[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77MPWADHF8Z5DEMRK2PBGZ9":3,"skill-same:01M77MPWADHF8Z5DEMRK2PBGZ9":45},{"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M77MPWADHF8Z5DEMRK2PBGZ9","impl-screen-specs",null,"Generate the SCREEN_SPECS manifest — a per-screen specification (components, data, API calls, user actions, states, i18n). Optional tool a developer may use anytime to blueprint screens; not required before code (TASK-230, 2026-09-16 human decision). Vendored Spine skill; see src\u002Fmanifest-policy.js.","HexingBot\u002Fhivemind","HexingBot","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F296674764?v=4","01M77MMXMW5SWSXKHB0VA4N1FF","01M77MMXNV3PZA3795D6PYX5C9",1,"MIT","https:\u002F\u002Fgithub.com\u002FHexingBot\u002Fhivemind\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimpl-screen-specs\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: impl-screen-specs\ndescription: Generate the SCREEN_SPECS manifest — a per-screen specification (components, data, API calls, user actions, states, i18n). Optional tool a developer may use anytime to blueprint screens; not required before code (TASK-230, 2026-09-16 human decision). Vendored Spine skill; see src\u002Fmanifest-policy.js.\n---\n\n## Sources & manifest status (hivemind)\n\nVendored from implementation-engine. In hivemind the \"context\" this skill reads is the project's\nknowledge surface — `PROJECT.md`, the wisearcher brain graph (`kb_search`\u002F`kb_answer`, or the local\n`knowledge\u002F` KB when the brain is offline), and the ticket's scope + acceptance criteria. Where the\nbody below refers to `context\u002F\u003Cfile>.md`, read the equivalent from that surface. Output goes to\n`implementation\u002FSCREEN_SPECS.md`.\n\n**Status (TASK-230, 2026-09-16 human decision):** optional tool, not a gate. No `verification_tier`\nrequires this manifest before code — see `src\u002Fmanifest-policy.js` (`requiresManifest` always returns\n`false`). Generate\u002Fupdate it whenever it helps, in whatever order the Developer chooses; the\nreviewer does NOT treat a missing manifest as a finding. Preserve epistemic markers\n(`[EXPLICIT]`\u002F`[INFERRED:strong|weak]`\u002F`[ASSUMED]`) and respect source tiers.\n\n---\n\n# impl-screen-specs\n\nGenerates `implementation\u002FSCREEN_SPECS.md` — a per-screen specification covering every screen in the project scope.\n\n## Read first\n\nRead these files from `context\u002F` (and only from `context\u002F`):\n- `context\u002Fscope.md` — identifies all scope items (S-##) and their feature areas\n- `context\u002Ftechnical.md` — navigation structure, architecture patterns, component conventions\n- `context\u002Fexecution.md` — phase assignments per feature area\n\n## Output: `implementation\u002FSCREEN_SPECS.md`\n\nWrite one entry per screen. Derive the screen list from the scope items (S-AUTH, S-HOME, S-CAMP, S-WORK, S-CHAT, S-PROF, S-SET, S-PAY, S-REP) and expand each into its constituent screens.\n\n### Format for each screen\n\n```markdown\n## \u003CScreen Name>\n\n**Scope item**: S-##\n**Phase**: P#\n**Navigation path**: \u003Ctab> → \u003Cstack position>  (e.g., Campaigns tab → Campaign Detail)\n\n### Components\n- \u003CCanonical component name from COMPONENT_CATALOG>: \u003Cbrief purpose>\n  (reference catalog entries by name — never describe a bespoke date\u002Fselect\u002Fetc.)\n\n### Data\n- \u003Cwhat data this screen needs, where it comes from (API \u002F state store \u002F prop)>\n\n### API calls\n- \u003CMETHOD \u002Fpath> — \u003Cpurpose> [gap: G-## if blocked]\n\n### User actions\n- \u003Caction> → \u003Cresult or navigation target> — span `\u003Cfeature.action>`\n\n### States\n- **Loading**: \u003Cdescription>\n- **Empty**: \u003Cdescription>\n- **Error**: \u003Cdescription> — traced + logged (see Observability standard)\n- **Populated**: \u003Cdescription>\n\n### i18n keys\n- `\u003Ckey>`: \"\u003Cdefault text>\"\n\n### Open gaps\n- \u003CG-## or [MISSING_INFO] if something cannot be determined from context>\n```\n\n## Rules\n\n- Apply `.claude\u002Fshared\u002FUI_CONSISTENCY.md`: reference canonical components by catalog name;\n  flag any screen that would need a bespoke variant of a shared input.