[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78KXQEFDR6GTSG3S3FVP4B3":3,"skill-same:01M78KXQEFDR6GTSG3S3FVP4B3":62},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":13,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M78KXQEFDR6GTSG3S3FVP4B3","walk",null,"Measures a product from its users' purposes instead of its own feature list — a blind setter (a separate, tool-less model call that sees only what the project says it is for) writes personas and missions, an independent walker subagent tries each mission and its variations on the running product as that person would, and every finding is routed to an issue draft, the roadmap, the stage parking lot, or the owner. Changes no product code.","iyulab\u002Fclaude-plugins","iyulab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F52388508?v=4","01M6C4JT2KEXFSG8YWSMFYT0NQ","01M6C4JT8BEJCZ0VPCC69N9JDN",0,"MIT","https:\u002F\u002Fgithub.com\u002Fiyulab\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fiyu\u002Fskills\u002Fwalk\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: walk\ndescription: Measures a product from its users' purposes instead of its own feature list — a blind setter (a separate, tool-less model call that sees only what the project says it is for) writes personas and missions, an independent walker subagent tries each mission and its variations on the running product as that person would, and every finding is routed to an issue draft, the roadmap, the stage parking lot, or the owner. Changes no product code.\nargument-hint: \"[--reset] [--all] [mission ids]\"\ndisable-model-invocation: true\nallowed-tools: Read, Glob, Grep, Write, Edit, Bash, Agent\n---\n\n# Walk — try the product the way its users would\n\nThe point is order: **fix what people come to do before looking at what the product does**, then\nfind out whether they can do it. Missions, the blind setter, field ownership and where findings go:\n**[missions.md](${CLAUDE_SKILL_DIR}\u002F..\u002F_shared\u002Fmissions.md)** — read it first.\n\n## Process\n\n### 1. Resolve and decide what to walk\n\nResolve `\u003Croot>` ([continuity-docs.md](${CLAUDE_SKILL_DIR}\u002F..\u002F_shared\u002Fcontinuity-docs.md) §1).\n\n- **No `\u003Croot>\u002Fmissions\u002Fmissions.json`, or `--reset`** → set missions first (step 2).\n- **Otherwise** → walk: the ids in `$ARGUMENTS`; with `--all`, every `active` mission; with neither,\n  the `active` missions whose `walked.build` is not the current build, plus those passing through\n  what changed since their last walk (missions.md §10).\n\n### 2. Set missions — blind\n\n1. **Gather the purpose material and nothing else** (missions.md §2): quote it verbatim with its\n   source path into `\u003Croot>\u002Fmissions\u002Fpurpose.md`. With a stage contract, its `goal` comes first. If\n   the project states no purpose anywhere — no contract goal, no README or scope document that says\n   what it is for and for whom — stop: say what is missing and that `\u002Fiyu:charter` or a README\n   opening would supply it. Do not write a purpose yourself.\n2. **Run the setter**: `sh \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fset-missions.sh\"\n   \"${CLAUDE_SKILL_DIR}\u002Freferences\u002Fsetter.md\" \u003Croot>\u002Fmissions\u002Fpurpose.md \u003Ca temp file>`. Exit `2`\n   means no JSON came back — run it once more, then stop and report. Do not write missions yourself\n   or ask a subagent to: either would see the code.\n3. **Record verbatim** into `missions.json` (schema in missions.md §4): personas and missions as\n   returned, adding only `id`, `set`, `state: active`, variation objects with `verdict: null`, and a\n   `set` entry with the current commit. With `--reset`, mark every earlier mission `retired` first.\n   Show the user the personas and mission goals in a short list, and the setter's `unclear` lines.