[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75Y2CDJ0VFM25RJEBWTK0DR":3,"skill-same:01M75Y2CDJ0VFM25RJEBWTK0DR":51},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":44},"01M75Y2CDJ0VFM25RJEBWTK0DR","discovery",null,"Run an optional guided product-discovery interview and draft project-plan.md and build-plan.md only after the user is ready. Use for \u002Fdiscovery, guided planning, thinking through a new product, or deepening plans. Never require it before \u002Foverview.","aiblueprinthq\u002Fai-blueprint","aiblueprinthq","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F317905365?v=4","01M75XZGKSB8GPVXQ69BA57VA7","01M75XZGME4HNZG9CDB8K3TQ8X",510,"MIT","https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fdiscovery\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: discovery\ndescription: Run an optional guided product-discovery interview and draft project-plan.md and build-plan.md only after the user is ready. Use for \u002Fdiscovery, guided planning, thinking through a new product, or deepening plans. Never require it before \u002Foverview.\ndisable-model-invocation: true\n---\n\n# discovery - develop the plans through a deep conversation\n\n**Context reuse:** Reuse any required file already loaded in project instructions or the current session. Read it again only if absent, changed, or exact current bytes or line references are needed.\n\n**First action:** Before project inspection, preflight, or any other tool call,\npublish `running` to `blueprint\u002F.state\u002Frun.json` when `blueprint\u002F.state\u002F`\nexists. From the project root, run the first helper that exists,\n`node .agents\u002Fskills\u002Fblueprint-doctor\u002Fscripts\u002Frun-state.mjs` or\n`node .claude\u002Fskills\u002Fblueprint-doctor\u002Fscripts\u002Frun-state.mjs`, with `start --command\n\u003Cskill> --summary \"\u003Ctruthful summary>\" --boundary\n\u003Cread-only|reviewed|local-only>`. Use `update` at milestones, with `--status\nblocked --resume \u003Ccommand>` for a blocker, and `finish --status ready|completed`\nat the end; `--help` lists every option and `blueprint\u002Fworkflow.md` has the full\nactivity contract. A missing or failing helper is a warning, not a blocker.\n\nWhere this can sit in the workflow:\n\n    \u002Fonboard  ->  write the plans directly  ->  \u002Foverview\n              \\\n               ->  [discovery]  ->  review and approve plan drafts  ->  \u002Foverview\n\n`\u002Fdiscovery` is an optional planning partner, not a required workflow gate and\nnot a quick questionnaire. It can span as many turns as the project needs. Its\njob is to help the user think through the product, preserve the depth and nuance\nof that conversation, and draft the two user-owned planning files only when the\nuser asks for drafts.\n\nRunning `\u002Fonboard` never starts this skill. Empty plans never require it. A user\nwho writes detailed plans manually, has another AI conversation, or arrives with\nfinished plans continues directly to `\u002Foverview` exactly as before.\n\nFor a focused idea or technical tradeoff without drafting plans, use `\u002Fexplore`.\nDiscovery develops the broader product plans.\n\n## Step 1 - establish the starting point\n\nRead only the planning and project facts needed for the conversation:\n\n- `blueprint\u002Fproject-plan.md`\n- `blueprint\u002Fbuild-plan.md`\n- the root project manifest, README, and framework configuration when they\n  already contain relevant facts\n- `blueprint\u002Fcontext\u002Fproject-overview.md` only when the user is revisiting an\n  established project's direction\n\nClassify each planning file as a template, partial draft, or substantive plan.\nNever treat existing user content as disposable. When either plan has real\ncontent, summarize what it already establishes and ask whether the user wants to\ndeepen it, revise a specific direction, or use it unchanged as conversation\ncontext. Do not replace it with a fresh generic plan.\n\nStart with a short working hypothesis about the project and name the most\nimportant unknown. Then ask one focused question. Do not draft either plan yet.\n\n## Step 2 - run adaptive discovery\n\nAsk one meaningful question at a time and let each answer shape the next one.\nPrefer a likely interpretation the user can correct over a vague request for\nmore detail. Explain a tradeoff when the answer would materially change scope,\narchitecture, cost, or build order.