[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CB6PT0ZG243HPC62TVSWZD":3,"skill-same:01M6CB6PT0ZG243HPC62TVSWZD":78},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":60,"repositoryHtmlUrl":61,"repositoryHomepageUrl":6,"ownerHtmlUrl":62,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":63,"install":64,"resources":77},"01M6CB6PT0ZG243HPC62TVSWZD","pi-workflow-orchestration",null,"Manage Pi development workflows from Hermes chat with high fidelity. Treat Pi workflow documents and prompts as authoritative; orchestrate the same flow without redesigning artifacts.","adnichols\u002Fai-configs","adnichols","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F493746?v=4","01M6C33VRY9WF6XWYPT1AFA7JJ","Aaron Nichols","01M6C33VWTNKGRM92E9G643V4W",5,"MIT","https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs\u002Fblob\u002Fmain\u002F_hermes\u002Fdefault\u002Fskills\u002Fsoftware-development\u002Fpi-workflow-orchestration\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],"workflow orchestration","pi workflow orchestration","pi","orchestration","workflow","orchestrate","review","prompts","hermes agent","hermes","plan","execution","flow","writing","artifacts","planning","development","debugging","documents","workflows","2026-11-10 10:12:30",false,"---\nname: pi-workflow-orchestration\ndescription: Manage Pi development workflows from Hermes chat with high fidelity. Treat Pi workflow documents and prompts as authoritative; orchestrate the same flow without redesigning artifacts.\nversion: 1.0.0\nauthor: Hermes Agent\nlicense: MIT\nmetadata:\n  hermes:\n    tags: [pi, workflow, orchestration, planning, review, execution]\n    related_skills: [plan, writing-plans, systematic-debugging]\n---\n\n# Pi Workflow Orchestration\n\nUse this skill when the user wants Hermes to execute a Pi development workflow through chat.\n\n## Core rule\n\nThe Pi workflow documents are the authority.\n\nDo **not** redesign:\n- plan shape\n- review protocol\n- execution handoff\n- artifact names\n- readiness states\n- workflow ordering\n\nYour job is to manage the workflow faithfully.\n\n## Primary sources of truth\n\nRead these first when present:\n- `_pi\u002Fdever-dev-workflow\u002FREADME.remote.md`\n- `_pi\u002Fdever-dev-workflow\u002Fprompts\u002F*.md`\n- `_pi\u002Fdever-dev-workflow\u002Fagents\u002F*.md`\n- `_pi\u002Fdever-dev-workflow\u002Fextensions\u002F*`\n\nPrefer the prompt docs for exact per-step behavior and the README for canonical sequencing.\n\n## Canonical reviewed-plan flow\n\nFrom `README.remote.md`, preserve this sequence unless the user explicitly asks for a different path:\n\n1. `\u002Fdev:plan \u003Cplan>`\n2. `\u002Fdev:pm-review \u003Cplan> plan` (optional corrective PM reshaping pass)\n3. `\u002Freview:plan \u003Cplan>`\n4. `\u002Freview:change-integrate \u003Cplan>`\n5. `\u002Freview:plan-adversarial \u003Cplan>` (optional)\n6. `\u002Fcmd:execute-plan \u003Cplan>`\n\nExecution handoff then chooses between:\n- `\u002Fdev:run \u003Cplan>`\n- `\u002Fralph:run \u003Cplan>`\n\n## What Hermes should do\n\nWhen standing in for Pi, emulate the same workflow with Hermes tools:\n\n### Planning\n- Read the exact Pi planning prompt or extension-defined plan mode behavior.\n- Write\u002Fupdate the plan artifact in the workflow’s required format.\n- Do not substitute a different structure.\n\n### Review\n- Run the review step(s) defined by Pi.\n- If Pi says review is comment-only, keep it comment-only.\n- If Pi requires integrating review comments before execution, perform that integration step explicitly.\n\n### Execution\n- Respect the Pi execution mode distinction:\n  - `dev:run` = direct execution with one active-harness `reviewer` subagent pass after each phase\n  - `ralph:run` = quality-gated repeated review\u002Ffix loops after each phase\n- Continue autonomously unless truly blocked.\n\n### Validation\n- If the workflow defines a post-implementation validation step, run it.\n- Treat validation as separate from implementation when the Pi prompt does.\n\n## Fresh-session semantics\n\nIf Pi docs describe a fresh-session handoff, preserve that intent as closely as Hermes allows:\n- summarize the authoritative artifact\n- delegate cleanly with only the needed context\n- avoid leaking planning-mode assumptions into implementation\n\n## Ask the user only when\n- the Pi docs leave a material decision unresolved,\n- multiple valid execution modes exist and Pi expects an explicit choice,\n- or a blocker changes external behavior \u002F risk materially.\n\nOtherwise proceed.