[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79FMVEEWZ2ZPZNEGEQNBMCK":3,"skill-same:01M79FMVEEWZ2ZPZNEGEQNBMCK":77},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M79FMVEEWZ2ZPZNEGEQNBMCK","safari-browser",null,"Use Safari (never Playwright\u002FChromium) for all browser automation on this Mac. The user is authenticated in Safari for X, Grok, Google Drive, GitHub, and other web services required by research workflows. Trigger on any browser task: open a URL, scrape a page, read a Grok share, log into a site, fill a form, take a screenshot, debug a web UI, or when Playwright would otherwise be chosen. Happy path: safari_read_page.sh or safari_extract_fast.py (AppleScript innerText). Interactive grok.com chat (modes, send, harvest): see references\u002Fgrok-com-computer-use.md. Interactive gemini.google.com chat: see references\u002Fgemini-google-computer-use.md. Do NOT use Playwright unless the user explicitly overrides this preference.","zfifteen\u002Fskills-catalog","zfifteen","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F221906715?v=4","01M79CQFXDZM5J5CJTCECPFA66","Dionisio Alberto Lopez III","01M79CQFY4C62PN8A2T5KDAHGA",1,"MIT","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fsafari-browser\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: safari-browser\ndescription: >\n  Use Safari (never Playwright\u002FChromium) for all browser automation on this Mac.\n  The user is authenticated in Safari for X, Grok, Google Drive, GitHub, and other\n  web services required by research workflows. Trigger on any browser task: open a\n  URL, scrape a page, read a Grok share, log into a site, fill a form, take a\n  screenshot, debug a web UI, or when Playwright would otherwise be chosen.\n  Happy path: safari_read_page.sh or safari_extract_fast.py (AppleScript innerText).\n  Interactive grok.com chat (modes, send, harvest): see references\u002Fgrok-com-computer-use.md.\n  Interactive gemini.google.com chat: see references\u002Fgemini-google-computer-use.md.\n  Do NOT use Playwright unless the user explicitly overrides this preference.\nmetadata:\n  short-description: \"Always use Safari for browser automation (authenticated session)\"\n  version: \"1.2.0\"\n---\n\n# Safari Browser (Global Preference)\n\n**Hard rule:** When a task needs a real browser on this Mac, use **Safari only**.\nDo not open Playwright, Chromium, or headless Chrome unless the user explicitly asks.\n\n**Why:** Safari carries the user's live sessions for X, Grok, Google, GitHub, and other services.\n\n## Interactive grok.com (computer use)\n\nFor **live chat** on `https:\u002F\u002Fgrok.com` (model mode Fast\u002FExpert\u002FHeavy, paste prompts, wait for generation, harvest answers), do **not** invent a new approach. Follow the learned playbook:\n\n**[references\u002Fgrok-com-computer-use.md](references\u002Fgrok-com-computer-use.md)**\n\nSummary of hard-won rules:\n- **NEVER BATCH.** Batch is **strictly prohibited.** One Act only, then screenshot + analyze.\n- **ALWAYS screenshot, then analyze.** Decisions come from the image, not key logs.\n- **Screenshot every 3–5 seconds** while operating; determine state each time; then decide.\n- **OODA Loop mandatory:** Observe → Orient → Decide → Act → Observe again.\n- Scroll the full reply only if shots prove content moved; action bar must be **visible in the image** before Copy.\n- **Never retype the URL** if already on grok.com; new chat via **Home page** link.\n- Address bar only when needed: Meta+l → Meta+a → **Backspace** → type URL → **verify field** → Return (OCU `type_text` **appends** even when selected).\n- Mode: **Model select** + real cursor (not avatar **F**).\n- **Harvest after each round:** action bar visible in shot → **Copy at end of that response** → clipboard (`pbpaste`). Not full-page scrape as default.\n\n## Happy path (use this first)\n\nValidated on `x.com\u002Fi\u002Fgrok\u002Fshare\u002F...` Grok conversations (2026-07-08):\n\n```bash\nbash \"$HOME\u002F.grok\u002Fskills\u002Fsafari-browser\u002Fscripts\u002Fsafari_read_page.sh\" \\\n  'https:\u002F\u002Fx.com\u002Fi\u002Fgrok\u002Fshare\u002F\u003Cid>' \\\n  --output experiments\u002F\u003Ctopic>\u002Fsafari_transcript.txt \\\n  --wait 12\n```\n\n**What it does:** `safari_open.sh` → wait 12s → AppleScript `document.body.innerText` in 5k chunks → clean text (~21k chars in \u003C2s after load).