\n\nCover the areas that matter to this project, not a fixed questionnaire:\n\n- problem, desired outcome, and why the project should exist\n- target users, their context, and their primary workflows\n- MVP capabilities, explicit non-goals, and later possibilities\n- business rules, data, integrations, permissions, and important edge cases\n- stack choices, constraints, dependencies, and technical unknowns\n- UI\u002FUX direction, accessibility needs, and useful references\n- monetization or business model when relevant\n- deployment shape, environments, background work, storage, and operations\n- risks, assumptions, unresolved decisions, and how success will be judged\n- feature boundaries, dependencies, and a sensible build order\n\nDepth is the goal. Follow a consequential answer until its implications are\nclear instead of racing to the next category. Do not ask the user to repeat facts\nalready established in the conversation or repository. Do not force irrelevant\ntopics merely to complete a checklist.\n\nFollow the proportional-engineering contract in `AGENTS.md`: ask about optional\nusage or trust constraints only when they materially change the solution, record\nestablished non-requirements, and leave unknowns blank.\n\nPeriodically return a compact discovery snapshot with:\n\n- confirmed decisions\n- working assumptions that still need confirmation\n- open questions or conflicts\n- ideas explicitly deferred or excluded\n\nThe snapshot keeps a long conversation coherent. It is not permission to write\nthe plans.\n\n## Step 3 - decide whether the plans are ready\n\nDo not end discovery because a preset number of questions has been reached. It\nis ready to draft when:\n\n- the problem, users, and core workflows are concrete\n- MVP scope and non-goals are distinguishable\n- data and technical choices are detailed enough to expose major dependencies\n- the build order can be expressed as feature-sized outcomes\n- important contradictions are resolved\n- remaining unknowns are either safe to defer or explicitly accepted as TODOs\n- the user says they are ready for the plans to be drafted\n\nIf the user asks for drafts while a material gap remains, name the gap and ask\nwhether to continue discovery or preserve it as an explicit TODO. Respect the\nchoice. The user may also stop at any time and write the plans manually.\n\n## Step 4 - draft both planning files\n\nWhen the user asks for drafts, produce complete proposed contents for both files\nwithout writing them yet.\n\nFor `blueprint\u002Fproject-plan.md`:\n\n- keep the template's main subject areas, adding useful sections when the\n  conversation requires them\n- preserve rationale, examples, tradeoffs, constraints, edge cases, and\n  exclusions that will matter during later feature work\n- be as detailed as the project needs; never compress a rich discovery into a\n  line or two per section\n- distinguish confirmed decisions from assumptions and TODOs\n\nFor `blueprint\u002Fbuild-plan.md`:\n\n- use numbered checkboxes and optional milestone headings\n- keep each item a high-level, feature-sized outcome with a concise description\n- order items by dependency and the earliest useful vertical slice\n- keep implementation detail in later `\u002Ffeature` specs rather than turning the\n  roadmap into a task dump\n- include only agreed scope; place deferred ideas outside the MVP or omit them as\n  the user directed\n\nIf substantive plans already exist, preserve their information and completed\nbuild-plan numbering. Clearly identify proposed additions, removals, or changed\ndecisions.\n\nEnd by asking the user to review the full drafts. Do not write either file in the\nsame response that first presents them.\n\n## Step 5 - write only after approval\n\nWrite the approved drafts only after the user explicitly approves them. If the\nuser requests changes, revise the drafts and show the affected sections again\nbefore writing.\n\nAfter writing:\n\n- report which files changed\n- list any retained TODOs or unresolved decisions\n- remind the user that both files remain theirs to edit and deepen directly\n- stop before generating `blueprint\u002Fcontext\u002Fproject-overview.md`\n- point to `\u002Foverview` or `$overview` as the next optional command when the user\n  is satisfied with the plans\n\n## Rules\n\n- This skill is always optional. Never make it a prerequisite for `\u002Foverview`,\n  `\u002Ffeature`, or any other Blueprint command.\n- Never start it automatically from `\u002Fonboard`, because planning files are\n  empty, or because a project is new.