\n\n### 3. Walk — independent\n\nPick `NN`, the next unused walk number. Dispatch **one** `Agent` call (`subagent_type:\ngeneral-purpose`) whose prompt is the full text of\n[references\u002Fwalker.md](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fwalker.md) followed by absolute paths to\n`missions.json` and `\u003Croot>\u002Fmissions\u002Fwalks\u002F`, the walk number, the missions to walk, the surface, and\nthe command that builds and starts the product (the stage contract's `run`, else the project's\ndocumented one, else \"none\"). Pass nothing about how the product is built inside.\n\n### 4. Route — every finding has somewhere to go\n\nRead the report. Only now compare it with the project's own records: the stage contract and its\nnon-goals, `parking.md`, `ROADMAP.md`, the issue drafts. Route each finding by missions.md §7 —\nwrite the issue drafts, the `ROADMAP.md` phases with their self-decision record, the `parking.md`\nlines — and fill the report's `## Routing`: each finding's route, and the mission × stage map\n(missions.md §8).\n\n### 5. Report\n\nA few lines: verdict counts, the findings by type with where each went, what was `unverified` and\nwhy, and the mission concerns. Name what the owner should look at — only the routes that need them.\n\n## Standing rules\n\n- **No product code changes.** Defects go to issue drafts; building is `drive`'s or `run-cycle`'s.\n- **The setter's text and the walker's verdicts are theirs** (missions.md §5). This skill copies,\n  numbers, routes — it does not reword a mission or reconsider a verdict.\n- **A walk is a heavy verification.** Walk only what step 1 selected; `--all` is for a stage boundary,\n  a release, a changed purpose, or when asked.\n- Output language: [continuity-docs.md](${CLAUDE_SKILL_DIR}\u002F..\u002F_shared\u002Fcontinuity-docs.md) §5.\n","# Walk — try the product the way its users would\n\nThe point is order: **fix what people come to do before looking at what the product does**, then\nfind out whether they can do it. Missions, the blind setter, field ownership and where findings go:\n**[missions.md](${CLAUDE_SKILL_DIR}\u002F..\u002F_shared\u002Fmissions.md)** — read it first.\n\n## Process\n\n### 1. Resolve and decide what to walk\n\nResolve `\u003Croot>` ([continuity-docs.md](${CLAUDE_SKILL_DIR}\u002F..\u002F_shared\u002Fcontinuity-docs.md) §1).\n\n- **No `\u003Croot>\u002Fmissions\u002Fmissions.json`, or `--reset`** → set missions first (step 2).\n- **Otherwise** → walk: the ids in `$ARGUMENTS`; with `--all`, every `active` mission; with neither,\n  the `active` missions whose `walked.build` is not the current build, plus those passing through\n  what changed since their last walk (missions.md §10).\n\n### 2. Set missions — blind\n\n1. **Gather the purpose material and nothing else** (missions.md §2): quote it verbatim with its\n   source path into `\u003Croot>\u002Fmissions\u002Fpurpose.md`. With a stage contract, its `goal` comes first. If\n   the project states no purpose anywhere — no contract goal, no README or scope document that says\n   what it is for and for whom — stop: say what is missing and that `\u002Fiyu:charter` or a README\n   opening would supply it. Do not write a purpose yourself.\n2. **Run the setter**: `sh \"${CLAUDE_SKILL_DIR}\u002Fscripts\u002Fset-missions.sh\"\n   \"${CLAUDE_SKILL_DIR}\u002Freferences\u002Fsetter.md\" \u003Croot>\u002Fmissions\u002Fpurpose.md \u003Ca temp file>`. Exit `2`\n   means no JSON came back — run it once more, then stop and report. Do not write missions yourself\n   or ask a subagent to: either would see the code.\n3. **Record verbatim** into `missions.json` (schema in missions.md §4): personas and missions as\n   returned, adding only `id`, `set`, `state: active`, variation objects with `verdict: null`, and a\n   `set` entry with the current commit. With `--reset`, mark every earlier mission `retired` first.\n   Show the user the personas and mission goals in a short list, and the setter's `unclear` lines.\n\n### 3. Walk — independent\n\nPick `NN`, the next unused walk number. Dispatch **one** `Agent` call (`subagent_type:\ngeneral-purpose`) whose prompt is the full text of\n[references\u002Fwalker.md](${CLAUDE_SKILL_DIR}\u002Freferences\u002Fwalker.md) followed by absolute paths to\n`missions.json` and `\u003Croot>\u002Fmissions\u002Fwalks\u002F`, the walk number, the missions to walk, the surface, and\nthe command that builds and starts the product (the stage contract's `run`, else the project's\ndocumented one, else \"none\"). Pass nothing about how the product is built inside.