[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PB5JSQZJHW2B69HQ29JKHJ":3,"skill-same:01M6PB5JSQZJHW2B69HQ29JKHJ":78},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":31,"commitSha":59,"skillDirectory":60,"forksCount":13,"repositoryHtmlUrl":61,"repositoryHomepageUrl":6,"ownerHtmlUrl":62,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":63,"install":64,"resources":77},"01M6PB5JSQZJHW2B69HQ29JKHJ","open-dynamic-workflows",null,"Plan, orchestrate, and adversarially verify parallel AI coding agents with a dynamic multi-agent workflow engine.","duc-duy-1612\u002FOnline-Delivery-Systems-Web","duc-duy-1612","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F192231384?v=4","01M6NSDKQQDKVTHZ8DZMZ1VYY6","01M6NSDKW8DDVTQHBT1HBDDJPT",0,"MIT","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fopen-dynamic-workflows\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],"open dynamic workflows","workflows","open","dynamic workflows","multi-agent","adversarial-verification","coding-agents","critical","main","community","parallel","coding","gemini","plan","orchestrate","workflow engine","verification","ai coding agents","workflow","orchestration","2026-11-10 10:12:30",false,"---\nname: open-dynamic-workflows\ndescription: \"Plan, orchestrate, and adversarially verify parallel AI coding agents with a dynamic multi-agent workflow engine.\"\ncategory: ai-agents\nrisk: critical\nsource: community\nsource_repo: Suraj1235\u002Fopen-dynamic-workflows\nsource_type: community\ndate_added: \"2026-06-06\"\nauthor: Suraj1235\ntags: [multi-agent, orchestration, workflow, adversarial-verification, coding-agents]\ntools: [claude, cursor, codex, gemini, antigravity]\n# Optional: declare the upstream license if source_repo is set\nlicense: \"MIT\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002FSuraj1235\u002Fopen-dynamic-workflows\u002Fblob\u002Fmain\u002FLICENSE\"\n---\n\n# Open Dynamic Workflows\n\n## Overview\n\nOpen Dynamic Workflows (ODW) is an open-source dynamic multi-agent workflow engine for AI coding agents such as OpenCode, Codex, Antigravity, and VS Code. It lets you plan a task, orchestrate multiple agents working in parallel, and adversarially verify their output before it lands. ODW ships a Codex\u002FAntigravity skill folder (`SKILL.md` plus a daemon bridge) and an OpenCode plugin, and it is bring-your-own-model (Anthropic, OpenAI-compatible, or Ollama). This skill is adapted from the community project at `Suraj1235\u002Fopen-dynamic-workflows`.\n\n## When to Use This Skill\n\n- Use when you need to decompose a coding task into independent subtasks and run multiple agents in parallel.\n- Use when working across more than one AI coding tool (OpenCode, Codex, Antigravity, VS Code) and want a single orchestration layer.\n- Use when the user asks for adversarial review or verification of agent-generated changes before merging.\n\n## How It Works\n\n### Step 1: Plan\n\nODW takes a high-level goal and produces a dynamic workflow graph of subtasks, identifying which can run in parallel and which have dependencies.\n\n### Step 2: Orchestrate\n\nThe engine dispatches subtasks to parallel agents through the OpenCode plugin or the Codex\u002FAntigravity daemon bridge, using your configured model provider (Anthropic, OpenAI-compatible, or Ollama).\n\n### Step 3: Adversarially Verify\n\nCompleted work is routed through an adversarial verification pass that challenges the output before results are synthesized and returned.\n\n## Examples\n\n### Example 1: Run a parallel workflow\n\nODW is installed from source (clone the repo, then `npm install`). The CLI is\n`odw-daemon` — run it as `npm run odw -- \u003Cargs>` from inside the repo, or as\n`npx odw-daemon \u003Cargs>` \u002F a global `odw-daemon` if you link the bin.\n\n```bash\n# Configure your model provider (bring-your-own-model)\nexport ANTHROPIC_API_KEY=...        # or an OpenAI-compatible \u002F Ollama endpoint\n\n# One-time setup: generate ~\u002F.odw\u002Fconfig.json\nnpm run setup\n\n# Start the local workflow daemon (once)\nnpm run odw -- start\n\n# Plan, orchestrate, and verify a task across parallel agents\nnpm run odw -- run --prompt \"refactor the auth module and add tests\"\n```\n\n### Example 2: Use the Codex\u002FAntigravity skill bridge\n\n```bash\n# ODW ships a SKILL.md + daemon bridge consumed by Codex \u002F Antigravity.\n# Start the daemon, then run a saved orchestration script through it:\nnpm run odw -- start\nnpm run odw -- run --script examples\u002Fworkflows\u002Fstudio-prime.workflow.js --cwd .\n```\n\n## Best Practices\n\n- ✅ Scope each subtask so agents can run without shared state.\n- ✅ Keep the adversarial verification pass enabled before merging agent output.\n- ❌ Don't run interdependent subtasks in parallel without declaring their dependencies.\n- ❌ Don't commit provider API keys; use environment variables or a secrets manager.