\n- Apply `.claude\u002Fshared\u002FOBSERVABILITY.md`: every user action names its trace span; the Error\n  state is traced + logged.\n- Cover every screen derivable from scope. If a scope item maps to multiple screens (e.g., S-WORK has 7 workflow steps), create one entry per step.\n- Use generic terms for architecture references (\"state store\", \"HTTP client\") except when an ADR decision is being cited — in that case label it clearly.\n- Do not invent API endpoints. If the endpoint is unknown, write `[MISSING_INFO] endpoint TBD` and cite the relevant gap.\n- Mark any uncertainty with `[INFERRED]` or `[ASSUMED]` as appropriate.\n- Preserve `[MISSING_INFO]` for anything that cannot be derived from context.\n\n## After writing\n\nReport: total screen count, scope items covered, number of `[MISSING_INFO]` markers found.\n","## Sources & manifest status (hivemind)\n\nVendored from implementation-engine. In hivemind the \"context\" this skill reads is the project's\nknowledge surface — `PROJECT.md`, the wisearcher brain graph (`kb_search`\u002F`kb_answer`, or the local\n`knowledge\u002F` KB when the brain is offline), and the ticket's scope + acceptance criteria. Where the\nbody below refers to `context\u002F\u003Cfile>.md`, read the equivalent from that surface. Output goes to\n`implementation\u002FSCREEN_SPECS.md`.\n\n**Status (TASK-230, 2026-09-16 human decision):** optional tool, not a gate. No `verification_tier`\nrequires this manifest before code — see `src\u002Fmanifest-policy.js` (`requiresManifest` always returns\n`false`). Generate\u002Fupdate it whenever it helps, in whatever order the Developer chooses; the\nreviewer does NOT treat a missing manifest as a finding. Preserve epistemic markers\n(`[EXPLICIT]`\u002F`[INFERRED:strong|weak]`\u002F`[ASSUMED]`) and respect source tiers.\n\n---\n\n# impl-screen-specs\n\nGenerates `implementation\u002FSCREEN_SPECS.md` — a per-screen specification covering every screen in the project scope.\n\n## Read first\n\nRead these files from `context\u002F` (and only from `context\u002F`):\n- `context\u002Fscope.md` — identifies all scope items (S-##) and their feature areas\n- `context\u002Ftechnical.md` — navigation structure, architecture patterns, component conventions\n- `context\u002Fexecution.md` — phase assignments per feature area\n\n## Output: `implementation\u002FSCREEN_SPECS.md`\n\nWrite one entry per screen. Derive the screen list from the scope items (S-AUTH, S-HOME, S-CAMP, S-WORK, S-CHAT, S-PROF, S-SET, S-PAY, S-REP) and expand each into its constituent screens.\n\n### Format for each screen\n\n```markdown\n## \u003CScreen Name>\n\n**Scope item**: S-##\n**Phase**: P#\n**Navigation path**: \u003Ctab> → \u003Cstack position>  (e.g., Campaigns tab → Campaign Detail)\n\n### Components\n- \u003CCanonical component name from COMPONENT_CATALOG>: \u003Cbrief purpose>\n  (reference catalog entries by name — never describe a bespoke date\u002Fselect\u002Fetc.)\n\n### Data\n- \u003Cwhat data this screen needs, where it comes from (API \u002F state store \u002F prop)>\n\n### API calls\n- \u003CMETHOD \u002Fpath> — \u003Cpurpose> [gap: G-## if blocked]\n\n### User actions\n- \u003Caction> → \u003Cresult or navigation target> — span `\u003Cfeature.action>`\n\n### States\n- **Loading**: \u003Cdescription>\n- **Empty**: \u003Cdescription>\n- **Error**: \u003Cdescription> — traced + logged (see Observability standard)\n- **Populated**: \u003Cdescription>\n\n### i18n keys\n- `\u003Ckey>`: \"\u003Cdefault text>\"\n\n### Open gaps\n- \u003CG-## or [MISSING_INFO] if something cannot be determined from context>\n```\n\n## Rules\n\n- Apply `.claude\u002Fshared\u002FUI_CONSISTENCY.md`: reference canonical components by catalog name;\n  flag any screen that would need a bespoke variant of a shared input.\n- Apply `.claude\u002Fshared\u002FOBSERVABILITY.md`: every user action names its trace span; the Error\n  state is traced + logged.\n- Cover every screen derivable from scope. If a scope item maps to multiple screens (e.g., S-WORK has 7 workflow steps), create one entry per step.