\n\n### 4. Route — every finding has somewhere to go\n\nRead the report. Only now compare it with the project's own records: the stage contract and its\nnon-goals, `parking.md`, `ROADMAP.md`, the issue drafts. Route each finding by missions.md §7 —\nwrite the issue drafts, the `ROADMAP.md` phases with their self-decision record, the `parking.md`\nlines — and fill the report's `## Routing`: each finding's route, and the mission × stage map\n(missions.md §8).\n\n### 5. Report\n\nA few lines: verdict counts, the findings by type with where each went, what was `unverified` and\nwhy, and the mission concerns. Name what the owner should look at — only the routes that need them.\n\n## Standing rules\n\n- **No product code changes.** Defects go to issue drafts; building is `drive`'s or `run-cycle`'s.\n- **The setter's text and the walker's verdicts are theirs** (missions.md §5). This skill copies,\n  numbers, routes — it does not reword a mission or reconsider a verdict.\n- **A walk is a heavy verification.** Walk only what step 1 selected; `--all` is for a stage boundary,\n  a release, a changed purpose, or when asked.\n- Output language: [continuity-docs.md](${CLAUDE_SKILL_DIR}\u002F..\u002F_shared\u002Fcontinuity-docs.md) §5.\n",{"name":5,"description":7,"allowed-tools":23,"argument-hint":24,"disable-model-invocation":25},"Read, Glob, Grep, Write, Edit, Bash, Agent","[--reset] [--all] [mission ids]",true,"main","7edf5451517425157f96c10c6c52925035f73c31","plugins\u002Fiyu\u002Fskills\u002Fwalk","https:\u002F\u002Fgithub.com\u002Fiyulab\u002Fclaude-plugins","https:\u002F\u002Fgithub.com\u002Fiyulab","www.iyulab.com","2026-11-14 12:28:05",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add iyulab\u002Fclaude-plugins --skill walk",{"tool":39,"command":40},"bunx","bunx skills add iyulab\u002Fclaude-plugins --skill walk",{"tool":42,"command":43},"pnpm","pnpm dlx skills add iyulab\u002Fclaude-plugins --skill walk","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fiyulab\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fiyu\u002Fskills\u002Fwalk\u002FSKILL.md",[46,52,56],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fsetter.md","REFERENCE","参考文档",3164,"https:\u002F\u002Fgithub.com\u002Fiyulab\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fiyu\u002Fskills\u002Fwalk\u002Freferences\u002Fsetter.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fwalker.md",5014,"https:\u002F\u002Fgithub.com\u002Fiyulab\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fiyu\u002Fskills\u002Fwalk\u002Freferences\u002Fwalker.md",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"scripts\u002Fset-missions.sh","SCRIPT","脚本",3434,"https:\u002F\u002Fgithub.com\u002Fiyulab\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fiyu\u002Fskills\u002Fwalk\u002Fscripts\u002Fset-missions.sh",[63,90,108,127,161,182],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":89},"01M6WKK4AZHX2ERR9RW97WX0BN","drive","Pushes the open stage of a product to its agreed satisfaction bar — implement one failing scenario at a time, have an independent evaluator judge the running build, repeat until the stage passes or needs something only the owner can supply, then show the owner a demo. Use after `\u002Fiyu:charter` has a signed stage contract.","https:\u002F\u002Fgithub.com\u002Fiyulab\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fiyu\u002Fskills\u002Fdrive\u002FSKILL.md",[],[65,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88],"supply","running","show","time","failing","true","open","contract","only","use","stage","Bash","websearch","implement","can","task","demo","id","product","2026-11-10 10:12:30",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":89},"01M6WKK02K2DQYHRR9KKY8C522","charter","Interviews the owner to set a product's goal and writes the stage contract — an ordered ladder of stages that each work on their