[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CQJ4Z0J28HT251GGAWB9RF":3,"skill-same:01M6CQJ4Z0J28HT251GGAWB9RF":86},{"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":23,"publishedAt":50,"linkOnly":51,"markdownContent":52,"markdownBody":53,"frontMatter":54,"refName":63,"commitSha":64,"skillDirectory":65,"forksCount":14,"repositoryHtmlUrl":66,"repositoryHomepageUrl":67,"ownerHtmlUrl":68,"ownerBlogUrl":69,"ownerDescription":70,"updatedAt":71,"install":72,"resources":85},"01M6CQJ4Z0J28HT251GGAWB9RF","agent-workflow",null,"Multi-agent orchestration, subagent dispatch, autonomous loops, plan-execute-verify.","Trollz1004\u002FANTIGRAVITY","Trollz1004","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F132442315?v=4","01M6CQ4Z97ERZA2CXR388F6NZ1","Joshua Coleman","01M6CQ4ZCYE67QPNWBBV8H9DBE",0,"MIT","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002Fhermes\u002Fagent-workflow\u002Fagent-workflow\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"workflow","agent workflow","hermes agent","test-driven","subagent dispatch","test-driven-development","loops","multi","autonomous loops","agent orchestration","dispatch","execute","autonomous","brainstorm","macos","hermes","multi-agent","subagent","plan","verify","delegation","development","windows","test","orchestration","linux","2026-11-10 10:12:30",false,"---\nname: agent-workflow\ndescription: \"Multi-agent orchestration, subagent dispatch, autonomous loops, plan-execute-verify.\"\nversion: 1.0.0\nauthor: Joshua (joshlcoleman), Hermes Agent\nlicense: MIT\nplatforms: [linux, macos, windows]\nmetadata:\n  hermes:\n    tags: [agent, workflow, orchestration, subagent, autonomous, delegation]\n    related_skills: [brainstorm, test-driven-development]\n---\n\n# Agent Workflow\n\n## When to Use\n\n- Multi-step tasks that benefit from parallel execution\n- Complex research or analysis\n- Codebase-wide changes\n- Tasks requiring specialized subagents\n\n## Quick Reference\n\n| Task | Approach |\n|------|----------|\n| Parallel research | `delegate_task` with multiple goals |\n| Code implementation | `delegate_task` with TDD context |\n| Review\u002FQA | `delegate_task` with review checklist |\n| Long-running | `terminal(background=true)` + `process` |\n\n## The Plan-Execute-Verify Loop\n\n### 1. Plan\n\n```\n- Break task into 3-7 subtasks\n- Identify dependencies between subtasks\n- Determine which can run in parallel\n- Assign tools and constraints per subtask\n```\n\n### 2. Execute\n\n```python\n# Parallel execution for independent tasks\ndelegate_task(tasks=[\n    {\"goal\": \"Research X\", \"context\": \"...\"},\n    {\"goal\": \"Research Y\", \"context\": \"...\"},\n    {\"goal\": \"Research Z\", \"context\": \"...\"},\n])\n\n# Sequential for dependent tasks\nresult_1 = delegate_task(goal=\"Step 1\")\nresult_2 = delegate_task(goal=\"Step 2\", context=result_1)\n```\n\n### 3. Verify\n\n```\n- Check each subtask output against success criteria\n- Integration test the combined result\n- Document what worked and what didn't\n- Update memory\u002Flessons learned\n```\n\n## Subagent Patterns\n\n### Investigator → Builder → Reviewer\n\n```python\n# 1. Investigate\ninvestigation = delegate_task(\n    goal=\"Investigate root cause of auth token expiry\",\n    context=\"User reports 401 errors after 30 minutes. Stack: Next.js, Supabase.\",\n)\n\n# 2. Build\nbuild = delegate_task(\n    goal=\"Fix the auth token refresh issue\",\n    context=f\"Root cause: {investigation}\\nFollow TDD. Use Supabase auth.\",\n)\n\n# 3. Review\nreview = delegate_task(\n    goal=\"Review the fix for correctness and security\",\n    context=f\"Fix: {build}\\nCheck: token refresh, CSRF, session fixation.\",\n)\n```\n\n### Parallel Scrub\n\n```python\n# When order doesn't matter, fan out\ndelegate_task(tasks=[\n    {\"goal\": \"Update README\", \"context\": \"...\"},\n    {\"goal\": \"Add tests\", \"context\": \"...\"},\n    {\"goal\": \"Fix lint errors\", \"context\": \"...\"},\n    {\"goal\": \"Update types\", \"context\": \"...\"},\n])\n```\n\n## Pitfalls\n\n- **Over-parallelizing** → Some tasks need sequential context\n- **Vague goals** → Subagents need specific, checkable objectives\n- **No verification** → Always check subagent output\n- **Ignoring failures** → One failed subtask can invalidate the whole\n- **Too many levels** → Max 2 levels of delegation\n\n## Verification\n\n- [ ] All subtasks completed successfully\n- [ ] Outputs integrated correctly\n- [ ] Success criteria met for each subtask\n- [ ] No regressions from parallel changes\n- [ ] Lessons learned documented\n","# Agent Workflow\n\n## When to Use\n\n- Multi-step tasks that benefit from parallel execution\n- Complex research or analysis\n- Codebase-wide changes\n- Tasks requiring specialized subagents\n\n## Quick Reference\n\n| Task | Approach |\n|------|----------|\n| Parallel research | `delegate_task` with multiple goals |\n| Code implementation | `delegate_task` with TDD context |\n| Review\u002FQA | `delegate_task` with review checklist |\n| Long-running | `terminal(background=true)` + `process` |\n\n## The Plan-Execute-Verify Loop\n\n### 1. Plan\n\n```\n- Break task into 3-7 subtasks\n- Identify dependencies between subtasks\n- Determine which can run in parallel\n- Assign tools and constraints per subtask\n```\n\n### 2. Execute\n\n```python\n# Parallel execution for independent tasks\ndelegate_task(tasks=[\n    {\"goal\": \"Research X\", \"context\": \"...