[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E7MXADB11PD3BCH3BKB4K7":3,"skill-same:01M7E7MXADB11PD3BCH3BKB4K7":83},{"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":34,"commitSha":35,"skillDirectory":36,"forksCount":14,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":40,"updatedAt":41,"install":42,"resources":54},"01M7E7MXADB11PD3BCH3BKB4K7","business-case-study-internal",null,"Use when writing a tier-2 internal case study from a business-value run: tagged outcomes, lessons, and a replication guide for other teams.","tony\u002Fskills","tony","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F26336?v=4","01M72E5RNJ7SQV8F9KBM5RKRMN","Tony Narlock","01M7E7MBN5C6YZ4JJJ5Y82KBJG",0,"MIT","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbusiness-case-study-internal\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: business-case-study-internal\ndescription: >-\n  Use when writing a tier-2 internal case study from a business-value run:\n  tagged outcomes, lessons, and a replication guide for other teams.\ndisable-model-invocation: true\nallowed-tools: [\"Bash\", \"Read\", \"Write\", \"Grep\", \"AskUserQuestion\"]\nmetadata:\n  argument-hint: \"[run directory]\"\n  source: \"plugins\u002Fbusiness\u002Fskills\u002Fcase-study-internal\u002FSKILL.md\"\n---\n\n# Internal Case Study (tier 2)\n\nTurn a run package into a narrative case study for internal\ncirculation: what happened, what it measured, what other teams can\ntake from it. The tier-2 contract is in `audiences.md`.\n\nRead `references\u002Finterim-format.md` first. It defines the run\nlocation, the completeness gate, and the output frame. Defer these\nuntil the gate passes:\n\n- `references\u002Fprovenance.md`\n- `references\u002Faudiences.md`: the tier-2 contract.\n\nUser arguments: $ARGUMENTS\n\n## Procedure\n\n### 1. Locate the run and pass the gate\n\nPer `interim-format.md` § Rendering a report. When the request names a\nworkflow, take the first line of `runs --workflow \u003Cslug>` as the run.\n\n### 2. Ask for what the run package lacks\n\nThe run package holds no maintainer, no lessons, and no replication\nnotes, and may hold no build time. With a question tool, ask the user\nonce, in one batch (`ask-user-choice`), for: the maintainer's role, the\nbuild time if `build-hours` is not registered, what worked and what did\nnot, and what the team would change. Record the answers in\n`findings.md` under a `## User-supplied context` heading, with a\nbuild time also appended to `assumptions.yaml` as an ESTIMATED entry\n(`provenance.md`); then run `business.py gate \u003Crun>` again. Name a\nperson only as a role. Without a question tool, or without an answer, write\neach such part as unknown with the data that would resolve it.\n\n### 3. Render the case study\n\nWrite `\u003Crun>\u002Freports\u002Fcase-study-internal.md` as a narrative in this\nfixed order:\n\n1. Situation: the team, the recurring task, why it cost enough\n   to act on.\n2. What was built: the skill or workflow, its build time\n   (tagged), and who maintains it.\n3. Measured outcomes: every figure tagged, denominator stated,\n   window pinned. Include the costs: verification time, failed\n   runs, maintenance.\n4. Lessons: what worked, what did not, what the team would do\n   differently.\n5. How other teams can replicate: prerequisites, the expected\n   ramp (and the excluded novelty window), and where results are\n   likely to differ.\n\nTake every item from the run package or the user's answers; a part\nneither holds is written as unknown with the data that would resolve\nit, never supplied from inference.\n\nWrite it per `references\u002Fprose-rules.md`.\n\nThen scan for individuals with `references\u002Fbusiness.py scan --run \u003Crun>\n--tier 2 \u003Crun>\u002Freports\u002Fcase-study-internal.md` (absolute path); it reads the README\n`People:` line and reports each name; rewrite it as a role, since tier 2\nallows roles only. Then run steps 4 and 5 of `interim-format.md` § Rendering\na report: the money check, then `stamp`.\n\n## Output\n\nHero success form: `✓ Case study: \u003Cone-line outcome with tag>`.\nSections and stopped-run shape as in `interim-format.md`. Panel options: write the public\ncase study next (read the `business-case-study-public` skill and follow it),\nadjust the narrative, or stop.\n\n\n## Portability notes\n\n- `ask-user-choice` — present the listed options and wait for the user to pick one. Hosts with a structured multiple-choice tool (Claude Code's `AskUserQuestion`) should use it; otherwise print a numbered list and wait for a numbered reply. Never proceed on an assumed answer.\n- `$ARGUMENTS` — the text the user passed when invoking this skill. If your host does not substitute it, read it as the user's request in the current turn, and ask when there is none.\n- Bundled files — every relative path in this skill points at a file shipped inside this skill directory. Read them from here, not from the host's plugin tree.\n","# Internal Case Study (tier 2)\n\nTurn a run package into a narrative case study for internal\ncirculation: what happened, what it measured, what other teams can\ntake from it. The tier-2 contract is in `audiences.md`.\n\nRead `references\u002Finterim-format.md` first. It defines the run\nlocation, the completeness gate, and the output frame. Defer these\nuntil the gate passes:\n\n- `references\u002Fprovenance.md`\n- `references\u002Faudiences.md`: the tier-2 contract.\n\nUser arguments: $ARGUMENTS\n\n## Procedure\n\n### 1. Locate the run and pass the gate\n\nPer `interim-format.md` § Rendering a report. When the request names a\nworkflow, take the first line of `runs --workflow \u003Cslug>` as the run.\n\n### 2. Ask for what the run package lacks\n\nThe run package holds no maintainer, no lessons, and no replication\nnotes, and may hold no build time. With a question tool, ask the user\nonce, in one batch (`ask-user-choice`), for: the maintainer's role, the\nbuild time if `build-hours` is not registered, what worked and what did\nnot, and what the team would change. Record the answers in\n`findings.md` under a `## User-supplied context` heading, with a\nbuild time also appended to `assumptions.yaml` as an ESTIMATED entry\n(`provenance.md`); then run `business.py gate \u003Crun>` again. Name a\nperson only as a role. Without a question tool, or without an answer, write\neach such part as unknown with the data that would resolve it.