own, with scenarios an observer can watch, a calibrated satisfaction bar, the promises each stage must keep, and every owner decision that could block it. Use before `\u002Fiyu:drive`, and again at each stage boundary.","https:\u002F\u002Fgithub.com\u002Fiyulab\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fiyu\u002Fskills\u002Fcharter\u002FSKILL.md",[],[92,97,98,99,100,101,102,75,76,77,103,79,80,104,81,82,84,105,106,107],"SET","promises","scope","re","work on","decision","observer","keep","with","work","boundary",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":89},"01M6WKJKPMSG3MPR0CZQZ9MVG1","accept","Judges the open stage by having an independent evaluator subagent drive the real, running build like a user — scenario by scenario, against the rubric — and record an evidence report and the status fields. Use to get a verdict without building anything; `\u002Fiyu:drive` dispatches the same evaluator each round.","https:\u002F\u002Fgithub.com\u002Fiyulab\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fiyu\u002Fskills\u002Faccept\u002FSKILL.md",[],[110,71,115,116,117,75,76,79,80,81,118,87,119,120,121,122,123,124,125,126],"evidence","smoke","get","subagent","record","verdict","build","read","report","rubric","grep","status",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":143,"publishedAt":89},"01M6C4KKDYZE639N931JNRYZEY","telemetry-az","Analyzes Azure Application Insights telemetry since the last run to surface defects, performance regressions, and feature-drop signals, tracked run-over-run as a quality trend (error-rate\u002Fp95\u002Fissue-count direction, with closed-issue recurrence detection), plus a report-only user-analytics reading (active-user growth, feature\u002Fpage preference shifts, engagement). Triages findings against project philosophy, files issues only for threshold-crossing ones, and leads every report with a both-purpose Trend section backed by a 12-run history.","https:\u002F\u002Fgithub.com\u002Fiyulab\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fiyu\u002Fskills\u002Ftelemetry-az\u002FSKILL.md",[133,138],{"categoryNo":134,"categoryName":135,"taxonomyType":136,"taxonomyTypeDesc":137},"01JBSEEDCAT000000000000013","分析与可视化","SCENARIO","使用场景",{"categoryNo":139,"categoryName":140,"taxonomyType":141,"taxonomyTypeDesc":142},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[144,145,146,147,148,78,81,149,150,151,152,153,154,155,156,157,158,82,159,160],"telemetry","telemetry az","performance","up","issues","analyze","error","app","direction","project","trending","insights","files","when","drop","dry","philosophy",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":167,"publishedAt":89},"01M6C4KGM2AA9JXQNHB7MW8JJ1","ship","Takes finished work out — bumps the version, commits, pushes, and watches the CI run to completion, reporting what failed if it fails. Checks first whether now is the right moment — if remaining backlog work would touch the same consumer-facing surface, it says so and asks rather than publishing a version the next few items obsolete.","https:\u002F\u002Fgithub.com\u002Fiyulab\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fiyu\u002Fskills\u002Fship\u002FSKILL.md",[],[163,168,169,170,171,172,78,79,173,81,174,175,176,106,177,178,179,122,180,181],"ready","push","commits","ci","publishing","version","patch","commit","publish","first","cicd","run","reporting","edit",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":188,"publishedAt":89},"01M6C4KD17SZCFRPYD3Q45XKAG","run-cycle","Executes adaptive iterative development cycles — each cycle is a self-contained plan\u002Fexecute\u002Fverify\u002Freflect loop that reshapes the roadmap and derives emergent follow-on scope from its own output","https:\u002F\u002Fgithub.com\u002Fiyulab\u002Fclaude-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fiyu\u002Fskills\u002Frun-cycle\u002FSKILL.md",[],[189,179,190,191,192,193,194,81,195,196,197,122,198,181,99,82,199,200,201,202],"run cycle","cycle","development","iterative development","loop","roadmap","reflect","plan","command","write","self","scripts","stop","adaptive"]