\"},\n    {\"goal\": \"Research Y\", \"context\": \"...\"},\n    {\"goal\": \"Research Z\", \"context\": \"...\"},\n])\n\n# Sequential for dependent tasks\nresult_1 = delegate_task(goal=\"Step 1\")\nresult_2 = delegate_task(goal=\"Step 2\", context=result_1)\n```\n\n### 3. Verify\n\n```\n- Check each subtask output against success criteria\n- Integration test the combined result\n- Document what worked and what didn't\n- Update memory\u002Flessons learned\n```\n\n## Subagent Patterns\n\n### Investigator → Builder → Reviewer\n\n```python\n# 1. Investigate\ninvestigation = delegate_task(\n    goal=\"Investigate root cause of auth token expiry\",\n    context=\"User reports 401 errors after 30 minutes. Stack: Next.js, Supabase.\",\n)\n\n# 2. Build\nbuild = delegate_task(\n    goal=\"Fix the auth token refresh issue\",\n    context=f\"Root cause: {investigation}\\nFollow TDD. Use Supabase auth.\",\n)\n\n# 3. Review\nreview = delegate_task(\n    goal=\"Review the fix for correctness and security\",\n    context=f\"Fix: {build}\\nCheck: token refresh, CSRF, session fixation.\",\n)\n```\n\n### Parallel Scrub\n\n```python\n# When order doesn't matter, fan out\ndelegate_task(tasks=[\n    {\"goal\": \"Update README\", \"context\": \"...\"},\n    {\"goal\": \"Add tests\", \"context\": \"...\"},\n    {\"goal\": \"Fix lint errors\", \"context\": \"...\"},\n    {\"goal\": \"Update types\", \"context\": \"...\"},\n])\n```\n\n## Pitfalls\n\n- **Over-parallelizing** → Some tasks need sequential context\n- **Vague goals** → Subagents need specific, checkable objectives\n- **No verification** → Always check subagent output\n- **Ignoring failures** → One failed subtask can invalidate the whole\n- **Too many levels** → Max 2 levels of delegation\n\n## Verification\n\n- [ ] All subtasks completed successfully\n- [ ] Outputs integrated correctly\n- [ ] Success criteria met for each subtask\n- [ ] No regressions from parallel changes\n- [ ] Lessons learned documented\n",{"name":5,"author":55,"license":15,"version":56,"metadata":57,"platforms":62,"description":7},"Joshua (joshlcoleman), Hermes Agent","1.0.0",{"hermes":58},{"tags":59,"related_skills":61},[60,24,48,41,36,44],"agent",[37,29],[49,38,46],"main","6deb42cc8c67a99d7613cb5802f8bbe01a0f3d12","hermes\u002Fagent-workflow\u002Fagent-workflow","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY","https:\u002F\u002Fwww.ai-solutions.store","https:\u002F\u002Fgithub.com\u002FTrollz1004","https:\u002F\u002Fyouandinotai.com","Founder building YouAndINotAI, OnlineRecycle, and AIDoesItAll through Trash Or Treasure Online Recycler LLC.","2026-11-11 02:46:56",{"source":8,"skillName":5,"commands":73,"prompt":83,"zipAvailable":84},[74,77,80],{"tool":75,"command":76},"npx","npx skills add Trollz1004\u002FANTIGRAVITY --skill agent-workflow",{"tool":78,"command":79},"bunx","bunx skills add Trollz1004\u002FANTIGRAVITY --skill agent-workflow",{"tool":81,"command":82},"pnpm","pnpm dlx skills add Trollz1004\u002FANTIGRAVITY --skill agent-workflow","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002Fhermes\u002Fagent-workflow\u002Fagent-workflow\u002FSKILL.md",true,[],[87,114,152,176,203,229],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":50},"01M6M5BT49KEBHJM9D0P5NM8ED","security-audit","Security guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons. Use for security questions, focused reviews, vulnerability research, security audits, or pen tests. Run the complete workflow only for explicit codebase audit or pen-test requests, full\u002Fcomprehensive\u002Fend-to-end reviews, or requested report artifacts.","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsecurity-audit\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsecurity-audit\u002FSKILL.md",[],[95,96,97,98,99,100,24,101,102,103,104,105,106,107,108,109,110,111,112,113],"security audit","audit","security","reviews","end","only","vulnerability","review","libraries","cli","run","Tools","full","for","complete","security guidance","codebase audit","tests","use",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":118,"licenseFileUrl":119,"sourceHtmlUrl":120,"categories":121,"keywords":133,"publishedAt":50},"01M6M5B16Q534MKFHKBHRZ2773","impeccable","Use when the user wants to design, redesign, shape, critique, audit, polish, simplify, harden, animate, or otherwise improve a frontend interface: websites, landing pages, dashboards, product UI, components, forms, settings, onboarding, empty states, and native iOS or Android screens. Handles UX review, hierarchy, layout, typography, color, motion, UX copy, accessibility, responsive behavior, edge cases, and capturing or documenting design systems (DESIGN.md, tokens). Also for making bland UI bolder, loud UI quieter, or ambitious visual effects. Not for backend-only or non-UI tasks.