[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77PJFHHZ13PC9VQQ02N70C0":3,"skill-same:01M77PJFHHZ13PC9VQQ02N70C0":87},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":14,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":37,"ownerDescription":38,"updatedAt":39,"install":40,"resources":52},"01M77PJFHHZ13PC9VQQ02N70C0","vibe-aso",null,"Full-funnel App Store Optimization for an iOS app — keyword research (popularity\u002Fdifficulty driven), a keyword-led name\u002Fsubtitle\u002Fkeyword field, App Store metadata localized into up to 50 locales, localized screenshot headings burned over your mockups, worldwide territory pricing, and in-app string localization. Use when the user wants to \"do the ASO\", \"find keywords\", \"localize my app \u002F my App Store page \u002F my screenshots\", \"pick a name and subtitle\", \"set worldwide prices\", or is preparing an App Store submission.","Necmttn\u002Fskills","Necmttn","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5212808?v=4","01M77PDTX0P2888A46VQ6DREZG","Neco","01M77PDTXNATPR101437VV6H7Y",0,"MIT","https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fskills\u002Fblob\u002Fmain\u002Fkb-site\u002Fexternal\u002Fvibe-aso\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fskills\u002Fblob\u002Fmain\u002Fkb-site\u002Fexternal\u002Fvibe-aso\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: vibe-aso\ndescription: Full-funnel App Store Optimization for an iOS app — keyword research (popularity\u002Fdifficulty driven), a keyword-led name\u002Fsubtitle\u002Fkeyword field, App Store metadata localized into up to 50 locales, localized screenshot headings burned over your mockups, worldwide territory pricing, and in-app string localization. Use when the user wants to \"do the ASO\", \"find keywords\", \"localize my app \u002F my App Store page \u002F my screenshots\", \"pick a name and subtitle\", \"set worldwide prices\", or is preparing an App Store submission.\nuser-invocable: true\nallowed-tools:\n  - Read\n  - Write\n  - Edit\n  - Bash\n  - AskUserQuestion\n---\n\n# Vibe ASO — the whole App Store funnel, from Claude Code\n\nYou built an app. This skill takes it the rest of the way: what people search,\nwhat your listing says in every language, what your screenshots say, what the\napp costs in every country, and what the app itself says once installed.\n\nIt is organized as six phases. Run them in order for a new app, or jump to the\none the user asked for. Each phase has a reference file with the full rules —\n**read the reference file before starting a phase**; this page is the map, not\nthe territory.\n\n| Phase | Does | Reference |\n|---|---|---|\n| 0 SETUP | one-time wizard: ASC API key, translation engine, data source | below |\n| 1 RESEARCH | keyword research → main keyword, subtitle keyword, keyword field | `reference\u002Fkeyword-research.md` |\n| 2 METADATA | name\u002Fsubtitle\u002Fkeywords\u002Fdescription, en-US first, then all chosen locales | `reference\u002Fmetadata.md` |\n| 3 SCREENSHOTS | localized headings burned over the user's mockups, all locales | `reference\u002Fscreenshots.md` |\n| 4 PRICING | pricing model chosen by the user, applied per territory | `reference\u002Fpricing.md` |\n| 5 IN-APP | localize the app's own UI strings | `reference\u002Fapp-localization.md` |\n| 6 SUBMIT | upload, verify, and the manual-steps list Apple's API can't do | `reference\u002Fsubmission-checklist.md` |\n\nA worked example runs through every reference file: a calorie-tracking app\nwhose brand name is **Glow Up**. Every rule is illustrated on it; none of the\nrules are specific to it.\n\n## Phase 0 — Setup wizard (first run, or whenever a check fails)\n\nRun `scripts\u002Fcheck_setup.sh` first. If everything passes, skip to the phase the\nuser wants. Otherwise walk ONLY the missing pieces, in this order:\n\n**1. App Store Connect API key** (needed by phases 2, 3, 4, 6).\nAsk the user to create one — App Store Connect → Users and Access →\nIntegrations → App Store Connect API → Team Keys → **Generate API Key**, role\n**App Manager**, then download the `.p8` file (downloadable **once**). Then:\n\n- Store the `.p8` at `~\u002F.vibe-aso\u002FAuthKey.p8`, `chmod 600`.