\n\n## Anti-patterns\n\nDo not:\n- translate Pi into a nicer generic Hermes framework\n- replace Pi’s plan artifact with your preferred template\n- skip required review\u002Fintegration steps\n- collapse distinct Pi steps into one because it feels simpler\n- introduce new workflow states not present in Pi docs\n- stop after a resumable checkpoint if Pi intends continuous execution\n\n## Minimal operating procedure\n\n1. Read README + exact prompt doc(s) for the requested stage.\n2. Identify current stage in the Pi workflow.\n3. Execute that stage faithfully.\n4. Advance to the next Pi-defined stage.\n5. Repeat until complete or truly blocked.\n\n## Output style\n\nBe brief and operational:\n- say what stage you are executing,\n- what artifact or review gate you updated,\n- and what stage comes next.\n\nDo not explain a replacement methodology unless the user explicitly asks for one.\n","# Pi Workflow Orchestration\n\nUse this skill when the user wants Hermes to execute a Pi development workflow through chat.\n\n## Core rule\n\nThe Pi workflow documents are the authority.\n\nDo **not** redesign:\n- plan shape\n- review protocol\n- execution handoff\n- artifact names\n- readiness states\n- workflow ordering\n\nYour job is to manage the workflow faithfully.\n\n## Primary sources of truth\n\nRead these first when present:\n- `_pi\u002Fdever-dev-workflow\u002FREADME.remote.md`\n- `_pi\u002Fdever-dev-workflow\u002Fprompts\u002F*.md`\n- `_pi\u002Fdever-dev-workflow\u002Fagents\u002F*.md`\n- `_pi\u002Fdever-dev-workflow\u002Fextensions\u002F*`\n\nPrefer the prompt docs for exact per-step behavior and the README for canonical sequencing.\n\n## Canonical reviewed-plan flow\n\nFrom `README.remote.md`, preserve this sequence unless the user explicitly asks for a different path:\n\n1. `\u002Fdev:plan \u003Cplan>`\n2. `\u002Fdev:pm-review \u003Cplan> plan` (optional corrective PM reshaping pass)\n3. `\u002Freview:plan \u003Cplan>`\n4. `\u002Freview:change-integrate \u003Cplan>`\n5. `\u002Freview:plan-adversarial \u003Cplan>` (optional)\n6. `\u002Fcmd:execute-plan \u003Cplan>`\n\nExecution handoff then chooses between:\n- `\u002Fdev:run \u003Cplan>`\n- `\u002Fralph:run \u003Cplan>`\n\n## What Hermes should do\n\nWhen standing in for Pi, emulate the same workflow with Hermes tools:\n\n### Planning\n- Read the exact Pi planning prompt or extension-defined plan mode behavior.\n- Write\u002Fupdate the plan artifact in the workflow’s required format.\n- Do not substitute a different structure.\n\n### Review\n- Run the review step(s) defined by Pi.\n- If Pi says review is comment-only, keep it comment-only.\n- If Pi requires integrating review comments before execution, perform that integration step explicitly.\n\n### Execution\n- Respect the Pi execution mode distinction:\n  - `dev:run` = direct execution with one active-harness `reviewer` subagent pass after each phase\n  - `ralph:run` = quality-gated repeated review\u002Ffix loops after each phase\n- Continue autonomously unless truly blocked.\n\n### Validation\n- If the workflow defines a post-implementation validation step, run it.\n- Treat validation as separate from implementation when the Pi prompt does.\n\n## Fresh-session semantics\n\nIf Pi docs describe a fresh-session handoff, preserve that intent as closely as Hermes allows:\n- summarize the authoritative artifact\n- delegate cleanly with only the needed context\n- avoid leaking planning-mode assumptions into implementation\n\n## Ask the user only when\n- the Pi docs leave a material decision unresolved,\n- multiple valid execution modes exist and Pi expects an explicit choice,\n- or a blocker changes external behavior \u002F risk materially.\n\nOtherwise proceed.\n\n## Anti-patterns\n\nDo not:\n- translate Pi into a nicer generic Hermes framework\n- replace Pi’s plan artifact with your preferred template\n- skip required review\u002Fintegration steps\n- collapse distinct Pi steps into one because it feels simpler\n- introduce new workflow states not present in Pi docs\n- stop after a resumable checkpoint if Pi intends continuous execution\n\n## Minimal operating procedure\n\n1. Read README + exact prompt doc(s) for the requested stage.\n2. Identify current stage in the Pi workflow.\n3. Execute that stage faithfully.\n4. Advance to the next Pi-defined stage.\n5. Repeat until complete or truly blocked.\n\n## Output style\n\nBe brief and operational:\n- say what stage you are executing,\n- what artifact or review gate you updated,\n- and what stage comes next.\n\nDo not explain a replacement methodology unless the user explicitly asks for one.