[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6J4SXAFRX9JB4E5CQX1FRN0":3,"skill-same:01M6J4SXAFRX9JB4E5CQX1FRN0":82},{"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":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M6J4SXAFRX9JB4E5CQX1FRN0","planr-operate",null,"Run a focused operating review across seven executive lenses and produce a decision and action brief. Use for periodic product or company-level leadership review.","openplanr\u002FOpenPlanr","openplanr","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F273764861?v=4","01M6J4PHHBPM1ATKH7TXR1AZMB","OpenPlanr","01M6J4PHNQ7FWP1CC3JGNVBQ8N",6,"MIT","https:\u002F\u002Fgithub.com\u002Fopenplanr\u002FOpenPlanr\u002Fblob\u002Fmain\u002Fskills\u002Fplanr-operate\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"operate","planr operate","operating","brief","decision","review","across","leadership","product","run","action","for","periodic","produce","use","company","2026-11-10 10:12:30",false,"---\nname: planr-operate\ndescription: \"Run a focused operating review across seven executive lenses and produce a decision and action brief. Use for periodic product or company-level leadership review.\"\nlicense: MIT\n---\n\n# OpenPlanr Operate\n\nRun one useful operating review, not a ceremony. By default one agent applies all seven lenses in one pass and writes one report with decisions, actions, risks, gaps, and any real issues.\n\n## Scope the review\n\nInfer these values from the request and repository when they are clear:\n\n- **Subject** — the product, area, change, or decision under review.\n- **Window** — a date or revision range, or the current snapshot when no comparison was requested.\n- **Requested decision** — the choice the review should inform, or `periodic review`.\n- **Roster** — all seven lenses unless the user selects fewer.\n\nUse the current repository, current snapshot, periodic review, and all seven lenses as sensible\ndefaults. A recommendation may suggest a person, a role, or `unassigned`.\n\nAsk only when an unresolved choice would materially change the sources inspected or the decision\nbeing answered. Use the host's native structured-question UI when available, offering a\nrecommended choice and short alternatives. Otherwise ask one concise chat question at a time.\nNever present the scope fields as a prose questionnaire.\n\nRecord the user's wording and the effective scope in the report's Scope section. Do not claim a\ntrend from a current snapshot; describe current state and name any missing baseline.\n\n## Choose the mode\n\nDefault: this agent applies the lenses itself. Use subagents only when the user names a roster or\nasks for independent reviewers; then follow Fan out.\n\nWhere the report goes: with no `.planr\u002F` in the repository, answer in chat, or write one file where\nthe repository already keeps such documents. With `.planr\u002F`, write `board-report.md` in a cycle\ndirectory (below). `cycle.md`, `brief.md` and per-lens notes only when subagents run or the user asks to persist the cycle; a persisted cycle without fan-out writes `cycle.md` and `brief.md` with the contents defined under Fan out.\n\n## Read the sources\n\nRead the files the request names, plus `AGENTS.md` and `CLAUDE.md` when tracked, in one batch.\nExpand only for a missing contract, a dependency or a contradiction, and stop when each claim has\nevidence or a named gap. Keep observations separate from interpretation.\n\n## Apply the lenses\n\nWork through each selected lens in one pass:\n\n| Lens | Focus |\n|---|---|\n| CEO | strategy and finance: direction, runway, margin, cost of delay |\n| CTO | technology and delivery risk: architecture, reliability, security, execution risk |\n| CPO | product and activation: customer value, activation, prioritization, adoption |\n| CMO | growth and market: acquisition, positioning, demand, retention, measurement |\n| COO | operations and customer health: process, support, incidents, capacity |\n| Challenger | for each material claim: the strongest alternative, the downside, and the confidence |\n| Chair | the decision queue and action plan, from the findings above |\n\nName each Review coverage row `CEO`, `CTO`, `CPO`, `CMO`, `COO`, `Challenger` or `Chair`; the dashboard matches on those names.