\n- Write `~\u002F.vibe-aso\u002Fconfig.json` (create the dir `chmod 700`, file `chmod 600`):\n\n```json\n{\n  \"asc\": {\n    \"key_id\": \"\u003C10-char Key ID shown next to the key>\",\n    \"issuer_id\": \"\u003CUUID at the top of the Team Keys page>\",\n    \"p8_path\": \"~\u002F.vibe-aso\u002FAuthKey.p8\"\n  },\n  \"translation\": { \"engine\": \"subagents\" }\n}\n```\n\n- Verify with `ruby scripts\u002Fasc.rb GET '\u002Fv1\u002Fapps?limit=1'` → must print `HTTP 200`.\n\n**Security is non-negotiable:** the key lives in `~\u002F.vibe-aso\u002F`, never inside\nany project directory, never in a repo, never in a commit, never echoed to the\nterminal, never pasted into a file the user might share. If the user pastes the\nkey contents into chat, save it and tell them to revoke-and-regenerate if this\nconversation ever leaves their machine.\n\n**2. Translation engine** (phases 2, 3, 5). Ask via AskUserQuestion:\n\n- **Claude subagents** (default; recommended) — translations are generated by\n  spawned subagents, batched per locale. No extra account, no extra key. Cost\n  is the user's existing Claude usage.\n- **DeepSeek API** — cheapest for very large volumes (a whole in-app catalog ×\n  40 locales runs on cents). Key goes to `~\u002F.vibe-aso\u002Fdeepseek-key`\n  (`chmod 600`), config: `{\"engine\": \"deepseek\", \"api_key_path\":\n  \"~\u002F.vibe-aso\u002Fdeepseek-key\", \"base_url\": \"https:\u002F\u002Fapi.deepseek.com\", \"model\":\n  \"deepseek-chat\"}`.\n- **Any OpenAI-compatible API** — same shape: `{\"engine\": \"openai\",\n  \"api_key_path\": \"...\", \"base_url\": \"...\", \"model\": \"...\"}`. The user brings\n  whatever provider they like.\n\nFor API engines, verify the key works with one tiny request before any long\nrun. For DeepSeek specifically, **check the account balance, not just the\nkey** — a valid key on an empty account fails every request with `HTTP 402`,\nand it will do so 30 minutes into a cascade rather than up front\n(`check_setup.sh` does this).\n\n**3. Keyword data source** (phase 1). The research method needs, per keyword:\n**popularity** (search volume proxy), **difficulty**, and ideally \"how many\napps use this in their name\u002Fsubtitle\". Ask what the user has:\n\n- **Astro** (Mac ASO app) with its MCP server connected — best supported; the\n  reference file maps each step to Astro's tools.\n- **Another ASO tool** (AppFigures, Sensor Tower, Mobile Action, AppTweak…) —\n  the method is identical; the user runs the lookups in their tool and pastes\n  numbers when asked.\n- **No tool** — phase 1 still works but degrades honestly: Apple's own search\n  suggestions + competitor listings give the keyword *candidates*, and the\n  skill says plainly that popularity\u002Fdifficulty calls are guesses. Recommend\n  getting a data tool before betting the app name on a keyword.\n\nStore the answer in config as `\"keyword_source\": \"astro\" | \"manual\" | \"none\"`.\n\n## Cross-phase laws\n\nThese hold in every phase; the reference files repeat them where they bite.\n\n1. **Fan out to all locales in one pass, review by automated checks.** Never\n   pause a localization run for a per-language human review unless the user\n   explicitly asks for one. A human cannot review 40+ languages, and reviewing\n   one language proves nothing about the other 39. The review that works:\n   char-limit checks, format-specifier parity, verbatim-atom checks,\n   same-as-source detection, plus spot-checks of the hard scripts (CJK, RTL,\n   Indic) — all defined in the reference files.\n2. **Ask which locales, once, in phase 2.** Default: all supported locales.\n   The user may cut the set (e.g. top-15 markets); whatever is chosen there is\n   the set for screenshots and in-app strings too. Do not re-ask per phase.\n3. **App Store Connect is the source of truth** for anything Apple owns —\n   live metadata, prices, review state, IAP existence. Pull from it before\n   editing; never trust a possibly stale local copy over the live listing.\n4. **Sweep once, slice locally.** The ASC API is slow and rate-limited.\n   Anything that walks many locales or many products gets dumped to a local\n   file once; every follow-up question is answered from the file, never by\n   re-sweeping because the analysis changed.