\n\n**Do not use:** Playwright, `web_fetch`, raw `source` AppleScript (pre-JS shell), Cmd+A copy (gets URL only), or WebDriver `body.text` (pulls HTML junk). WebDriver `innerText` works but is slower (~22s); reserve for `--method webdriver`.\n\n### One-shot Python (same happy path)\n\n```bash\npython3 \"$HOME\u002F.grok\u002Fskills\u002Fsafari-browser\u002Fscripts\u002Fsafari_extract_fast.py\" \\\n  '\u003Curl>' --output transcript.txt --wait 12\n```\n\n### Read current tab (already open in Safari)\n\n```bash\npython3 \"$HOME\u002F.grok\u002Fskills\u002Fsafari-browser\u002Fscripts\u002Fsafari_extract_fast.py\" \\\n  '\u003Curl>' --no-open --output transcript.txt --wait 2\n```\n\n## Prerequisites (enabled on this machine)\n\nSafari → Settings → Developer:\n\n| Setting | Required for happy path |\n|---------|-------------------------|\n| **Allow JavaScript from Apple Events** | Yes — `safari_extract_fast.py` |\n| **Allow remote automation** | Optional — WebDriver fallback only |\n\n## Decision order\n\n1. **`safari_read_page.sh` \u002F `safari_extract_fast.py`** — default for all page reads\n2. **`safari_open.sh`** — navigation only\n3. **`safari_extract.py --method webdriver`** — scroll-heavy pages if fast path insufficient\n4. **UI scripting** — last resort only\n5. **Playwright** — forbidden unless user explicitly overrides\n\n## Agent workflow\n\n1. **Do not** reach for Playwright or `read_share.sh` (Playwright) for X-hosted Grok shares.\n2. Run `safari_read_page.sh` with `--output` under `experiments\u002F\u003Ctopic>\u002F`.\n3. If fast path fails, check Developer toggles; do not silently fall back to Playwright.\n4. Save artifact; summarize conversation from the clean transcript file.\n\n## Grok share links\n\nFor `x.com\u002Fi\u002Fgrok\u002Fshare\u002F\u003Cid>` or `grok.com\u002Fshare\u002F...`:\n\n```bash\nbash \"$HOME\u002F.grok\u002Fskills\u002Fsafari-browser\u002Fscripts\u002Fsafari_read_page.sh\" \\\n  'https:\u002F\u002Fx.com\u002Fi\u002Fgrok\u002Fshare\u002F\u003Cid>' \\\n  -o experiments\u002Fgrok-share-\u003Cid>\u002Fsafari_transcript.txt\n```\n\n## Script files\n\n| File | Role |\n|------|------|\n| `scripts\u002Fsafari_read_page.sh` | **Happy path entry point** |\n| `scripts\u002Fsafari_extract_fast.py` | AppleScript innerText extraction |\n| `scripts\u002Fsafari_open.sh` | Navigate Safari to URL |\n| `scripts\u002Fsafari_extract.py` | Wrapper; `--method fast` (default) or `webdriver` |\n| `references\u002Fgrok-com-computer-use.md` | **Interactive grok.com** OCU\u002FSafari playbook (modes, Copy harvest, OODA) |\n| `references\u002Fgemini-google-computer-use.md` | **Interactive Gemini** UI map (modes, tools, Stop\u002FCopy\u002FRedo, Temporary chat) |\n\n## Limits\n\n- macOS only\n- Requires authenticated Safari session for gated X\u002FGrok content\n- Cannot run inside Linux CI","# Safari Browser (Global Preference)\n\n**Hard rule:** When a task needs a real browser on this Mac, use **Safari only**.\nDo not open Playwright, Chromium, or headless Chrome unless the user explicitly asks.\n\n**Why:** Safari carries the user's live sessions for X, Grok, Google, GitHub, and other services.\n\n## Interactive grok.com (computer use)\n\nFor **live chat** on `https:\u002F\u002Fgrok.com` (model mode Fast\u002FExpert\u002FHeavy, paste prompts, wait for generation, harvest answers), do **not** invent a new approach. Follow the learned playbook:\n\n**[references\u002Fgrok-com-computer-use.md](references\u002Fgrok-com-computer-use.md)**\n\nSummary of hard-won rules:\n- **NEVER BATCH.** Batch is **strictly prohibited.** One Act only, then screenshot + analyze.\n- **ALWAYS screenshot, then analyze.** Decisions come from the image, not key logs.\n- **Screenshot every 3–5 seconds** while operating; determine state each time; then decide.\n- **OODA Loop mandatory:** Observe → Orient → Decide → Act → Observe again.\n- Scroll the full reply only if shots prove content moved; action bar must be **visible in the image** before Copy.\n- **Never retype the URL** if already on grok.com; new chat via **Home page** link.\n- Address bar only when needed: Meta+l → Meta+a → **Backspace** → type URL → **verify field** → Return (OCU `type_text` **appends** even when selected).\n- Mode: **Model select** + real cursor (not avatar **F**).\n- **Harvest after each round:** action bar visible in shot → **Copy at end of that response** → clipboard (`pbpaste`). Not full-page scrape as default.\n\n## Happy path (use this first)\n\nValidated on `x.com\u002Fi\u002Fgrok\u002Fshare\u002F...