\n\nEvery recommendation cites a source: a project path, command output, or a named gap. Do not\nfabricate a lens with no evidence; record it as `no material finding` or `unavailable` in review\ncoverage with the smallest next action. Then assemble the report below.\n\n## Cycle directory\n\nUse a short subject slug and today's ISO date: `.planr\u002Foperate\u002F\u003Cdate>-\u003Cslug>\u002F`. Choose the first\nunused path; when the base path exists, append `-02`, `-03`, and so on. Reuse an existing cycle\nonly when the user explicitly asks to resume it and its recorded scope matches. Never overwrite a\nprior cycle implicitly. If the directory is ignored by Git, continue locally and mention that in the\nreport; do not ask the user to change ignore rules. Report an exact filesystem error only when the\ndirectory cannot be created or written.\n\n## Fan out\n\nWhen the user names a roster or asks for independent reviewers, create the cycle directory with\n`cycle.md` (effective scope, roster, revision when relevant, outcome of each lens) and `brief.md`\n(scope, revision, source paths, context searched for but not found), then one note per selected lens. An advisor lens run on its own creates the same layout with a one-lens\nroster and an unsynthesized `board-report.md`.\n\nDispatch only the selected independent advisors, in parallel when subagents are\navailable, giving each the brief path, its output path and the effective scope:\n\n| Lens | Skill | Output |\n|---|---|---|\n| Strategy and finance | `planr-ceo-review` | `ceo.md` |\n| Technology and delivery risk | `planr-cto-review` | `cto.md` |\n| Product and activation | `planr-cpo-review` | `cpo.md` |\n| Growth and market | `planr-cmo-review` | `cmo.md` |\n| Operations and customer health | `planr-coo-review` | `coo.md` |\n\nDo not create note files for omitted lenses. After the advisor work finishes:\n\n1. If Challenger is selected, run `planr-challenger-review` over the available advisor notes to\n   surface only material exceptions, alternatives, and downside.\n2. If Chair is selected, run `planr-chair-review` over the available notes to produce the decision\n   queue and action plan.\n3. If Challenger or Chair is omitted, record `omitted by scope` in review coverage and label the\n   result an unsynthesized lens summary, not a Chair recommendation.\n\nMissing or malformed lens output is an issue, not a reason to fabricate that lens or discard the\nother work. Record the problem, its effect on confidence, and the smallest next action.\n\n## Assemble `board-report.md`\n\nUse these sections in this order:\n\n```markdown\n# Operating board report — \u003Csubject>\n\n> **Contract:** operate-review-quality-contract@2.0.0\n\n## Scope\n- **Subject:** \u003Ceffective subject>\n- **Window:** \u003Ceffective window>\n- **Requested decision:** \u003Cdecision or periodic review>\n- **Custody:** local-only | repository-trackable\n\n## Executive summary\n\u003Coverall signal and the two or three points that matter most>\n\n## Decision queue\n### D1 — [P0|P1|P2|unranked] \u003Cdecision>\n- **Recommendation:** \u003Cclear choice>\n- **Why now:** \u003Cconsequence or opportunity>\n- **Suggested owner:** \u003Cperson, role, or unassigned>\n- **Confidence:** high | medium | low — \u003Creason>\n- **Alternative:** \u003Ccredible alternative and trade-off>\n- **First step:** \u003Csmallest concrete start>\n- **Expected result:** \u003Cobservable result>\n- **Check:** \u003Chow to assess the result>\n- **Dependencies:** \u003CIDs or none>\n- **Revisit when:** \u003Cobservable condition>\n- **Sources:** \u003Cnote IDs and direct project paths>\n- **Dissent:** \u003Cmaterial exception or none>\n\n## Action plan\n| ID | Priority | Action | Suggested owner | First step | Success measure | Check | Depends on |\n|---|---|---|---|---|---|---|---|\n| A1 | P0 | ... | ... | ... | ... | ... | D1 |\n\n## Risks and dissent\n\u003Conly items that could change a decision or priority>\n\n## Decision-changing gaps\n\u003Cat most five; use `None.