[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75K9S2BYQ23DJ4HT4D7YJDC":3,"skill-same:01M75K9S2BYQ23DJ4HT4D7YJDC":60},{"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":32,"commitSha":33,"skillDirectory":34,"forksCount":14,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":37,"ownerDescription":38,"updatedAt":39,"install":40,"resources":53},"01M75K9S2BYQ23DJ4HT4D7YJDC","brain-pdf",null,"Generate a publication-quality PDF from any brain page via the gstack make-pdf binary. Strips YAML frontmatter, sanitizes emoji, applies running headers and page numbers. Brain page is always the source of truth; PDF is a rendering.","cheRoma\u002Fgbrain-link-chat","cheRoma","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F265356812?v=4","01M75JVGAJEZK04E1THSDHYVNK","Roman Cherepanov","01M75JVGB5SWY40H959C3QXRAQ",0,"MIT","https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Fplugin\u002Fskills\u002Fbrain-pdf\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: brain-pdf\nversion: 0.1.0\ndescription: Generate a publication-quality PDF from any brain page via the gstack make-pdf binary. Strips YAML frontmatter, sanitizes emoji, applies running headers and page numbers. Brain page is always the source of truth; PDF is a rendering.\ntriggers:\n  - \"make pdf from brain\"\n  - \"brain pdf\"\n  - \"convert brain page to pdf\"\n  - \"publish this page as pdf\"\n  - \"export brain page\"\nwhen_to_use: \"Use when the user asks: \\\"make pdf from brain\\\", \\\"brain pdf\\\", \\\"convert brain page to pdf\\\", \\\"publish this page as pdf\\\", \\\"export brain page\\\".\"\n---\n\n# brain-pdf — Render a Brain Page to Publication-Quality PDF\n\n> **Convention:** see [conventions\u002Fquality.md](..\u002Fconventions\u002Fquality.md) for\n> output rules. The PDF is a rendering — never the primary artifact. If a\n> PDF exists, the source brain page exists behind it.\n\n## The rule\n\nThe brain page is ALWAYS the source of truth. The PDF is a rendering of\nit, never a standalone artifact. If a PDF exists somewhere, the brain\npage must exist behind it.\n\n## What this does\n\nRenders a brain page (markdown with frontmatter) into a\npublication-quality PDF using the gstack `make-pdf` binary. Output is\nsuitable for:\n\n- Sharing a personalized book mirror via email or Telegram\n- Delivering a strategic-reading playbook as a clean read\n- Producing a briefing or report with running headers and page numbers\n- Archiving a long-form essay in a portable format\n\n## Prerequisite: gstack make-pdf\n\nThis skill depends on the gstack `make-pdf` binary at:\n\n```\n$HOME\u002F.claude\u002Fskills\u002Fgstack\u002Fmake-pdf\u002Fdist\u002Fpdf\n```\n\nThe user must have gstack co-installed. If absent, the skill cannot run.\nA future v0.26+ may bundle a fallback PDF renderer; for v0.25.1 gstack\nis a soft prereq.\n\nVerify it exists before invoking:\n\n```bash\nP=\"$HOME\u002F.claude\u002Fskills\u002Fgstack\u002Fmake-pdf\u002Fdist\u002Fpdf\"\n[ -x \"$P\" ] || { echo \"make-pdf not installed; install gstack\" >&2; exit 1; }\n```\n\n## Workflow\n\n```\n1. RESOLVE  → Confirm the brain page exists (gbrain get \u003Cslug>).\n2. STRIP    → Remove YAML frontmatter — the renderer would otherwise\n              dump it as a full page of raw metadata text.\n3. RENDER   → Invoke make-pdf with sane defaults (no --cover, no --toc).\n4. DELIVER  → Hand the PDF to the requester via the agent's preferred\n              channel (do not use raw `MEDIA:` tags on Telegram —\n              they fail silently).\n```\n\n## Invocation\n\n```bash\nSLUG=\"path\u002Fto\u002Fpage\"\nP=\"$HOME\u002F.claude\u002Fskills\u002Fgstack\u002Fmake-pdf\u002Fdist\u002Fpdf\"\n\n# 1. Confirm the page exists.\ngbrain get \"$SLUG\" > \u002Fdev\u002Fnull || { echo \"Page $SLUG not found\" >&2; exit 1; }\n\n# 2. Get the raw markdown. Two paths: read from the brain repo (if user\n#    syncs locally) OR ask gbrain for the body via the API.\nBRAIN_DIR=$(gbrain config get sync.repo_path 2>\u002Fdev\u002Fnull || echo)\nif [ -n \"$BRAIN_DIR\" ] && [ -f \"$BRAIN_DIR\u002F$SLUG.md\" ]; then\n  RAW=\"$BRAIN_DIR\u002F$SLUG.md\"\nelse\n  RAW=$(mktemp \u002Ftmp\u002Fbrain-page-XXXXXX.md)\n  gbrain get \"$SLUG\" > \"$RAW\"   # prints the page as markdown with frontmatter\nfi\n\n# 3. Strip the leading YAML frontmatter block only: line 1 '---' through\n#    the next '---'. A later '---' (a horizontal rule) and a page without\n#    frontmatter are kept as written. Plain awk, so it behaves the same with\n#    BSD (macOS) and GNU tools. Stop if nothing is left to render.\nCLEAN=$(mktemp \u002Ftmp\u002Fbrain-page-clean-XXXXXX.md)\nawk 'NR==1 && \u002F^---[[:space:]]*$\u002F {f=1; next} f==1 && \u002F^---[[:space:]]*$\u002F {f=2; next} f!=1' \"$RAW\" > \"$CLEAN\"\n[ -s \"$CLEAN\" ] || { echo \"brain-pdf: nothing to render for $SLUG after removing frontmatter\" >&2; exit 1; }\n\n# 4. Render. NO --cover, NO --toc by default — they look corporate\n#    and waste space. Add them only if explicitly requested.