` Grok conversations (2026-07-08):\n\n```bash\nbash \"$HOME\u002F.grok\u002Fskills\u002Fsafari-browser\u002Fscripts\u002Fsafari_read_page.sh\" \\\n  'https:\u002F\u002Fx.com\u002Fi\u002Fgrok\u002Fshare\u002F\u003Cid>' \\\n  --output experiments\u002F\u003Ctopic>\u002Fsafari_transcript.txt \\\n  --wait 12\n```\n\n**What it does:** `safari_open.sh` → wait 12s → AppleScript `document.body.innerText` in 5k chunks → clean text (~21k chars in \u003C2s after load).\n\n**Do not use:** Playwright, `web_fetch`, raw `source` AppleScript (pre-JS shell), Cmd+A copy (gets URL only), or WebDriver `body.text` (pulls HTML junk). WebDriver `innerText` works but is slower (~22s); reserve for `--method webdriver`.\n\n### One-shot Python (same happy path)\n\n```bash\npython3 \"$HOME\u002F.grok\u002Fskills\u002Fsafari-browser\u002Fscripts\u002Fsafari_extract_fast.py\" \\\n  '\u003Curl>' --output transcript.txt --wait 12\n```\n\n### Read current tab (already open in Safari)\n\n```bash\npython3 \"$HOME\u002F.grok\u002Fskills\u002Fsafari-browser\u002Fscripts\u002Fsafari_extract_fast.py\" \\\n  '\u003Curl>' --no-open --output transcript.txt --wait 2\n```\n\n## Prerequisites (enabled on this machine)\n\nSafari → Settings → Developer:\n\n| Setting | Required for happy path |\n|---------|-------------------------|\n| **Allow JavaScript from Apple Events** | Yes — `safari_extract_fast.py` |\n| **Allow remote automation** | Optional — WebDriver fallback only |\n\n## Decision order\n\n1. **`safari_read_page.sh` \u002F `safari_extract_fast.py`** — default for all page reads\n2. **`safari_open.sh`** — navigation only\n3. **`safari_extract.py --method webdriver`** — scroll-heavy pages if fast path insufficient\n4. **UI scripting** — last resort only\n5. **Playwright** — forbidden unless user explicitly overrides\n\n## Agent workflow\n\n1. **Do not** reach for Playwright or `read_share.sh` (Playwright) for X-hosted Grok shares.\n2. Run `safari_read_page.sh` with `--output` under `experiments\u002F\u003Ctopic>\u002F`.\n3. If fast path fails, check Developer toggles; do not silently fall back to Playwright.\n4. Save artifact; summarize conversation from the clean transcript file.\n\n## Grok share links\n\nFor `x.com\u002Fi\u002Fgrok\u002Fshare\u002F\u003Cid>` or `grok.com\u002Fshare\u002F...`:\n\n```bash\nbash \"$HOME\u002F.grok\u002Fskills\u002Fsafari-browser\u002Fscripts\u002Fsafari_read_page.sh\" \\\n  'https:\u002F\u002Fx.com\u002Fi\u002Fgrok\u002Fshare\u002F\u003Cid>' \\\n  -o experiments\u002Fgrok-share-\u003Cid>\u002Fsafari_transcript.txt\n```\n\n## Script files\n\n| File | Role |\n|------|------|\n| `scripts\u002Fsafari_read_page.sh` | **Happy path entry point** |\n| `scripts\u002Fsafari_extract_fast.py` | AppleScript innerText extraction |\n| `scripts\u002Fsafari_open.sh` | Navigate Safari to URL |\n| `scripts\u002Fsafari_extract.py` | Wrapper; `--method fast` (default) or `webdriver` |\n| `references\u002Fgrok-com-computer-use.md` | **Interactive grok.com** OCU\u002FSafari playbook (modes, Copy harvest, OODA) |\n| `references\u002Fgemini-google-computer-use.md` | **Interactive Gemini** UI map (modes, tools, Stop\u002FCopy\u002FRedo, Temporary chat) |\n\n## Limits\n\n- macOS only\n- Requires authenticated Safari session for gated X\u002FGrok content\n- Cannot run inside Linux CI",{"name":5,"metadata":24,"description":27},{"version":25,"short-description":26},"1.2.0","Always use Safari for browser automation (authenticated session)","Use Safari (never Playwright\u002FChromium) for all browser automation on this Mac. The user is authenticated in Safari for X, Grok, Google Drive, GitHub, and other web services required by research workflows. Trigger on any browser task: open a URL, scrape a page, read a Grok share, log into a site, fill a form, take a screenshot, debug a web UI, or when Playwright would otherwise be chosen. Happy path: safari_read_page.sh or safari_extract_fast.py (AppleScript innerText). Interactive grok.com chat (modes, send, harvest): see references\u002Fgrok-com-computer-use.md. Interactive gemini.google.com chat: see references\u002Fgemini-google-computer-use.md. Do NOT use Playwright unless the user explicitly overrides this preference.