` when empty>\n\n## Review coverage\n| Lens | Outcome | Note | Informed |\n|---|---|---|---|\n| CEO | reported \u002F no material finding \u002F unavailable \u002F omitted by scope | `file.md` or `—` | D1 \u002F watch \u002F none |\n\n## Issues\n- **I1 — \u003Cproblem>:** \u003Cimpact and practical next action>\n\u003Cor `None.`>\n```\n\nIn fan out with Chair, copy decisions and actions from `chair.md` without adding a new executive\nopinion. Without Chair, summarize only the available notes, label the report an unsynthesized lens\nsummary, and use `No decision-ready proposal was established.` plus `No proposed actions.` unless\nthose notes already state a supported proposal. Keep at most five decisions, seven actions, and five\ndecision-changing gaps. When no decision is ready, say so and keep the strongest watch items.\n\n## Quality check\n\nBefore returning, check the report (and any lens note) against [the note checklist](references\u002Fnote-checklist.md), which runs the CLI's `validate-note` when `command -v openplanr` succeeds and is the check otherwise. Put unresolved structural problems under `Issues` with their impact and next action.\n\n## Return\n\nLead with the grounded overall signal and most consequential decision or missing evidence.\nLink `board-report.md` when one was written, summarize decision and action counts and the review\ncoverage completed, and name any unavailable or unsynthesized lens. Follow\n[the shared return rules](references\u002Freturn-contract.md).\n\nWhen the OpenPlanr dashboard is running, the cycle is browsable at `#\u002Foperate\u002Fcycles\u002F\u003Cid>`, the\nreview index at `#\u002Foperate\u002Fcycles`, and the latest review at `#\u002Foperate\u002Ftoday`, read-only.\nInbox, actions, evidence, outcomes, recovery, and all mutations require an actor-bound governed\nOperate session.\n","# OpenPlanr Operate\n\nRun one useful operating review, not a ceremony. By default one agent applies all seven lenses in one pass and writes one report with decisions, actions, risks, gaps, and any real issues.\n\n## Scope the review\n\nInfer these values from the request and repository when they are clear:\n\n- **Subject** — the product, area, change, or decision under review.\n- **Window** — a date or revision range, or the current snapshot when no comparison was requested.\n- **Requested decision** — the choice the review should inform, or `periodic review`.\n- **Roster** — all seven lenses unless the user selects fewer.\n\nUse the current repository, current snapshot, periodic review, and all seven lenses as sensible\ndefaults. A recommendation may suggest a person, a role, or `unassigned`.\n\nAsk only when an unresolved choice would materially change the sources inspected or the decision\nbeing answered. Use the host's native structured-question UI when available, offering a\nrecommended choice and short alternatives. Otherwise ask one concise chat question at a time.\nNever present the scope fields as a prose questionnaire.\n\nRecord the user's wording and the effective scope in the report's Scope section. Do not claim a\ntrend from a current snapshot; describe current state and name any missing baseline.\n\n## Choose the mode\n\nDefault: this agent applies the lenses itself. Use subagents only when the user names a roster or\nasks for independent reviewers; then follow Fan out.\n\nWhere the report goes: with no `.planr\u002F` in the repository, answer in chat, or write one file where\nthe repository already keeps such documents. With `.planr\u002F`, write `board-report.md` in a cycle\ndirectory (below). `cycle.md`, `brief.md` and per-lens notes only when subagents run or the user asks to persist the cycle; a persisted cycle without fan-out writes `cycle.md` and `brief.md` with the contents defined under Fan out.\n\n## Read the sources\n\nRead the files the request names, plus `AGENTS.md` and `CLAUDE.md` when tracked, in one batch.\nExpand only for a missing contract, a dependency or a contradiction, and stop when each claim has\nevidence or a named gap. Keep observations separate from interpretation.