\n- Use generic terms for architecture references (\"state store\", \"HTTP client\") except when an ADR decision is being cited — in that case label it clearly.\n- Do not invent API endpoints. If the endpoint is unknown, write `[MISSING_INFO] endpoint TBD` and cite the relevant gap.\n- Mark any uncertainty with `[INFERRED]` or `[ASSUMED]` as appropriate.\n- Preserve `[MISSING_INFO]` for anything that cannot be derived from context.\n\n## After writing\n\nReport: total screen count, scope items covered, number of `[MISSING_INFO]` markers found.\n",{"name":5,"description":7},"main","c8856147b7a3246a1e54b66126d093183805d1f3",".claude\u002Fskills\u002Fimpl-screen-specs",0,"https:\u002F\u002Fgithub.com\u002FHexingBot\u002Fhivemind","https:\u002F\u002Fhivemind-ef84a.web.app","https:\u002F\u002Fgithub.com\u002FHexingBot","2026-10-10 00:50:01",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add HexingBot\u002Fhivemind --skill impl-screen-specs",{"tool":37,"command":38},"bunx","bunx skills add HexingBot\u002Fhivemind --skill impl-screen-specs",{"tool":40,"command":41},"pnpm","pnpm dlx skills add HexingBot\u002Fhivemind --skill impl-screen-specs","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHexingBot\u002Fhivemind\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimpl-screen-specs\u002FSKILL.md",true,[],[46,53,62,70,77,85],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M77MWBWY2AK0GJ91MMKAPZ0M","unknown-skill","A demo skill with no license signal at all, used to exercise the \"unknown\" classification branch of the human license gate (TASK-135).","https:\u002F\u002Fgithub.com\u002FHexingBot\u002Fhivemind\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Funknown-skill\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":57,"licenseFileUrl":58,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":18},"01M77MW9H43Z0ATZ15421K8J7D","spoofed-license-skill","A demo skill used to test TASK-150's SPDX-header-vs-LICENSE-file conflict surfacing.","GPL-3.0","https:\u002F\u002Fgithub.com\u002FHexingBot\u002Fhivemind\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fspoofed-license-skill\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHexingBot\u002Fhivemind\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fspoofed-license-skill\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":66,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":18},"01M77MW7715ENRZN6F01FDM81J","permissive-skill","A demo skill used to test assimilation of a permissively-licensed third party skill.","https:\u002F\u002Fgithub.com\u002FHexingBot\u002Fhivemind\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fpermissive-skill\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHexingBot\u002Fhivemind\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fpermissive-skill\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},"01M77MW3CRAPWETDAZT7E08BVS","malicious-skill","A fixture skill deliberately carrying risky content patterns, used only to exercise src\u002Fskill-scan.js (TASK-122). Never assimilated for real.","https:\u002F\u002Fgithub.com\u002FHexingBot\u002Fhivemind\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fmalicious-skill\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":57,"licenseFileUrl":81,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M77MW1RSWW1MTQGM9TY3X37G","copyleft-skill","A demo skill used to test the human license gate for a copyleft third party skill.","https:\u002F\u002Fgithub.com\u002FHexingBot\u002Fhivemind\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fcopyleft-skill\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHexingBot\u002Fhivemind\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills\u002Fcopyleft-skill\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M77MVWT1EVEJ8ZYZTCG4CENE","watch","Watch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video. (assimilated for Hivemind)","https:\u002F\u002Fgithub.com\u002FHexingBot\u002Fhivemind\u002Fblob\u002Fmain\u002Fskills\u002Fwatch\u002FSKILL.md",[],[]]