\n- Never imply that plans created manually or through another conversation are\n  inferior or incomplete merely because this skill was not used.\n- Never overwrite substantive planning content without showing the replacement\n  and receiving explicit approval.\n- Never write plans during the interview or after a vague signal such as \"looks\n  good.\" The user must explicitly approve the proposed file contents.\n- Never scaffold the app, edit product code, generate the overview, create a\n  feature spec, commit, merge, push, or deploy.\n- Preserve detailed project reasoning in `project-plan.md`, while keeping\n  `build-plan.md` high-level and trackable.\n- Keep the conversation adaptive. Depth comes from relevant follow-up questions,\n  not from mechanically asking every possible question.\n\n## Formatting\n\nFollow `blueprint\u002Fcontext\u002Fai-interaction.md`. During discovery, ask one focused\nquestion per turn. For snapshots and draft reviews, use concise headings and\nlists so confirmed decisions and remaining gaps are easy to inspect.\n","# discovery - develop the plans through a deep conversation\n\n**Context reuse:** Reuse any required file already loaded in project instructions or the current session. Read it again only if absent, changed, or exact current bytes or line references are needed.\n\n**First action:** Before project inspection, preflight, or any other tool call,\npublish `running` to `blueprint\u002F.state\u002Frun.json` when `blueprint\u002F.state\u002F`\nexists. From the project root, run the first helper that exists,\n`node .agents\u002Fskills\u002Fblueprint-doctor\u002Fscripts\u002Frun-state.mjs` or\n`node .claude\u002Fskills\u002Fblueprint-doctor\u002Fscripts\u002Frun-state.mjs`, with `start --command\n\u003Cskill> --summary \"\u003Ctruthful summary>\" --boundary\n\u003Cread-only|reviewed|local-only>`. Use `update` at milestones, with `--status\nblocked --resume \u003Ccommand>` for a blocker, and `finish --status ready|completed`\nat the end; `--help` lists every option and `blueprint\u002Fworkflow.md` has the full\nactivity contract. A missing or failing helper is a warning, not a blocker.\n\nWhere this can sit in the workflow:\n\n    \u002Fonboard  ->  write the plans directly  ->  \u002Foverview\n              \\\n               ->  [discovery]  ->  review and approve plan drafts  ->  \u002Foverview\n\n`\u002Fdiscovery` is an optional planning partner, not a required workflow gate and\nnot a quick questionnaire. It can span as many turns as the project needs. Its\njob is to help the user think through the product, preserve the depth and nuance\nof that conversation, and draft the two user-owned planning files only when the\nuser asks for drafts.\n\nRunning `\u002Fonboard` never starts this skill. Empty plans never require it. A user\nwho writes detailed plans manually, has another AI conversation, or arrives with\nfinished plans continues directly to `\u002Foverview` exactly as before.\n\nFor a focused idea or technical tradeoff without drafting plans, use `\u002Fexplore`.\nDiscovery develops the broader product plans.\n\n## Step 1 - establish the starting point\n\nRead only the planning and project facts needed for the conversation:\n\n- `blueprint\u002Fproject-plan.md`\n- `blueprint\u002Fbuild-plan.md`\n- the root project manifest, README, and framework configuration when they\n  already contain relevant facts\n- `blueprint\u002Fcontext\u002Fproject-overview.md` only when the user is revisiting an\n  established project's direction\n\nClassify each planning file as a template, partial draft, or substantive plan.\nNever treat existing user content as disposable. When either plan has real\ncontent, summarize what it already establishes and ask whether the user wants to\ndeepen it, revise a specific direction, or use it unchanged as conversation\ncontext. Do not replace it with a fresh generic plan.\n\nStart with a short working hypothesis about the project and name the most\nimportant unknown. Then ask one focused question. Do not draft either plan yet.\n\n## Step 2 - run adaptive discovery\n\nAsk one meaningful question at a time and let each answer shape the next one.\nPrefer a likely interpretation the user can correct over a vague request for\nmore detail. Explain a tradeoff when the answer would materially change scope,\narchitecture, cost, or build order.