\n\n## Apply the lenses\n\nWork through each selected lens in one pass:\n\n| Lens | Focus |\n|---|---|\n| CEO | strategy and finance: direction, runway, margin, cost of delay |\n| CTO | technology and delivery risk: architecture, reliability, security, execution risk |\n| CPO | product and activation: customer value, activation, prioritization, adoption |\n| CMO | growth and market: acquisition, positioning, demand, retention, measurement |\n| COO | operations and customer health: process, support, incidents, capacity |\n| Challenger | for each material claim: the strongest alternative, the downside, and the confidence |\n| Chair | the decision queue and action plan, from the findings above |\n\nName each Review coverage row `CEO`, `CTO`, `CPO`, `CMO`, `COO`, `Challenger` or `Chair`; the dashboard matches on those names.\n\nEvery recommendation cites a source: a project path, command output, or a named gap. Do not\nfabricate a lens with no evidence; record it as `no material finding` or `unavailable` in review\ncoverage with the smallest next action. Then assemble the report below.\n\n## Cycle directory\n\nUse a short subject slug and today's ISO date: `.planr\u002Foperate\u002F\u003Cdate>-\u003Cslug>\u002F`. Choose the first\nunused path; when the base path exists, append `-02`, `-03`, and so on. Reuse an existing cycle\nonly when the user explicitly asks to resume it and its recorded scope matches. Never overwrite a\nprior cycle implicitly. If the directory is ignored by Git, continue locally and mention that in the\nreport; do not ask the user to change ignore rules. Report an exact filesystem error only when the\ndirectory cannot be created or written.\n\n## Fan out\n\nWhen the user names a roster or asks for independent reviewers, create the cycle directory with\n`cycle.md` (effective scope, roster, revision when relevant, outcome of each lens) and `brief.md`\n(scope, revision, source paths, context searched for but not found), then one note per selected lens. An advisor lens run on its own creates the same layout with a one-lens\nroster and an unsynthesized `board-report.md`.\n\nDispatch only the selected independent advisors, in parallel when subagents are\navailable, giving each the brief path, its output path and the effective scope:\n\n| Lens | Skill | Output |\n|---|---|---|\n| Strategy and finance | `planr-ceo-review` | `ceo.md` |\n| Technology and delivery risk | `planr-cto-review` | `cto.md` |\n| Product and activation | `planr-cpo-review` | `cpo.md` |\n| Growth and market | `planr-cmo-review` | `cmo.md` |\n| Operations and customer health | `planr-coo-review` | `coo.md` |\n\nDo not create note files for omitted lenses. After the advisor work finishes:\n\n1. If Challenger is selected, run `planr-challenger-review` over the available advisor notes to\n   surface only material exceptions, alternatives, and downside.\n2. If Chair is selected, run `planr-chair-review` over the available notes to produce the decision\n   queue and action plan.\n3. If Challenger or Chair is omitted, record `omitted by scope` in review coverage and label the\n   result an unsynthesized lens summary, not a Chair recommendation.\n\nMissing or malformed lens output is an issue, not a reason to fabricate that lens or discard the\nother work. Record the problem, its effect on confidence, and the smallest next action.\n\n## Assemble `board-report.md`\n\nUse these sections in this order:\n\n```markdown\n# Operating board report — \u003Csubject>\n\n> **Contract:** operate-review-quality-contract@2.0.0\n\n## Scope\n- **Subject:** \u003Ceffective subject>\n- **Window:** \u003Ceffective window>\n- **Requested decision:** \u003Cdecision or periodic review>\n- **Custody:** local-only | repository-trackable\n\n## Executive summary\n\u003Coverall signal and the two or three points that matter most>\n\n## Decision queue\n### D1 — [P0|P1|P2|unranked] \u003Cdecision>\n- **Recommendation:** \u003Cclear choice>\n- **Why now:** \u003Cconsequence or opportunity>\n- **Suggested owner:** \u003Cperson, role, or unassigned>\n- **Confidence:** high | medium | low — \u003Creason>\n- **Alternative:** \u003Ccredible