\n\n### 3. Render the case study\n\nWrite `\u003Crun>\u002Freports\u002Fcase-study-internal.md` as a narrative in this\nfixed order:\n\n1. Situation: the team, the recurring task, why it cost enough\n   to act on.\n2. What was built: the skill or workflow, its build time\n   (tagged), and who maintains it.\n3. Measured outcomes: every figure tagged, denominator stated,\n   window pinned. Include the costs: verification time, failed\n   runs, maintenance.\n4. Lessons: what worked, what did not, what the team would do\n   differently.\n5. How other teams can replicate: prerequisites, the expected\n   ramp (and the excluded novelty window), and where results are\n   likely to differ.\n\nTake every item from the run package or the user's answers; a part\nneither holds is written as unknown with the data that would resolve\nit, never supplied from inference.\n\nWrite it per `references\u002Fprose-rules.md`.\n\nThen scan for individuals with `references\u002Fbusiness.py scan --run \u003Crun>\n--tier 2 \u003Crun>\u002Freports\u002Fcase-study-internal.md` (absolute path); it reads the README\n`People:` line and reports each name; rewrite it as a role, since tier 2\nallows roles only. Then run steps 4 and 5 of `interim-format.md` § Rendering\na report: the money check, then `stamp`.\n\n## Output\n\nHero success form: `✓ Case study: \u003Cone-line outcome with tag>`.\nSections and stopped-run shape as in `interim-format.md`. Panel options: write the public\ncase study next (read the `business-case-study-public` skill and follow it),\nadjust the narrative, or stop.\n\n\n## Portability notes\n\n- `ask-user-choice` — present the listed options and wait for the user to pick one. Hosts with a structured multiple-choice tool (Claude Code's `AskUserQuestion`) should use it; otherwise print a numbered list and wait for a numbered reply. Never proceed on an assumed answer.\n- `$ARGUMENTS` — the text the user passed when invoking this skill. If your host does not substitute it, read it as the user's request in the current turn, and ask when there is none.\n- Bundled files — every relative path in this skill points at a file shipped inside this skill directory. Read them from here, not from the host's plugin tree.\n",{"name":5,"metadata":24,"description":7,"allowed-tools":27,"disable-model-invocation":33},{"source":25,"argument-hint":26},"plugins\u002Fbusiness\u002Fskills\u002Fcase-study-internal\u002FSKILL.md","[run directory]",[28,29,30,31,32],"Bash","Read","Write","Grep","AskUserQuestion",true,"main","5fbeb3b47beedea13813be7b7023f736a8d97a65",".agents\u002Fskills\u002Fbusiness-case-study-internal","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills","https:\u002F\u002Fgithub.com\u002Ftony","https:\u002F\u002Ftony.sh","lighthouse keeper","2026-11-08 17:57:34",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":33},[44,47,50],{"tool":45,"command":46},"npx","npx skills add tony\u002Fskills --skill business-case-study-internal",{"tool":48,"command":49},"bunx","bunx skills add tony\u002Fskills --skill business-case-study-internal",{"tool":51,"command":52},"pnpm","pnpm dlx skills add tony\u002Fskills --skill business-case-study-internal","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbusiness-case-study-internal\u002FSKILL.md",[55,61,65,71,75,79],{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"agents\u002Fopenai.yaml","REFERENCE","参考文档",306,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbusiness-case-study-internal\u002Fagents\u002Fopenai.yaml",{"path":62,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Faudiences.md",6056,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbusiness-case-study-internal\u002Freferences\u002Faudiences.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fbusiness.py","SCRIPT","脚本",80988,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbusiness-case-study-internal\u002Freferences\u002Fbusiness.py",{"path":72,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Finterim-format.md",14571,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbusiness-case-study-internal\u002Freferences\u002Finterim-format.md",{"path":76,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fprose-rules.md",4644,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbusiness-case-study-internal\u002Freferences\u002Fprose-rules.md",{"path":80,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fprovenance.md",4425,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbusiness-case-study-internal\u002Freferences\u002Fprovenance.md",[84,91,98,105,112,119],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7E8NCSHXV2JPW4J61R0TQS7","serene-bliss","Use when asked to make a CLI --help, docs page, error message, or tooling UX more serene or calmer for developer experience; returns text, no edits.","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fserene-bliss\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7E8N87MAVJD8RRQKQB1ZPS6","review","Weave code review: run independent adversarial reviews in parallel, then synthesize findings","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"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":104,"publishedAt":19},"01M7E8N402XG4ZBFNACQ413163","refine","Use when asked to refine a draft, iterate on code until cleaner, or polish a README through repeated critique and improvement.","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Frefine\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M7E8N01KB86A7136P00GVKJW","prompt","Weave prompt: compare independent adversarial implementations, then adopt the single best one","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fprompt\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":19},"01M7E8MW7YJW2PCMDW3G9RTGNK","plan","Weave planning: compare independent adversarial plans, then synthesize the best one","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fplan\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":19},"01M7E8MSBYXNCV4ZYWDS4PFJXK","fix-review","Fix weave review findings: validate, add test coverage, fix, and commit each as atomic changes","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Ffix-review\u002FSKILL.md",[],[]]