\n\n## Limitations\n\n- This skill does not replace environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, or safety boundaries are missing.\n\n## Security & Safety Notes\n\n- ODW executes agent-generated code and shell commands; run it only in an authorized, local, or sandboxed environment.\n- Model provider credentials (Anthropic \u002F OpenAI-compatible \u002F Ollama) must be supplied via environment variables, never committed to source.\n- Review adversarial-verification output before applying changes to a production branch.\n\n## Common Pitfalls\n\n- **Problem:** Parallel agents collide on the same files.\n  **Solution:** Give each subtask exclusive file\u002Fmodule ownership and run conflicting tasks sequentially.\n\n## Related Skills\n\n- `@multi-agent-orchestration` - When coordinating multiple agents on one goal.\n- `@code-review` - How adversarial verification complements human review.\n","# Open Dynamic Workflows\n\n## Overview\n\nOpen Dynamic Workflows (ODW) is an open-source dynamic multi-agent workflow engine for AI coding agents such as OpenCode, Codex, Antigravity, and VS Code. It lets you plan a task, orchestrate multiple agents working in parallel, and adversarially verify their output before it lands. ODW ships a Codex\u002FAntigravity skill folder (`SKILL.md` plus a daemon bridge) and an OpenCode plugin, and it is bring-your-own-model (Anthropic, OpenAI-compatible, or Ollama). This skill is adapted from the community project at `Suraj1235\u002Fopen-dynamic-workflows`.\n\n## When to Use This Skill\n\n- Use when you need to decompose a coding task into independent subtasks and run multiple agents in parallel.\n- Use when working across more than one AI coding tool (OpenCode, Codex, Antigravity, VS Code) and want a single orchestration layer.\n- Use when the user asks for adversarial review or verification of agent-generated changes before merging.\n\n## How It Works\n\n### Step 1: Plan\n\nODW takes a high-level goal and produces a dynamic workflow graph of subtasks, identifying which can run in parallel and which have dependencies.\n\n### Step 2: Orchestrate\n\nThe engine dispatches subtasks to parallel agents through the OpenCode plugin or the Codex\u002FAntigravity daemon bridge, using your configured model provider (Anthropic, OpenAI-compatible, or Ollama).\n\n### Step 3: Adversarially Verify\n\nCompleted work is routed through an adversarial verification pass that challenges the output before results are synthesized and returned.\n\n## Examples\n\n### Example 1: Run a parallel workflow\n\nODW is installed from source (clone the repo, then `npm install`). The CLI is\n`odw-daemon` — run it as `npm run odw -- \u003Cargs>` from inside the repo, or as\n`npx odw-daemon \u003Cargs>` \u002F a global `odw-daemon` if you link the bin.\n\n```bash\n# Configure your model provider (bring-your-own-model)\nexport ANTHROPIC_API_KEY=...        # or an OpenAI-compatible \u002F Ollama endpoint\n\n# One-time setup: generate ~\u002F.odw\u002Fconfig.json\nnpm run setup\n\n# Start the local workflow daemon (once)\nnpm run odw -- start\n\n# Plan, orchestrate, and verify a task across parallel agents\nnpm run odw -- run --prompt \"refactor the auth module and add tests\"\n```\n\n### Example 2: Use the Codex\u002FAntigravity skill bridge\n\n```bash\n# ODW ships a SKILL.md + daemon bridge consumed by Codex \u002F Antigravity.\n# Start the daemon, then run a saved orchestration script through it:\nnpm run odw -- start\nnpm run odw -- run --script examples\u002Fworkflows\u002Fstudio-prime.workflow.js --cwd .\n```\n\n## Best Practices\n\n- ✅ Scope each subtask so agents can run without shared state.\n- ✅ Keep the adversarial verification pass enabled before merging agent output.\n- ❌ Don't run interdependent subtasks in parallel without declaring their dependencies.\n- ❌ Don't commit provider API keys; use environment variables or a secrets manager.\n\n## Limitations\n\n- This skill does not replace environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, or safety boundaries are missing.\n\n## Security & Safety Notes\n\n- ODW executes agent-generated code and shell commands; run it only in an authorized, local, or sandboxed environment.\n- Model provider credentials (Anthropic \u002F OpenAI-compatible \u002F Ollama) must be supplied via environment variables, never committed to source.\n- Review adversarial-verification output before applying changes to a production branch.\n\n## Common Pitfalls\n\n- **Problem:** Parallel agents collide on the same files.\n  **Solution:** Give each subtask exclusive file\u002Fmodule ownership and run conflicting tasks sequentially.\n\n## Related Skills\n\n- `@multi-agent-orchestration` - When coordinating multiple agents on one goal.\n- `@code-review` - How adversarial verification complements human review.