alternative and trade-off>\n- **First step:** \u003Csmallest concrete start>\n- **Expected result:** \u003Cobservable result>\n- **Check:** \u003Chow to assess the result>\n- **Dependencies:** \u003CIDs or none>\n- **Revisit when:** \u003Cobservable condition>\n- **Sources:** \u003Cnote IDs and direct project paths>\n- **Dissent:** \u003Cmaterial exception or none>\n\n## Action plan\n| ID | Priority | Action | Suggested owner | First step | Success measure | Check | Depends on |\n|---|---|---|---|---|---|---|---|\n| A1 | P0 | ... | ... | ... | ... | ... | D1 |\n\n## Risks and dissent\n\u003Conly items that could change a decision or priority>\n\n## Decision-changing gaps\n\u003Cat most five; use `None.` when empty>\n\n## Review coverage\n| Lens | Outcome | Note | Informed |\n|---|---|---|---|\n| CEO | reported \u002F no material finding \u002F unavailable \u002F omitted by scope | `file.md` or `—` | D1 \u002F watch \u002F none |\n\n## Issues\n- **I1 — \u003Cproblem>:** \u003Cimpact and practical next action>\n\u003Cor `None.`>\n```\n\nIn fan out with Chair, copy decisions and actions from `chair.md` without adding a new executive\nopinion. Without Chair, summarize only the available notes, label the report an unsynthesized lens\nsummary, and use `No decision-ready proposal was established.` plus `No proposed actions.` unless\nthose notes already state a supported proposal. Keep at most five decisions, seven actions, and five\ndecision-changing gaps. When no decision is ready, say so and keep the strongest watch items.\n\n## Quality check\n\nBefore returning, check the report (and any lens note) against [the note checklist](references\u002Fnote-checklist.md), which runs the CLI's `validate-note` when `command -v openplanr` succeeds and is the check otherwise. Put unresolved structural problems under `Issues` with their impact and next action.\n\n## Return\n\nLead with the grounded overall signal and most consequential decision or missing evidence.\nLink `board-report.md` when one was written, summarize decision and action counts and the review\ncoverage completed, and name any unavailable or unsynthesized lens. Follow\n[the shared return rules](references\u002Freturn-contract.md).\n\nWhen the OpenPlanr dashboard is running, the cycle is browsable at `#\u002Foperate\u002Fcycles\u002F\u003Cid>`, the\nreview index at `#\u002Foperate\u002Fcycles`, and the latest review at `#\u002Foperate\u002Ftoday`, read-only.\nInbox, actions, evidence, outcomes, recovery, and all mutations require an actor-bound governed\nOperate session.\n",{"name":5,"license":15,"description":7},"main","2e652da8c7d9983e0ad05bf1e27c683914ce56a1","skills\u002Fplanr-operate",1,"https:\u002F\u002Fgithub.com\u002Fopenplanr\u002FOpenPlanr","https:\u002F\u002Fopenplanr.dev","https:\u002F\u002Fgithub.com\u002Fopenplanr","https:\u002F\u002Fopenplanr.dev\u002F","Close the loop from intent to delivery. The open harness around your coding agent.","2026-11-12 12:17:02",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add openplanr\u002FOpenPlanr --skill planr-operate",{"tool":56,"command":57},"bunx","bunx skills add openplanr\u002FOpenPlanr --skill planr-operate",{"tool":59,"command":60},"pnpm","pnpm dlx skills add openplanr\u002FOpenPlanr --skill planr-operate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fopenplanr\u002FOpenPlanr\u002Fblob\u002Fmain\u002Fskills\u002Fplanr-operate\u002FSKILL.md",true,[64,70,74,78],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"agents\u002Fopenai.yaml","REFERENCE","参考文档",385,"https:\u002F\u002Fgithub.com\u002Fopenplanr\u002FOpenPlanr\u002Fblob\u002Fmain\u002Fskills\u002Fplanr-operate\u002Fagents\u002Fopenai.yaml",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"openplanr.skill.json",908,"https:\u002F\u002Fgithub.com\u002Fopenplanr\u002FOpenPlanr\u002Fblob\u002Fmain\u002Fskills\u002Fplanr-operate\u002Fopenplanr.skill.json",{"path":75,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fnote-checklist.md",8015,"https:\u002F\u002Fgithub.com\u002Fopenplanr\u002FOpenPlanr\u002Fblob\u002Fmain\u002Fskills\u002Fplanr-operate\u002Freferences\u002