\n",{"name":5,"author":49,"license":15,"version":50,"metadata":51,"description":7},"Hermes Agent","1.0.0",{"hermes":52},{"tags":53,"related_skills":54},[26,28,27,39,30,35],[34,55,56],"writing-plans","systematic-debugging","main","64e2fc9afa7bb3da1138eb73399144d0e7e73e9d","_hermes\u002Fdefault\u002Fskills\u002Fsoftware-development\u002Fpi-workflow-orchestration",4,"https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs","https:\u002F\u002Fgithub.com\u002Fadnichols","2026-11-06 00:28:38",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add adnichols\u002Fai-configs --skill pi-workflow-orchestration",{"tool":70,"command":71},"bunx","bunx skills add adnichols\u002Fai-configs --skill pi-workflow-orchestration",{"tool":73,"command":74},"pnpm","pnpm dlx skills add adnichols\u002Fai-configs --skill pi-workflow-orchestration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs\u002Fblob\u002Fmain\u002F_hermes\u002Fdefault\u002Fskills\u002Fsoftware-development\u002Fpi-workflow-orchestration\u002FSKILL.md",true,[],[79,99,123,147,157,173],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":44},"01M6CB7RN791P5RRRCJWWC7DAR","blocked-page-recovery","Use when a fetch fails: 403\u002F429, paywall, WAF, bot wall.","https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs\u002Fblob\u002Fmain\u002F_hermes\u002Fdefault\u002Fskills\u002Fweb\u002Fblocked-page-recovery\u002FSKILL.md",[],[86,87,88,89,90,91,92,32,33,93,94,95,96,97,98],"recovery","page","blocked page recovery","bot","fallback","use","fetch","Citations","waf","windows","research","linux","macos",{"skillNo":100,"name":55,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":113,"publishedAt":44},"01M6CB7NQY2VVYCQJ1QBXACQF4","Use when creating or updating executable software plans. Keep plans as local files unless the user explicitly asks to register them in Doct.","https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs\u002Fblob\u002Fmain\u002F_hermes\u002Fdefault\u002Fskills\u002Fsoftware-development\u002Fwriting-plans\u002FSKILL.md",[104,107,108],{"categoryNo":105,"categoryName":106,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":109,"categoryName":110,"taxonomyType":111,"taxonomyTypeDesc":112},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[37,114,115,116,28,117,118,40,39,119,120,121,91,122,32,33,34],"writing plans","documentation","test","design","user","files","implementation","html","ops",{"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":138,"publishedAt":44},"01M6CB7JME246KZQHP73Z2STDF","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs\u002Fblob\u002Fmain\u002F_hermes\u002Fdefault\u002Fskills\u002Fsoftware-development\u002Ftest-driven-development\u002FSKILL.md",[129,132,135],{"categoryNo":130,"categoryName":131,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":133,"categoryName":134,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":136,"categoryName":137,"taxonomyType":111,"taxonomyTypeDesc":112},"01JBSEEDCAT000000000000037","律师与法务",[116,40,139,140,141,32,33,142,34,143,144,41,98,145,97,146,95],"test driven development","red-green-refactor","superpowers","quality","refactor","code","tdd","testing",{"skillNo":148,"name":56,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":153,"publishedAt":44},"01M6CB7FQ407KQTD4Z9VAWKY54","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs\u002Fblob\u002Fmain\u002F_hermes\u002Fdefault\u002Fskills\u002Fsoftware-development\u002Fsystematic-debugging\u002FSKILL.md",[152],{"categoryNo":133,"categoryName":134,"taxonomyType":21,"taxonomyTypeDesc":22},[41,154,40,141,32,33,155,34,156,95,116,97,98],"systematic debugging","troubleshooting","investigation",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":166,"publishedAt":44},"01M6CB7D57MK88HE5YPZHKH68Q","spike","Throwaway experiments to validate an idea before build.","https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs\u002Fblob\u002Fmain\u002F_hermes\u002Fdefault\u002Fskills\u002Fsoftware-development\u002Fspike\u002FSKILL.md",[163],{"categoryNo":164,"categoryName":165,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",[159,95,167,168,96,169,97,98,170,171,172,32,33,34,39],"validate","experiments","prototype","feasibility","sketch","experiment",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":183,"publishedAt":44},"01M6CB7APAQ37YE5YE1MAAFT42","simplify-code","Parallel 3-agent cleanup of recent code changes.","https:\u002F\u002Fgithub.com\u002Fadnichols\u002Fai-configs\u002Fblob\u002Fmain\u002F_hermes\u002Fdefault\u002Fskills\u002Fsoftware-development\u002Fsimplify-code\u002FSKILL.md",[179,180],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":181,"categoryName":182,"taxonomyType":111,"taxonomyTypeDesc":112},"01JBSEEDCAT000000000000030","开发工程师",[184,185,144,186,32,33,187,34,143,188,189,190,40,95,116,97,30,98],"simplify code","simplify","subagent","parallel","code-review","delegation","cleanup"]