\n5. **A 2xx is not verification.** After any write, GET the field back and\n   check the value. Report only what a read-back confirmed.\n6. **Character limits are hard**: name 30, subtitle 30, keyword field 100,\n   promotional text 170, description 4000. Validate after writing, per locale.\n7. **Some strings never localize**: Apple product names (iPhone, Apple Watch,\n   iPad), URLs, email addresses, the brand name as the user styles it, product\n   codes. A translated support email is a dead mailto; a \"translated\" URL is a\n   404.\n8. **Chunk long-running work.** Translation cascades and bulk uploads run as\n   many small foreground commands (per locale, per batch), never one giant\n   call that outlives the shell's patience. Report only what is verified on\n   disk or read back from the API — \"the cascade is running\" is not a result.\n\n## Scripts and assets in this skill\n\n```\nscripts\u002Fasc.rb          # minimal ASC API client — ruby asc.rb GET '\u002Fv1\u002Fapps'\nscripts\u002Fcheck_setup.sh  # PASS\u002FWARN\u002FFAIL per prerequisite, with fix commands\nrenderer\u002F               # screenshot heading renderer (playwright + per-script fonts)\nrenderer\u002Ffetch_fonts.sh # one-time ~55MB font download (DM Sans + Noto per script)\nreference\u002F*.md          # the six phase guides — read before the phase\n```\n\nThe renderer needs a one-time `npm install && npx playwright install chromium`\nand `.\u002Ffetch_fonts.sh` inside `renderer\u002F` (check_setup.sh tells you if they're\nmissing).\n\n**Free Figma mockup template** (iPhone \u002F iPad \u002F Apple Watch frames with\n\"Your screenshot here\" placeholders) — offer it whenever the user has no\nscreenshot designs or asks how to provide them:\nhttps:\u002F\u002Fwww.figma.com\u002Fdesign\u002FftvaN3ZMfgkGrn7SAuqCvt\u002Fvibe-ASO-mockups\n\n## Reporting\n\nEnd every phase with three short sections: **Done** (what happened, verified),\n**Problems** (what surprised you and how it was handled), **Needs you** (manual\nsteps only the user can do — or \"nothing\"). Keep it outcome-level; skip file\npaths and internals unless asked.\n","# Vibe ASO — the whole App Store funnel, from Claude Code\n\nYou built an app. This skill takes it the rest of the way: what people search,\nwhat your listing says in every language, what your screenshots say, what the\napp costs in every country, and what the app itself says once installed.\n\nIt is organized as six phases. Run them in order for a new app, or jump to the\none the user asked for. Each phase has a reference file with the full rules —\n**read the reference file before starting a phase**; this page is the map, not\nthe territory.\n\n| Phase | Does | Reference |\n|---|---|---|\n| 0 SETUP | one-time wizard: ASC API key, translation engine, data source | below |\n| 1 RESEARCH | keyword research → main keyword, subtitle keyword, keyword field | `reference\u002Fkeyword-research.md` |\n| 2 METADATA | name\u002Fsubtitle\u002Fkeywords\u002Fdescription, en-US first, then all chosen locales | `reference\u002Fmetadata.md` |\n| 3 SCREENSHOTS | localized headings burned over the user's mockups, all locales | `reference\u002Fscreenshots.md` |\n| 4 PRICING | pricing model chosen by the user, applied per territory | `reference\u002Fpricing.md` |\n| 5 IN-APP | localize the app's own UI strings | `reference\u002Fapp-localization.md` |\n| 6 SUBMIT | upload, verify, and the manual-steps list Apple's API can't do | `reference\u002Fsubmission-checklist.md` |\n\nA worked example runs through every reference file: a calorie-tracking app\nwhose brand name is **Glow Up**. Every rule is illustrated on it; none of the\nrules are specific to it.\n\n## Phase 0 — Setup wizard (first run, or whenever a check fails)\n\nRun `scripts\u002Fcheck_setup.sh` first. If everything passes, skip to the phase the\nuser wants. Otherwise walk ONLY the missing pieces, in this order:\n\n**1. App Store Connect API key** (needed by phases 2, 3, 4, 6).\nAsk the user to create one — App Store Connect → Users and Access →\nIntegrations → App Store Connect API → Team Keys → **Generate API Key**, role\n**App Manager**, then download the `.p8` file (downloadable **once**). Then:\n\n- Store the `.p8` at `~\u002F.vibe-aso\u002FAuthKey.p8`, `chmod 600`.