\n","main","d9535210da9af28aa76bca80de80355197e1b6d6","skills\u002Fsafari-browser","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog","https:\u002F\u002Fgithub.com\u002Fzfifteen","I like to measure things.","2026-07-19 23:41:54",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add zfifteen\u002Fskills-catalog --skill safari-browser",{"tool":41,"command":42},"bunx","bunx skills add zfifteen\u002Fskills-catalog --skill safari-browser",{"tool":44,"command":45},"pnpm","pnpm dlx skills add zfifteen\u002Fskills-catalog --skill safari-browser","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fsafari-browser\u002FSKILL.md",true,[49,55,59,65,69,73],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fgemini-google-computer-use.md","REFERENCE","参考文档",15425,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fsafari-browser\u002Freferences\u002Fgemini-google-computer-use.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fgrok-com-computer-use.md",14124,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fsafari-browser\u002Freferences\u002Fgrok-com-computer-use.md",{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"scripts\u002Fsafari_extract_fast.py","SCRIPT","脚本",2906,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fsafari-browser\u002Fscripts\u002Fsafari_extract_fast.py",{"path":66,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":67,"sourceHtmlUrl":68},"scripts\u002Fsafari_extract.py",2960,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fsafari-browser\u002Fscripts\u002Fsafari_extract.py",{"path":70,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":71,"sourceHtmlUrl":72},"scripts\u002Fsafari_open.sh",450,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fsafari-browser\u002Fscripts\u002Fsafari_open.sh",{"path":74,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":75,"sourceHtmlUrl":76},"scripts\u002Fsafari_read_page.sh",817,"https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fsafari-browser\u002Fscripts\u002Fsafari_read_page.sh",[78,85,92,99,108,115],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M79GXQ2PWPT2E4CJYHXVJ0YE","Zotero","Use Zotero Desktop from Codex to enable\u002Fprobe the local API, search a local Zotero library, list items\u002Fcollections\u002Ftags, export BibTeX, insert citation keys into LaTeX or Markdown drafts, read indexed full text when requested, and import BibTeX\u002FRIS records into Zotero through the connector server. Use when the user mentions Zotero, citations, references.bib, BibTeX export, local Zotero API, localhost:23119, or adding citations from a Zotero library.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fzotero\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M79GXN85NETKBE06865CWK6Z","zoom-apps-sdk","Use when using Apps SDK.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M79GXCYD7FGYS932J9N9RFFY","youtube","Obtain accurate, timestamped YouTube video transcripts (preferring manual captions over auto-generated) as the primary deliverable, then derive summaries, key claims, or notes from that transcript.  Use when the user provides a YouTube URL (or video ID) and wants the transcript, a faithful summary, key claims with attribution, timestamped notes, or \"what does this video actually say\".  The skill is transcript-first: never substitute metadata, title, description, or search snippets for the spoken content.  Triggers: \"youtube transcript\", \"get the transcript of this video\", \"summarize this youtube video\", \"what did they say in https:\u002F\u002Fyoutube.com\u002F...\", \"key claims from this talk\".","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":103,"licenseFileUrl":104,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M79GX8EXHHYM566BKR7MS778","yeet","Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M79GX2HFJPX84NMRE5VBTYX9","x-post-creator","Create X-ready post threads and co-located story packages from the active conversation or referenced project material. Use when the user says turn this into an X-post, \u002Fx-post, make this into an X thread, or wants plain-language social posts with supporting images saved to docs\u002Fx-posts\u002F[story-name]\u002F.","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fx-post-creator\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":19},"01M79GWXQT4HBT6QME6QSBZJFA","x-api","Search, read, and write X posts through the local X API MCP server (the same backend used by the Codex x-api skill). Use for searching X\u002Fx.com, reading threads and replies, creating lists, staging\u002Fpublishing posts for @alltheputs, finding high-visibility reply targets for research outreach, ingesting public context, or any request that mentions \u002Fx-api or \"search X\".","https:\u002F\u002Fgithub.com\u002Fzfifteen\u002Fskills-catalog\u002Fblob\u002Fmain\u002Fskills\u002Fx-api\u002FSKILL.md",[],[]]