Fnote-checklist.md",{"path":79,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Freturn-contract.md",676,"https:\u002F\u002Fgithub.com\u002Fopenplanr\u002FOpenPlanr\u002Fblob\u002Fmain\u002Fskills\u002Fplanr-operate\u002Freferences\u002Freturn-contract.md",[83,99,117,137,161,178],{"skillNo":84,"name":85,"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":86,"categories":87,"keywords":98,"publishedAt":35},"01M70XD1RYQC5160MRRCPTGA2K","design","https:\u002F\u002Fgithub.com\u002Fopenplanr\u002FOpenPlanr\u002Fblob\u002Fmain\u002Ftests\u002Frelease-train\u002Ffixtures\u002Ffigma\u002Fskills\u002Fdesign\u002FSKILL.md",[88,93],{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[85],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":35},"01M6J4V75T3VW91HJQ5ZD5SFW0","planr-sync","Audit OpenPlanr planning artifacts for graph and protocol drift. Use when statuses, references, schemas, or generated planning views may be inconsistent.","https:\u002F\u002Fgithub.com\u002Fopenplanr\u002FOpenPlanr\u002Fblob\u002Fmain\u002Fskills\u002Fplanr-sync\u002FSKILL.md",[],[106,107,108,109,110,111,112,113,114,115,33,30,116],"sync","planr sync","generated","when","graph","protocol","audit","references","drift","artifacts","planning",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":35},"01M6J4V38R89DYYA4AAN312MNZ","planr-status","Inspect project delivery or one feature's pipeline status without changing state. Use when the user asks what is done, pending, blocked, or next.","https:\u002F\u002Fgithub.com\u002Fopenplanr\u002FOpenPlanr\u002Fblob\u002Fmain\u002Fskills\u002Fplanr-status\u002FSKILL.md",[],[124,125,126,127,128,33,129,130,131,132,133,134,109,135,136],"status","planr status","next","state","done","inspect","pipeline","project","feature","delivery","pending","pipeline status","user",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":146,"publishedAt":35},"01M6J4TYGNBZG2YSSHCY8BASFB","planr-sprint","Refine every open backlog item against the code and the calendar, refute the picks, and select a sprint that fits capacity and the release cut. Use before a cut or sprint; not for decomposing one specification or reporting status.","https:\u002F\u002Fgithub.com\u002Fopenplanr\u002FOpenPlanr\u002Fblob\u002Fmain\u002Fskills\u002Fplanr-sprint\u002FSKILL.md",[143],{"categoryNo":144,"categoryName":145,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000030","开发工程师",[147,148,149,150,33,151,152,30,124,153,154,155,156,157,158,159,160],"planr sprint","sprint","release","capacity","release cut","backlog","refine","reporting","calendar","cut","specification","code","open","select",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":167,"publishedAt":35},"01M6J4TT7X6GV9A25JHSMKEMHJ","planr-spec","Shape vague product or engineering intent into a clear, measurable Protocol-compatible specification grounded in the current repository. Use when requirements need clarification before planning or implementation.","https:\u002F\u002Fgithub.com\u002Fopenplanr\u002FOpenPlanr\u002Fblob\u002Fmain\u002Fskills\u002Fplanr-spec\u002FSKILL.md",[],[168,169,170,33,116,171,172,109,173,174,111,175,176,27,177,157],"spec","planr spec","requirements","vague","engineering","implementation","clear","shape","repository","intent",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":184,"publishedAt":35},"01M6J4TNYE49SE8PBNNWJKK1CN","planr-ship","Implement an OpenPlanr plan, specification, task, or clearly stated request end to end in the current repository. Use when the user asks to build, implement, fix, finish, or ship local work, or to plan and implement an accepted change. Invoke before editing files for the requested change. Not for planning only, landing, release, or work handed to another coding agent.","https:\u002F\u002Fgithub.com\u002Fopenplanr\u002FOpenPlanr\u002Fblob\u002Fmain\u002Fskills\u002Fplanr-ship\u002FSKILL.md",[],[185,186,187,188,189,190,191,192,193,194,195,109,196,197,198,30,116,199,200,149,176,201,157,202],"ship","planr ship","local","only","end","fix","coding agent","work","plan","plan and implement","request","invoke","landing","editing","coding","finish","files","change"]