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fimpeccable\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fimpeccable\u002FSKILL.md",[122,125,128],{"categoryNo":123,"categoryName":124,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":126,"categoryName":127,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":129,"categoryName":130,"taxonomyType":131,"taxonomyTypeDesc":132},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[116,134,135,136,137,138,139,140,100,141,142,143,144,145,102,146,147,148,149,150,151],"ux copy","states","quieter","frontend","improve","design","interface","design systems","effects","simplify","tasks","components","hierarchy","critique","native","product","layout","when",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":156,"sourceHtmlUrl":157,"categories":158,"keywords":161,"publishedAt":50},"01M6M5AHHV2NPZYVMW48HP7A6H","hallmark","Design skill for websites and new pages that look designed, not generated. Use when the user asks to build or design something new, or names Hallmark. Never use it on an existing design unless the user names Hallmark, as in `\u002Fhallmark redesign \u003Cpath>`.","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fhallmark\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fhallmark\u002FSKILL.md",[159,160],{"categoryNo":126,"categoryName":127,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[154,162,163,108,164,165,139,166,113,167,168,169,96,170,171,172,173,174,175,151],"as","never","true","pages","generated","Existing","prompt","build","redesign","look","it","user","path","new",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":118,"licenseFileUrl":180,"sourceHtmlUrl":181,"categories":182,"keywords":187,"publishedAt":50},"01M6CQDXJ785JCD5PMKYD239ZZ","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[183,186],{"categoryNo":184,"categoryName":185,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":123,"categoryName":124,"taxonomyType":21,"taxonomyTypeDesc":22},[188,189,190,191,137,192,193,194,195,196,197,198,199,200,108,201,202],"webapp","testing","webapp testing","applications","debugging","toolkit","logs","browser","playwright","web","behavior","ui","screenshots","local","with",{"skillNo":204,"name":205,"nameZh":6,"description":206,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":207,"sourceHtmlUrl":208,"categories":209,"keywords":210,"publishedAt":50},"01M6CQ5HBDE9Q5WJZXQ7G72MYD","appinsights-instrumentation","Guidance for instrumenting webapps with Azure Application Insights. Provides telemetry patterns, SDK setup, and configuration references. USE FOR: how to instrument app, App Insights SDK, telemetry patterns, what is App Insights, Application Insights guidance, instrumentation examples, APM best practices. DO NOT USE FOR: adding App Insights to my app (use azure-prepare), add telemetry to my project (use azure-prepare), add monitoring (use azure-prepare). This skill provides guidance—azure-prepare orchestrates component changes.","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fappinsights-instrumentation\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fappinsights-instrumentation\u002FSKILL.md",[],[211,212,213,214,215,113,216,217,218,219,220,221,222,223,224,225,226,227,228,108],"appinsights instrumentation","instrumentation","do","azure","telemetry","monitoring","references","component","how","patterns","apm","sdk setup","app","project","insights","how to","my","add",{"skillNo":230,"name":231,"nameZh":6,"description":232,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":233,"categories":234,"keywords":248,"publishedAt":50},"01M6CQNQ5FNDP6K32RKXQ9X157","youtube-automation","YouTube automation: upload, SEO, thumbnails, scheduling, analytics.","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002Fops\u002Fskills\u002Fyoutube-automation\u002FSKILL.md",[235,238,241,242,245],{"categoryNo":236,"categoryName":237,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",{"categoryNo":239,"categoryName":240,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000019","营销推广",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":243,"categoryName":244,"taxonomyType":131,"taxonomyTypeDesc":132},"01JBSEEDCAT000000000000033","数据分析师",{"categoryNo":246,"categoryName":247,"taxonomyType":131,"taxonomyTypeDesc":132},"01JBSEEDCAT000000000000035","市场营销",[249,250,251,46,252,49,253,254,39,255,26,256,38,257],"automation","youtube","youtube automation","seo","scheduling","thumbnails","analytics","content","upload"]