\n- Write `~\u002F.vibe-aso\u002Fconfig.json` (create the dir `chmod 700`, file `chmod 600`):\n\n```json\n{\n  \"asc\": {\n    \"key_id\": \"\u003C10-char Key ID shown next to the key>\",\n    \"issuer_id\": \"\u003CUUID at the top of the Team Keys page>\",\n    \"p8_path\": \"~\u002F.vibe-aso\u002FAuthKey.p8\"\n  },\n  \"translation\": { \"engine\": \"subagents\" }\n}\n```\n\n- Verify with `ruby scripts\u002Fasc.rb GET '\u002Fv1\u002Fapps?limit=1'` → must print `HTTP 200`.\n\n**Security is non-negotiable:** the key lives in `~\u002F.vibe-aso\u002F`, never inside\nany project directory, never in a repo, never in a commit, never echoed to the\nterminal, never pasted into a file the user might share. If the user pastes the\nkey contents into chat, save it and tell them to revoke-and-regenerate if this\nconversation ever leaves their machine.\n\n**2. Translation engine** (phases 2, 3, 5). Ask via AskUserQuestion:\n\n- **Claude subagents** (default; recommended) — translations are generated by\n  spawned subagents, batched per locale. No extra account, no extra key. Cost\n  is the user's existing Claude usage.\n- **DeepSeek API** — cheapest for very large volumes (a whole in-app catalog ×\n  40 locales runs on cents). Key goes to `~\u002F.vibe-aso\u002Fdeepseek-key`\n  (`chmod 600`), config: `{\"engine\": \"deepseek\", \"api_key_path\":\n  \"~\u002F.vibe-aso\u002Fdeepseek-key\", \"base_url\": \"https:\u002F\u002Fapi.deepseek.com\", \"model\":\n  \"deepseek-chat\"}`.\n- **Any OpenAI-compatible API** — same shape: `{\"engine\": \"openai\",\n  \"api_key_path\": \"...\", \"base_url\": \"...\", \"model\": \"...\"}`. The user brings\n  whatever provider they like.\n\nFor API engines, verify the key works with one tiny request before any long\nrun. For DeepSeek specifically, **check the account balance, not just the\nkey** — a valid key on an empty account fails every request with `HTTP 402`,\nand it will do so 30 minutes into a cascade rather than up front\n(`check_setup.sh` does this).\n\n**3. Keyword data source** (phase 1). The research method needs, per keyword:\n**popularity** (search volume proxy), **difficulty**, and ideally \"how many\napps use this in their name\u002Fsubtitle\". Ask what the user has:\n\n- **Astro** (Mac ASO app) with its MCP server connected — best supported; the\n  reference file maps each step to Astro's tools.\n- **Another ASO tool** (AppFigures, Sensor Tower, Mobile Action, AppTweak…) —\n  the method is identical; the user runs the lookups in their tool and pastes\n  numbers when asked.\n- **No tool** — phase 1 still works but degrades honestly: Apple's own search\n  suggestions + competitor listings give the keyword *candidates*, and the\n  skill says plainly that popularity\u002Fdifficulty calls are guesses. Recommend\n  getting a data tool before betting the app name on a keyword.\n\nStore the answer in config as `\"keyword_source\": \"astro\" | \"manual\" | \"none\"`.\n\n## Cross-phase laws\n\nThese hold in every phase; the reference files repeat them where they bite.\n\n1. **Fan out to all locales in one pass, review by automated checks.** Never\n   pause a localization run for a per-language human review unless the user\n   explicitly asks for one. A human cannot review 40+ languages, and reviewing\n   one language proves nothing about the other 39. The review that works:\n   char-limit checks, format-specifier parity, verbatim-atom checks,\n   same-as-source detection, plus spot-checks of the hard scripts (CJK, RTL,\n   Indic) — all defined in the reference files.\n2. **Ask which locales, once, in phase 2.** Default: all supported locales.\n   The user may cut the set (e.g. top-15 markets); whatever is chosen there is\n   the set for screenshots and in-app strings too. Do not re-ask per phase.\n3. **App Store Connect is the source of truth** for anything Apple owns —\n   live metadata, prices, review state, IAP existence. Pull from it before\n   editing; never trust a possibly stale local copy over the live listing.\n4. **Sweep once, slice locally.** The ASC API is slow and rate-limited.