or phone\n- Use when running a solo or team project that needs autonomous task dispatch with cost tracking\n- Use when you need crash-proof orchestration that survives session restarts\n\n## Core Concepts\n\n### 7-Stage Kanban Pipeline\n\nTasks flow through: Backlog, Research, Build, Review, Test, Integrate, Done. Each stage has specific gates. The Kanban board IS the orchestration layer — no separate database, no message queue, no custom infrastructure.\n\n### Stateless Orchestrator\n\nA crontab-driven one-shot sweep runs every 15 minutes. No daemon, no session dependency. If it crashes, the next sweep picks up where it left off because all state lives in your PM tool.\n\n### Deterministic Before Probabilistic\n\nHard gates (tsc + eslint + tests) run before any AI review, catching roughly 60% of issues at near-zero cost. AI review comes after, as a second layer.\n\n### Adversarial Review\n\nA different AI agent reviews code and must list 3 things wrong before deciding to pass. This prevents rubber-stamp approvals.\n\n### Transitive Priority Dispatch\n\nTasks that unblock the most downstream work get built first, automatically computing the critical path.\n\n## Skills \u002F Commands\n\n### `\u002Fspec-to-board`\nDecomposes a SPEC.md into atomic tasks on your Kanban board with dependencies mapped.\n\n### `\u002Fsdlc-orchestrate`\nDispatches tasks to workers based on transitive priority and conflict detection. Runs as a crontab sweep.\n\n### `\u002Fsdlc-worker --slot \u003CN>`\nRuns a worker in a terminal slot that picks up tasks, builds code, and creates PRs. Run 3-4 workers in parallel.\n\n### `\u002Fsdlc-health`\nReal-time pipeline status dashboard showing current stage, assigned agent, retry count, and accumulated cost for every task.\n\n### `\u002Fsdlc-stop`\nGraceful shutdown: active workers finish their current task, unstarted tasks return to Backlog.\n\n## Step-by-Step Guide\n\n### 1. Write Your Spec\n\nCreate a `SPEC.md` for your project describing what you want to build.\n\n### 2. Decompose Into Tasks\n\n```\nclaude -p \"\u002Fspec-to-board\"\n```\n\nThis reads your SPEC.md, decomposes it into atomic tasks, maps dependencies, and creates them on your Kanban board.\n\n### 3. Start Workers\n\nOpen 3-4 terminal windows, each as a worker slot:\n\n```bash\n# Terminal 2 — Builder\nclaude -p \"\u002Fsdlc-worker --slot T2\"\n\n# Terminal 3 — Builder\nclaude -p \"\u002Fsdlc-worker --slot T3\"\n\n# Terminal 4 — Reviewer\nclaude -p \"\u002Fsdlc-worker --slot T4\"\n\n# Terminal 5 — Tester\nclaude -p \"\u002Fsdlc-worker --slot T5\"\n```\n\n### 4. Start the Orchestrator\n\n```bash\n# Add to crontab (runs every 15 minutes)\ncrontab -e\n# Add: *\u002F15 * * * * ~\u002F.claude\u002Fsdlc\u002Fagentflow-cron.sh >> \u002Ftmp\u002Fagentflow-orchestrate.log 2>&1\n```\n\n### 5. Monitor and Intervene\n\nOpen your Kanban board on your phone. Watch tasks flow through the pipeline. Drag any card to \"Needs Human\" to intervene. Run `\u002Fsdlc-health` for a terminal dashboard.\n\n### 6. Stop the Pipeline\n\n```\nclaude -p \"\u002Fsdlc-stop\"\n```\n\n## Quality Gates\n\nEach stage enforces specific gates before promotion:\n\n- **Build to Review**: `tsc` + `eslint` + `npm test` must all pass (deterministic)\n- **Review to Test**: Adversarial reviewer must list 3 issues before passing\n- **Test to Integrate**: 80% coverage threshold on new files\n- **Integrate to Done**: Full test suite on main after merge; auto-reverts on failure\n\n## Cost Tracking\n\nPer-task cost tracking with stage ceilings (Sonnet defaults):\n\n- Research: ~$0.10\n- Build: ~$0.40\n- Review: ~$0.10\n- Test: ~$0.05\n- Integrate: ~$0.03\n\nAutomatic guardrails: warning at $3\u002F$8, hard stop at $10\u002F$20 (Sonnet\u002FOpus) with human escalation.