\n\nCover the areas that matter to this project, not a fixed questionnaire:\n\n- problem, desired outcome, and why the project should exist\n- target users, their context, and their primary workflows\n- MVP capabilities, explicit non-goals, and later possibilities\n- business rules, data, integrations, permissions, and important edge cases\n- stack choices, constraints, dependencies, and technical unknowns\n- UI\u002FUX direction, accessibility needs, and useful references\n- monetization or business model when relevant\n- deployment shape, environments, background work, storage, and operations\n- risks, assumptions, unresolved decisions, and how success will be judged\n- feature boundaries, dependencies, and a sensible build order\n\nDepth is the goal. Follow a consequential answer until its implications are\nclear instead of racing to the next category. Do not ask the user to repeat facts\nalready established in the conversation or repository. Do not force irrelevant\ntopics merely to complete a checklist.\n\nFollow the proportional-engineering contract in `AGENTS.md`: ask about optional\nusage or trust constraints only when they materially change the solution, record\nestablished non-requirements, and leave unknowns blank.\n\nPeriodically return a compact discovery snapshot with:\n\n- confirmed decisions\n- working assumptions that still need confirmation\n- open questions or conflicts\n- ideas explicitly deferred or excluded\n\nThe snapshot keeps a long conversation coherent. It is not permission to write\nthe plans.\n\n## Step 3 - decide whether the plans are ready\n\nDo not end discovery because a preset number of questions has been reached. It\nis ready to draft when:\n\n- the problem, users, and core workflows are concrete\n- MVP scope and non-goals are distinguishable\n- data and technical choices are detailed enough to expose major dependencies\n- the build order can be expressed as feature-sized outcomes\n- important contradictions are resolved\n- remaining unknowns are either safe to defer or explicitly accepted as TODOs\n- the user says they are ready for the plans to be drafted\n\nIf the user asks for drafts while a material gap remains, name the gap and ask\nwhether to continue discovery or preserve it as an explicit TODO. Respect the\nchoice. The user may also stop at any time and write the plans manually.\n\n## Step 4 - draft both planning files\n\nWhen the user asks for drafts, produce complete proposed contents for both files\nwithout writing them yet.\n\nFor `blueprint\u002Fproject-plan.md`:\n\n- keep the template's main subject areas, adding useful sections when the\n  conversation requires them\n- preserve rationale, examples, tradeoffs, constraints, edge cases, and\n  exclusions that will matter during later feature work\n- be as detailed as the project needs; never compress a rich discovery into a\n  line or two per section\n- distinguish confirmed decisions from assumptions and TODOs\n\nFor `blueprint\u002Fbuild-plan.md`:\n\n- use numbered checkboxes and optional milestone headings\n- keep each item a high-level, feature-sized outcome with a concise description\n- order items by dependency and the earliest useful vertical slice\n- keep implementation detail in later `\u002Ffeature` specs rather than turning the\n  roadmap into a task dump\n- include only agreed scope; place deferred ideas outside the MVP or omit them as\n  the user directed\n\nIf substantive plans already exist, preserve their information and completed\nbuild-plan numbering. Clearly identify proposed additions, removals, or changed\ndecisions.\n\nEnd by asking the user to review the full drafts. Do not write either file in the\nsame response that first presents them.\n\n## Step 5 - write only after approval\n\nWrite the approved drafts only after the user explicitly approves them. If the\nuser requests changes, revise the drafts and show the affected sections again\nbefore writing.\n\nAfter writing:\n\n- report which files changed\n- list any retained TODOs or unresolved decisions\n- remind the user that both files remain theirs to edit and deepen directly\n- stop before generating `blueprint\u002Fcontext\u002Fproject-overview.md`\n- point to `\u002Foverview` or `$overview` as the next optional command when the user\n  is satisfied with the plans\n\n## Rules\n\n- This skill is always optional. Never make it a prerequisite for `\u002Foverview`,\n  `\u002Ffeature`, or any other Blueprint command.\n- Never start it automatically from `\u002Fonboard`, because planning files are\n  empty, or because a project is new.