\n   Anything that walks many locales or many products gets dumped to a local\n   file once; every follow-up question is answered from the file, never by\n   re-sweeping because the analysis changed.\n5. **A 2xx is not verification.** After any write, GET the field back and\n   check the value. Report only what a read-back confirmed.\n6. **Character limits are hard**: name 30, subtitle 30, keyword field 100,\n   promotional text 170, description 4000. Validate after writing, per locale.\n7. **Some strings never localize**: Apple product names (iPhone, Apple Watch,\n   iPad), URLs, email addresses, the brand name as the user styles it, product\n   codes. A translated support email is a dead mailto; a \"translated\" URL is a\n   404.\n8. **Chunk long-running work.** Translation cascades and bulk uploads run as\n   many small foreground commands (per locale, per batch), never one giant\n   call that outlives the shell's patience. Report only what is verified on\n   disk or read back from the API — \"the cascade is running\" is not a result.\n\n## Scripts and assets in this skill\n\n```\nscripts\u002Fasc.rb          # minimal ASC API client — ruby asc.rb GET '\u002Fv1\u002Fapps'\nscripts\u002Fcheck_setup.sh  # PASS\u002FWARN\u002FFAIL per prerequisite, with fix commands\nrenderer\u002F               # screenshot heading renderer (playwright + per-script fonts)\nrenderer\u002Ffetch_fonts.sh # one-time ~55MB font download (DM Sans + Noto per script)\nreference\u002F*.md          # the six phase guides — read before the phase\n```\n\nThe renderer needs a one-time `npm install && npx playwright install chromium`\nand `.\u002Ffetch_fonts.sh` inside `renderer\u002F` (check_setup.sh tells you if they're\nmissing).\n\n**Free Figma mockup template** (iPhone \u002F iPad \u002F Apple Watch frames with\n\"Your screenshot here\" placeholders) — offer it whenever the user has no\nscreenshot designs or asks how to provide them:\nhttps:\u002F\u002Fwww.figma.com\u002Fdesign\u002FftvaN3ZMfgkGrn7SAuqCvt\u002Fvibe-ASO-mockups\n\n## Reporting\n\nEnd every phase with three short sections: **Done** (what happened, verified),\n**Problems** (what surprised you and how it was handled), **Needs you** (manual\nsteps only the user can do — or \"nothing\"). Keep it outcome-level; skip file\npaths and internals unless asked.\n",{"name":5,"description":7,"allowed-tools":25,"user-invocable":31},[26,27,28,29,30],"Read","Write","Edit","Bash","AskUserQuestion",true,"main","b321807e50f72ccb0df5da9aaeba42088271907e","kb-site\u002Fexternal\u002Fvibe-aso","https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fskills","https:\u002F\u002Fgithub.com\u002FNecmttn","https:\u002F\u002Fnecmttn.com","Fractional CTO - \r\nAI Solution Architect","2026-11-07 08:05:35",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":31},[42,45,48],{"tool":43,"command":44},"npx","npx skills add Necmttn\u002Fskills --skill vibe-aso",{"tool":46,"command":47},"bunx","bunx skills add Necmttn\u002Fskills --skill vibe-aso",{"tool":49,"command":50},"pnpm","pnpm dlx skills add Necmttn\u002Fskills --skill vibe-aso","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fskills\u002Fblob\u002Fmain\u002Fkb-site\u002Fexternal\u002Fvibe-aso\u002FSKILL.md",[53,57,63,67,71,75,79,83],{"path":54,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":16},"LICENSE","许可证",1063,{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"reference\u002Fapp-localization.md","REFERENCE","参考文档",11092,"https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fskills\u002Fblob\u002Fmain\u002Fkb-site\u002Fexternal\u002Fvibe-aso\u002Freference\u002Fapp-localization.md",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"reference\u002Fkeyword-research.md",7624,"https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fskills\u002Fblob\u002Fmain\u002Fkb-site\u002Fexternal\u002Fvibe-aso\u002Freference\u002Fkeyword-research.md",{"path":68,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":69,"sourceHtmlUrl":70},"reference\u002Fmetadata.md",7217,"https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fskills\u002Fblob\u002Fmain\u002Fkb-site\u002Fexternal\u002Fvibe-aso\u002Freference\u002Fmetadata.md",{"path":72,