\n\n## Safety and Recovery\n\n- **Auto-revert**: Integration failures trigger `git revert` (new commit, never force-push)\n- **Blocked tasks**: After 2 failed attempts, tasks escalate to human review\n- **Dead agent detection**: Heartbeat every 5 min, reassign after 10 min timeout\n- **Graceful shutdown**: `\u002Fsdlc-stop` drains workers, returns unstarted tasks to backlog\n- **Scope creep detection**: PR diff files compared against predicted files list\n- **Spec drift detection**: SHA-256 hash comparison catches requirement changes mid-sprint\n\n## Installation\n\n```bash\n# Clone the repo\ngit clone https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow.git\n\n# Copy skills and prompts to your Claude Code config\ncp -r agentflow\u002Fskills\u002F* ~\u002F.claude\u002Fskills\u002F\ncp -r agentflow\u002Fprompts\u002F* ~\u002F.claude\u002Fsdlc\u002Fprompts\u002F\ncp agentflow\u002Fconventions.md ~\u002F.claude\u002Fsdlc\u002Fconventions.md\n```\n\nOr install as a Claude Code plugin:\n\n```bash\n\u002Fplugin marketplace add UrRhb\u002Fagentflow\n\u002Fplugin install agentflow\n```\n\n## Best Practices\n\n- Do: Write a clear SPEC.md before running `\u002Fspec-to-board`\n- Do: Start with 3-4 workers for a typical project\n- Do: Monitor from your Kanban board and drag cards to \"Needs Human\" when needed\n- Do: Review LEARNINGS.md periodically — it captures common failure patterns\n- Don't: Skip the deterministic quality gates — they catch most issues cheaply\n- Don't: Force-push to main — AgentFlow uses `git revert` for safety\n- Don't: Run more workers than your project's parallelism supports\n\n## Troubleshooting\n\n### Problem: Worker appears stuck or dead\n**Symptoms:** Task card hasn't moved in 15+ minutes, no new comments\n**Solution:** The orchestrator detects dead agents via heartbeat and reassigns after 10 minutes. If the issue persists, run `\u002Fsdlc-health` to check status and manually drag the card back to Backlog.\n\n### Problem: Cost guardrail triggered\n**Symptoms:** Task moved to \"Needs Human\" with COST:CRITICAL tag\n**Solution:** Review the task's comment thread for accumulated context. Decide whether to increase the budget, simplify the task, or split it into smaller pieces.\n\n### Problem: Integration test failure after merge\n**Symptoms:** Task auto-reverted from main\n**Solution:** The auto-revert preserves main stability. Check the task's retry context in comments, which carries what was tried and what failed. The next worker assigned will use this context.\n\n## Related Skills\n\n- `@brainstorming` - Use before AgentFlow to design your SPEC.md\n- `@writing-plans` - Complements spec writing for task decomposition\n- `@test-driven-development` - Works well with AgentFlow's quality gates\n- `@subagent-driven-development` - Alternative approach to multi-agent coordination\n\n## Additional Resources\n\n- [AgentFlow Repository](https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow)\n- [Architecture Documentation](https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow\u002Fblob\u002Fmain\u002Fdocs\u002Farchitecture.md)\n- [Gap Registry (45 failure modes)](https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow\u002Fblob\u002Fmain\u002Fdocs\u002Fgap-registry.md)\n- [Getting Started Guide](https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow\u002Fblob\u002Fmain\u002Fdocs\u002Fgetting-started.md)\n",{"name":5,"risk":37,"source":22,"date_added":43,"description":7},"2026-04-02","main","a50a3aa6b39fb0e1b7db88bef1bfc9c93606e126","modules\u002Fagent_skills\u002Fawesome-skills\u002Fplaybooks\u002Fagentflow",0,"https:\u002F\u002Fgithub.com\u002FSam-06060\u002Fjarvis-assistant","https:\u002F\u002Fgithub.com\u002FSam-06060","Mobile Application Developer | Kotlin | Flutter, KMP, Swfit, Android,Swift UI | Building at Saar It Resources | Creator of Jarvis (AI Assistant)","2026-06-23 05:13:38",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add Sam-06060\u002Fjarvis-assistant --skill agentflow",{"tool":58,"command":59},"bunx","bunx skills add Sam-06060\u002Fjarvis-assistant --skill agentflow",{"tool":61,"command":62},"pnpm","pnpm dlx skills add Sam-06060\u002Fjarvis-assistant --skill