\n",{"name":5,"risk":30,"tags":48,"tools":49,"author":54,"source":32,"license":14,"category":55,"date_added":56,"description":7,"source_repo":57,"source_type":32,"license_source":58},[27,42,41,28,29],[50,51,52,35,53],"claude","cursor","codex","antigravity","Suraj1235","ai-agents","2026-06-06","Suraj1235\u002Fopen-dynamic-workflows","https:\u002F\u002Fgithub.com\u002FSuraj1235\u002Fopen-dynamic-workflows\u002Fblob\u002Fmain\u002FLICENSE","f3312ba749561b6159f477dbfc9313c875d40a56",".agents\u002Fskills_archive\u002Fopen-dynamic-workflows","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612","2026-10-25 23:50:58",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill open-dynamic-workflows",{"tool":70,"command":71},"bunx","bunx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill open-dynamic-workflows",{"tool":73,"command":74},"pnpm","pnpm dlx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill open-dynamic-workflows","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fopen-dynamic-workflows\u002FSKILL.md",true,[],[79,104,127,151,178,201],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":88,"publishedAt":43},"01M6Q0FA5FZ410Z33Z3TFQ4DBA","zero-trust","Implement zero-trust network architecture. Configure identity-based access, micro-segmentation, and continuous verification. Use when implementing modern security architectures.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzero-trust\u002FSKILL.md",[85],{"categoryNo":86,"categoryName":87,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[89,90,91,92,93,39,81,94,95,96,97,98,32,31,99,30,100,101,102,103],"ZeRO","trust","zero trust","architecture","assessment","segmentation","devops-security","access","configure","only","active","scope","scripts","relevant","implementing",{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":43},"01M6Q0F1YZJW3KX5FBKEVZ8CV4","zcode-delegate","Delegate coding tasks to the Z.AI ZCode CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzcode-delegate\u002FSKILL.md",[],[111,112,113,114,115,42,116,117,118,119,120,121,122,98,123,32,124,125,30,126],"delegate","zcode","zcode delegate","review","cli","tasks","run","Bash","model","node","read","orchestrator","files","desktop app","app","agent-orchestration",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":43},"01M6Q0ETK41VGNMYEXW0T00AJN","youtube-transcript","Fetch YouTube transcripts through DeepAPI or local fallback tooling and save clean text output.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript\u002FSKILL.md",[],[134,135,136,137,138,52,139,140,141,142,143,144,145,32,31,146,147,148,149,150],"transcript","youtube transcript","youtube","safe","github","research","license","https","text","fetch","tooling","clean","local","output","deepapi","youtube transcripts","blob",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":168,"publishedAt":43},"01M6Q0EPPH2PVMDW40017F8WX0","youtube-transcript-skills","Fetch YouTube video transcripts, search videos\u002Fchannels, browse channels, and extract playlists via the getyoutubetranscript.com API - free tier, no card required.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript-skills\u002FSKILL.md",[157,160,163],{"categoryNo":158,"categoryName":159,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":161,"categoryName":162,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":164,"categoryName":165,"taxonomyType":166,"taxonomyTypeDesc":167},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[134,135,136,169,137,35,138,52,140,170,171,172,173,143,174,32,31,175,176,177],"youtube transcript skills","search","api","Video","browse","api-integration","free","card","channels",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":188,"publishedAt":43},"01M6Q0EAB96PX83W5PTE8A0R8D","youtube-notetaker","Turn YouTube talks into local study notes with slides, transcripts, editable annotations, and a markdown-backed viewer.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002FSKILL.md",[184,187],{"categoryNo":185,"categoryName":186,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":161,"categoryName":162,"taxonomyType":20,"taxonomyTypeDesc":21},[136,189,190,115,137,41,191,192,193,140,172,194,195,196,197,31,198,146,199,200],"youtube notetaker","notetaker","official","notes","code","markdown","slides","annotations","README","study","dair-academy","viewer",{"skillNo":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":205,"categories":206,"keywords":208,"publishedAt":43},"01M6Q0E55F0GW5MX48V8HXS8B5","youtube-full","Fetch YouTube transcripts, search videos, browse channels, and extract playlists via TranscriptAPI — no yt-dlp, no Google API key, works from any cloud server.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-full\u002FSKILL.md",[207],{"categoryNo":158,"categoryName":159,"taxonomyType":20,"taxonomyTypeDesc":21},[209,136,210,211,137,35,170,212,213,171,172,173,143,214,174,32,31,175,215,149],"youtube full","full","google","server","dlp","credits","automatic"]