\n- Never imply that plans created manually or through another conversation are\n  inferior or incomplete merely because this skill was not used.\n- Never overwrite substantive planning content without showing the replacement\n  and receiving explicit approval.\n- Never write plans during the interview or after a vague signal such as \"looks\n  good.\" The user must explicitly approve the proposed file contents.\n- Never scaffold the app, edit product code, generate the overview, create a\n  feature spec, commit, merge, push, or deploy.\n- Preserve detailed project reasoning in `project-plan.md`, while keeping\n  `build-plan.md` high-level and trackable.\n- Keep the conversation adaptive. Depth comes from relevant follow-up questions,\n  not from mechanically asking every possible question.\n\n## Formatting\n\nFollow `blueprint\u002Fcontext\u002Fai-interaction.md`. During discovery, ask one focused\nquestion per turn. For snapshots and draft reviews, use concise headings and\nlists so confirmed decisions and remaining gaps are easy to inspect.\n",{"name":5,"description":7,"disable-model-invocation":23},true,"main","483eb73dbc58a4b82a5642f864ea7569af947e39",".claude\u002Fskills\u002Fdiscovery",132,"https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint","https:\u002F\u002Fai-blueprint.dev","https:\u002F\u002Fgithub.com\u002Faiblueprinthq","2026-11-14 19:46:05",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":23},[34,37,40],{"tool":35,"command":36},"npx","npx skills add aiblueprinthq\u002Fai-blueprint --skill discovery",{"tool":38,"command":39},"bunx","bunx skills add aiblueprinthq\u002Fai-blueprint --skill discovery",{"tool":41,"command":42},"pnpm","pnpm dlx skills add aiblueprinthq\u002Fai-blueprint --skill discovery","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fdiscovery\u002FSKILL.md",[45],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"agents\u002Fopenai.yaml","REFERENCE","参考文档",234,"https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fdiscovery\u002Fagents\u002Fopenai.yaml",[52,58,63,70,77,84],{"skillNo":53,"name":54,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M75Y34X26C74A66RYE49W8JY","status","https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint\u002Fblob\u002Fmain\u002Fpackages\u002Fcreate-ai-blueprint\u002Ftest\u002Ffixtures\u002Fhealthy-blueprint\u002F.claude\u002Fskills\u002Fstatus\u002FSKILL.md",[],[],{"skillNo":59,"name":54,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":18},"01M75Y3456H4WZZ25634QY9KRA","https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint\u002Fblob\u002Fmain\u002Fpackages\u002Fcreate-ai-blueprint\u002Ftest\u002Ffixtures\u002Fhealthy-blueprint\u002F.agents\u002Fskills\u002Fstatus\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":18},"01M75Y31WCYVFM5M4NH7D9MRMW","tests","Set up unit testing with \u002Ftests or \u002Ftests unit, or explicitly set up browser and end-to-end testing with \u002Ftests browser. Reuse or install a suitable test runner, add one example or smoke test, document commands, and verify. Use check for one-time live verification.","https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftests\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":18},"01M75Y2ZETQZEHN2V19HWZBB1R","prototype","Plan and create throwaway static HTML and CSS mockups with shared design tokens before feature implementation. Use for \u002Fprototype, screen mockups, layout exploration, themes, or deciding a project's look and feel.","https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fprototype\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":18},"01M75Y2WY81F9N40G2RADX2FKH","overview","Validate and normalize project-plan.md and build-plan.md, then generate the durable project-overview.md used by agents. Use for \u002Foverview, plan cleanup, generating the first overview, or refreshing context after either plan changes.","https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Foverview\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":18},"01M75Y2SNF3FZJP3NHRT0B5MQE","onboard","Onboard a fresh or early scaffold after Blueprint is overlaid by tuning commands, standards, adapters, visibility, and context loading. Use for \u002Fonboard, fresh installation setup, or what to do after installing Blueprint. Use adopt for an established app.","https:\u002F\u002Fgithub.com\u002Faiblueprinthq\u002Fai-blueprint\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fonboard\u002FSKILL.md",[],[]]