agentflow","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSam-06060\u002Fjarvis-assistant\u002Fblob\u002Fmain\u002Fmodules\u002Fagent_skills\u002Fawesome-skills\u002Fplaybooks\u002Fagentflow\u002FSKILL.md",true,[],[67,80,96,123,142,168],{"skillNo":68,"name":69,"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":70,"categories":71,"keywords":77,"publishedAt":38},"01M6GDRVS6FXX3ESH0C9DW01C0","test_skill","https:\u002F\u002Fgithub.com\u002FSam-06060\u002Fjarvis-assistant\u002Fblob\u002Fmain\u002Fscratch\u002Ftest_skill\u002FSKILL.md",[72],{"categoryNo":73,"categoryName":74,"taxonomyType":75,"taxonomyTypeDesc":76},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[78,79],"Test Skill","test",{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":38},"01M6GDRQ40HX22MA6XWC31RHHK","zustand-store-ts","Create Zustand stores following established patterns with proper TypeScript types and middleware.","https:\u002F\u002Fgithub.com\u002FSam-06060\u002Fjarvis-assistant\u002Fblob\u002Fmain\u002Fmodules\u002Fagent_skills\u002Fawesome-skills\u002Fplaybooks\u002Fzustand-store-ts\u002FSKILL.md",[],[87,88,89,90,91,92,93,22,94,95],"zustand store ts","zustand","store","with","types","middleware","patterns","create","typescript",{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":105,"publishedAt":38},"01M6GDRKEA0WE670SPFWX5GKCN","zoom-automation","Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002FSam-06060\u002Fjarvis-assistant\u002Fblob\u002Fmain\u002Fmodules\u002Fagent_skills\u002Fawesome-skills\u002Fplaybooks\u002Fzoom-automation\u002FSKILL.md",[102],{"categoryNo":103,"categoryName":104,"taxonomyType":75,"taxonomyTypeDesc":76},"01JBSEEDCAT000000000000023","Skill与智能体开发",[106,107,108,109,110,111,112,113,114,115,116,117,118,119,22,120,121,122],"automation","zoom automation","zoom","first","Tools","search","MCP","via","meeting","automate","critical","creation","webinars","composio","recordings","management","tracking",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":130,"publishedAt":38},"01M6GDRFS1452PC71JQ38S24HR","zoho-crm-automation","Automate Zoho CRM tasks via Rube MCP (Composio): create\u002Fupdate records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002FSam-06060\u002Fjarvis-assistant\u002Fblob\u002Fmain\u002Fmodules\u002Fagent_skills\u002Fawesome-skills\u002Fplaybooks\u002Fzoho-crm-automation\u002FSKILL.md",[129],{"categoryNo":103,"categoryName":104,"taxonomyType":75,"taxonomyTypeDesc":76},[131,106,132,133,134,135,136,22,111,137,119,138,116,115,110,139,94,140,112,141],"crm automation","zoho crm","crm","zoho crm automation","zoho","leads","contacts","records","update","tasks","manage",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":151,"publishedAt":38},"01M6GDRCKQBAVTGHX5XBH26KPZ","zod-validation-expert","Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.","https:\u002F\u002Fgithub.com\u002FSam-06060\u002Fjarvis-assistant\u002Fblob\u002Fmain\u002Fmodules\u002Fagent_skills\u002Fawesome-skills\u002Fplaybooks\u002Fzod-validation-expert\u002FSKILL.md",[148],{"categoryNo":149,"categoryName":150,"taxonomyType":75,"taxonomyTypeDesc":76},"01JBSEEDCAT000000000000009","前端开发",[152,153,154,155,156,95,37,157,158,159,160,161,90,162,163,164,165,22,166,167],"expert","zod","zod validation expert","validation","react","parsing","errors","schema validation","react hook form","hook","trpc","form","type","next","schema","Next.js",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":175,"publishedAt":38},"01M6GDR658B08K4MY0RWD4A6EH","zeroize-audit","Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C\u002FC++\u002FRust code handling secrets, keys, passwords, or other sensitive data.","https:\u002F\u002Fgithub.com\u002FSam-06060\u002Fjarvis-assistant\u002Fblob\u002Fmain\u002Fmodules\u002Fagent_skills\u002Fawesome-skills\u002Fplaybooks\u002Fzeroize-audit\u002FSKILL.md",[174],{"categoryNo":103,"categoryName":104,"taxonomyType":75,"taxonomyTypeDesc":76},[176,177,178,179,180,181,182,183,22,184,185,186,187,188,189,190,191,33,192,112],"zeroize audit","audit","write","passwords","get","project","c++","activate","assembly","read","Bash","secrets","analysis","data","flow","verification","rust"]