[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A5NXKCFRF1HC6GCATFVRV1":3,"skill-same:01M7A5NXKCFRF1HC6GCATFVRV1":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7A5NXKCFRF1HC6GCATFVRV1","mawf-orchestration",null,"Plan and coordinate cost-bounded multi-agent workflows for complex projects using mawf.","imBlanker\u002Fmulti-agents-workflow","imBlanker","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F197924924?v=4","01M7A5MDZZ6ZJDWQFNEZMX7P0E","WUSHANGZHEN0010","01M7A5ME12861T0VDS548C6NX6",1,"MIT","https:\u002F\u002Fgithub.com\u002FimBlanker\u002Fmulti-agents-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fmawf-orchestration\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: mawf-orchestration\ndescription: \"Plan and coordinate cost-bounded multi-agent workflows for complex projects using mawf.\"\n---\n\n# MAW Orchestration (skill)\n\n> Use when planning or running a multi-agent workflow for a complex codebase.\n\nMAW (multi-agents-workflow) dynamically picks an architecture per project and writes per-agent, independently-editable configs under `.mawf\u002F`.\n\n## When to use\n- A new complex project: after `mawf init`, run `mawf plan`.\n- An existing project where a single agent is insufficient (many files, multiple languages, high risk, large context).\n- You want cost-bounded multi-agent runs with Codex review gates.\n\n## The four paradigms MAW picks between (and combines)\n- **Loop engineering** — open-ended single tasks; Think→Act→Observe until done.\n- **Subagents \u002F orchestrator-workers** — dynamic, parallelizable subtasks; each subagent gets its own context window and compresses findings.\n- **Multi-agent** — high-value breadth-first work that tolerates ~15× token cost.\n- **Graph engineering** — predictable, inspectable control with HITL, persistence, and review gates.\n\nMAW also understands **dynamic** (prefer the host's native dynamic-workflow\u002Fmulti-agent mechanism) and **ultracode** (complex coding with implement→codex-review→fix loops + graph checkpoints).\n\n## Quickstart\n```bash\nmawf init -u \u003Cuser>          # init workspace\nmawf plan --project .        # probe + plan + write .mawf\u002F\nmawf doctor                  # env + capability check\nmawf cost                    # real cost rate from cc-switch\nmawf run                     # execution guidance (batches + guards)\n```\n\n## Core invariants\n- Start simple; add complexity only when it demonstrably helps.\n- The cost guard is authoritative: $5\u002Fmin per agent, $10\u002Fmin total (defaults), measured from real cc-switch spend — not token estimates.\n- Codex review is risk-gated, not on every step.\n- Every file under `.mawf\u002F` is editable; `mawf plan` regenerates from fresh signals.\n\nSee the architecture report at `docs\u002FARCHITECTURE.md` for the theoretical grounding.\n","# MAW Orchestration (skill)\n\n> Use when planning or running a multi-agent workflow for a complex codebase.\n\nMAW (multi-agents-workflow) dynamically picks an architecture per project and writes per-agent, independently-editable configs under `.mawf\u002F`.\n\n## When to use\n- A new complex project: after `mawf init`, run `mawf plan`.\n- An existing project where a single agent is insufficient (many files, multiple languages, high risk, large context).\n- You want cost-bounded multi-agent runs with Codex review gates.\n\n## The four paradigms MAW picks between (and combines)\n- **Loop engineering** — open-ended single tasks; Think→Act→Observe until done.\n- **Subagents \u002F orchestrator-workers** — dynamic, parallelizable subtasks; each subagent gets its own context window and compresses findings.\n- **Multi-agent** — high-value breadth-first work that tolerates ~15× token cost.\n- **Graph engineering** — predictable, inspectable control with HITL, persistence, and review gates.\n\nMAW also understands **dynamic** (prefer the host's native dynamic-workflow\u002Fmulti-agent mechanism) and **ultracode** (complex coding with implement→codex-review→fix loops + graph checkpoints).\n\n## Quickstart\n```bash\nmawf init -u \u003Cuser>          # init workspace\nmawf plan --project .        # probe + plan + write .mawf\u002F\nmawf doctor                  # env + capability check\nmawf cost                    # real cost rate from cc-switch\nmawf run                     # execution guidance (batches + guards)\n```\n\n## Core invariants\n- Start simple; add complexity only when it demonstrably helps.\n- The cost guard is authoritative: $5\u002Fmin per agent, $10\u002Fmin total (defaults), measured from real cc-switch spend — not token estimates.\n- Codex review is risk-gated, not on every step.\n- Every file under `.mawf\u002F` is editable; `mawf plan` regenerates from fresh signals.\n\nSee the architecture report at `docs\u002FARCHITECTURE.md` for the theoretical grounding.\n",{"name":5,"description":7},"main","508d7774c4f188065d05f2a51eb7609cd97c0367","skills\u002Fmawf-orchestration",0,"https:\u002F\u002Fgithub.com\u002FimBlanker\u002Fmulti-agents-workflow","https:\u002F\u002Fimblanker.github.io\u002Fmulti-agents-workflow\u002F","https:\u002F\u002Fgithub.com\u002FimBlanker","I am a master student in Shenzhen MSU-BIT University. I love solving various problems after struggling. ","2026-11-09 16:53:27",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add imBlanker\u002Fmulti-agents-workflow --skill mawf-orchestration",{"tool":39,"command":40},"bunx","bunx skills add imBlanker\u002Fmulti-agents-workflow --skill mawf-orchestration",{"tool":42,"command":43},"pnpm","pnpm dlx skills add imBlanker\u002Fmulti-agents-workflow --skill mawf-orchestration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FimBlanker\u002Fmulti-agents-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fmawf-orchestration\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7A5P1QNT3EVNA1GSQGW5KVB","mawf-planner","Choose an agent architecture from project signals, host capabilities, risk, parallelism, and cost constraints.","https:\u002F\u002Fgithub.com\u002FimBlanker\u002Fmulti-agents-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fmawf-planner\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7A5NS3YAEG37D8S72JXY2CT","mawf-loop","Run open-ended coding or research work with an iterative act, observe, reflect, and decide loop.","https:\u002F\u002Fgithub.com\u002FimBlanker\u002Fmulti-agents-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fmawf-loop\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7A5NN6QB0HSF5A74T41BYHN","mawf-knowledge","Retrieve prior decisions and solutions from the MAWF knowledge store and inject bounded context. Use when planning or taking over a task, before authoring decision\u002Fsolution notes, or when a symptom smells like a known pitfall.","https:\u002F\u002Fgithub.com\u002FimBlanker\u002Fmulti-agents-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fmawf-knowledge\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7A5NDSW69VHHAGMVQ9MXPHE","trellis-brainstorm","Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, runs the grill-with-docs interview (grilling + domain-modeling) to resolve the decision tree in rounds, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex task.","https:\u002F\u002Fgithub.com\u002FimBlanker\u002Fmulti-agents-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fmawf-grill\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7A5N9R8CPRK7CX4NAAE41PY","mawf-graph","Plan and inspect graph workflows with review gates, branching, checkpoints, and persistent execution state.","https:\u002F\u002Fgithub.com\u002FimBlanker\u002Fmulti-agents-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fmawf-graph\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7A5N34NBNBX0XV62VKHBBT0","mawf-decision","Author and maintain long-lived decision notes in the MAWF knowledge store (write-notes semantics). Use only for non-trivial changes that deserve a durable decision record; never for mechanical edits or task-local design.","https:\u002F\u002Fgithub.com\u002FimBlanker\u002Fmulti-agents-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fmawf-decision\u002FSKILL.md",[],[]]