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":73,"sourceHtmlUrl":74},"reference\u002Fpricing.md",4464,"https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fskills\u002Fblob\u002Fmain\u002Fkb-site\u002Fexternal\u002Fvibe-aso\u002Freference\u002Fpricing.md",{"path":76,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":77,"sourceHtmlUrl":78},"reference\u002Fscreenshots.md",7324,"https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fskills\u002Fblob\u002Fmain\u002Fkb-site\u002Fexternal\u002Fvibe-aso\u002Freference\u002Fscreenshots.md",{"path":80,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":81,"sourceHtmlUrl":82},"reference\u002Fsubmission-checklist.md",5255,"https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fskills\u002Fblob\u002Fmain\u002Fkb-site\u002Fexternal\u002Fvibe-aso\u002Freference\u002Fsubmission-checklist.md",{"path":84,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":85,"sourceHtmlUrl":86},"UPSTREAM.md",2508,"https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fskills\u002Fblob\u002Fmain\u002Fkb-site\u002Fexternal\u002Fvibe-aso\u002FUPSTREAM.md",[88,95,102,109,116,124],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":20},"01M77PNJ1JCKWHR2XJDBX8Q85P","wiki","Recall from the personal LLM wiki at ~\u002Fwiki. Use when the user asks what the wiki says, wants prior thinking\u002Fintuition on a concept, or when grounding a design or decision in previously synthesized knowledge. Read-only - never writes to the wiki.","https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fwiki\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":20},"01M77PNERKEH3ZN11HMC6YEH9G","wiki-ingest","Curate a source into the personal LLM wiki at ~\u002Fwiki following its SCHEMA.md - a file, URL, research output, ax session, or a pending ~\u002Fwiki\u002Finbox\u002F brief. Use when the user says \"add this to the wiki\", \"ingest this\", \"promote the inbox\", or after research worth keeping long-term.","https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fwiki-ingest\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":20},"01M77PNB9SMTTG3D80BXGCY16B","wiki-harvest","Propose-only sweep of recent coding sessions (via the ax CLI) for recurring concepts that are missing from, or should update, the personal LLM wiki at ~\u002Fwiki. Writes candidate briefs to ~\u002Fwiki\u002Finbox\u002F only - never wiki pages. Use on schedule or when the user asks \"harvest the wiki\" or \"what concepts am I repeating\".","https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fwiki-harvest\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":20},"01M77PN73WAF08PCWBYXST9BW6","no-ai-slop","Strip AI-slop patterns from a draft while preserving the writer's voice, or detect slop without rewriting. Use as the mandatory final pass on any copy before shipping, when the user wants a draft clearer\u002Fless AI-sounding, or when asked \"is this AI slop?\", \"audit this writing\", \"does this read as AI\".","https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpersonal\u002Fno-ai-slop\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":20},"01M77PN2H1QTPD9GD6VBJ3YBPN","aso-appstore-screenshots","Generate high-converting App Store screenshots by analyzing your app's codebase, discovering core benefits, and creating ASO-optimized screenshot images using Nano Banana Pro.","https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmisc\u002Faso-appstore-screenshots\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmisc\u002Faso-appstore-screenshots\u002FSKILL.md",[],[],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":20},"01M77PMVGA58GA46JCFJW2JH5X","app-idea","Run a new or existing consumer\u002FAI app idea through the golden-track playbook (~\u002Fwiki\u002Fplaybook\u002Fapps.md) from intake to verdict, write a verdict card, stop for the owner, and ratchet owner overrides back into the doctrine. Use when the user shares an app idea, asks \"should I build X\", \"audit \u003Capp>\", \"re-score \u003Capp>\", or pastes an idea in a product context. Never builds; never promotes a rule on its own.","https:\u002F\u002Fgithub.com\u002FNecmttn\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmisc\u002Fapp-idea\u002FSKILL.md",[],[]]