\nOUT=\"\u002Ftmp\u002F$(basename \"$SLUG\").pdf\"\nCONTAINER=1 \"$P\" generate \"$CLEAN\" \"$OUT\"\n\necho \"Rendered: $OUT\"\n```\n\n`CONTAINER=1` is mandatory in containerized environments — it tells\nPlaywright to skip Chromium sandboxing. Harmless on bare-metal.\n\n## Common patterns\n\n```bash\n# Default — clean PDF, no cover, no TOC\nbrain-pdf \u003Cslug>\n\n# Draft watermark for in-progress work\nCONTAINER=1 \"$P\" generate --watermark DRAFT \"$CLEAN\" \"$OUT\"\n\n# Optional cover + TOC if the user explicitly asks\nCONTAINER=1 \"$P\" generate --cover --toc \"$CLEAN\" \"$OUT\"\n\n# Custom title + author override (otherwise pulled from frontmatter)\nCONTAINER=1 \"$P\" generate --title \"Custom Title\" --author \"Custom Author\" \"$CLEAN\" \"$OUT\"\n```\n\n## Defaults: NO cover, NO TOC\n\nThese flags are off by default because they look corporate and waste\nspace on most personal-knowledge content. Only add them when the user\nexplicitly asks for \"formal\" output (e.g., something they're sending to\na board or printing as a deliverable).\n\n## Font requirements\n\nThe renderer needs:\n\n- `fonts-liberation` (Helvetica\u002FArial substitute)\n- `fonts-noto-cjk` (Chinese\u002FJapanese\u002FKorean characters)\n- Minimum body font size: 10pt (page chrome 9pt)\n- Body text: 11pt\n\nIf running in an environment without these fonts, install them via the\nhost's package manager (`apt install fonts-liberation fonts-noto-cjk` on\nDebian\u002FUbuntu containers).\n\n## Delivery\n\nAfter rendering, deliver via the agent's preferred channel:\n\n- **Telegram:** use the `message` tool with `filePath=\"\u002Ftmp\u002F\u003Cslug>.pdf\"`\n  attachment. NEVER use raw `MEDIA:` tags — they fail silently.\n- **Email:** attach via the host's email tool.\n- **Direct file response:** print the PDF path; the user can pull it\n  manually.\n\nAlways include the brain page link in the delivery message so the user\ncan also see it on GitHub \u002F locally. The PDF is a rendering; the source\nis the artifact.\n\n## When it fails\n\nFollow the [agent operator protocol](..\u002Fconventions\u002Fagent-operator-protocol.md) for any gbrain error `code`, exit code, `[AGENT]` block or notice block. Specific to this skill:\n\n- `gbrain get \u003Cslug>` fails with `page_not_found`: stop before rendering and resolve the real slug; report the page missing only after a title search.\n- The make-pdf binary is missing: this is a gstack dependency, not a gbrain error. Tell the user to install gstack; do not hand-roll a PDF.\n\n## Anti-Patterns\n\n- ❌ Generating a PDF without first confirming the brain page exists.\n  No source = no PDF.\n- ❌ Skipping the frontmatter strip. The renderer dumps frontmatter as\n  raw text on the first page; ugly.\n- ❌ Skipping emoji sanitization. Emoji that don't map to the rendering\n  font show up as `□` boxes.\n- ❌ Adding `--cover` or `--toc` by default. Off unless asked.\n- ❌ Using raw `MEDIA:` tags for Telegram delivery. Use the `message`\n  tool with `filePath`.\n\n## Related skills\n\n- `skills\u002Fbook-mirror\u002FSKILL.md` — produces a brain page that's a\n  natural input to brain-pdf (chapter-by-chapter personalized analysis).\n- `skills\u002Fstrategic-reading\u002FSKILL.md` — same shape, problem-lens variant.\n- `skills\u002Fpublish\u002FSKILL.md` — share brain pages as password-protected\n  HTML (different rendering target).\n\n\n## Contract\n\nThis skill guarantees:\n\n- Routing matches the canonical triggers in the frontmatter.\n- Output written under the directories listed in `writes_to:` (when applicable).\n- Conventions referenced (`quality.md`, `brain-first.md`, `_brain-filing-rules.md`) are followed.\n- Privacy contract preserved: no real names, no fork-specific filesystem path literals, no upstream-fork references.\n\nThe full behavior contract is documented in the body sections above; this section exists for the conformance test.\n\n## Output Format\n\nThe skill's output shape is documented inline in the body sections above (see \"Output\", \"Brain page format\", or equivalent). The literal section header here exists for the conformance test (`test\u002Fskills-conformance.test.ts`).\n","# brain-pdf — Render a Brain Page to Publication-Quality PDF\n\n> **Convention:** see [conventions\u002Fquality.md](..\u002Fconventions\u002Fquality.md) for\n> output rules. The PDF is a rendering — never the primary artifact. If a\n> PDF exists, the source brain page exists behind it.\n\n## The rule\n\nThe brain page is ALWAYS the source of truth. The PDF is a rendering of\nit, never a standalone artifact. If a PDF exists somewhere, the brain\npage must exist behind it.\n\n## What this does\n\nRenders a brain page (markdown with frontmatter) into a\npublication-quality PDF using the gstack `make-pdf` binary. Output is\nsuitable for:\n\n- Sharing a personalized book mirror via email or Telegram\n- Delivering a strategic-reading playbook as a clean read\n- Producing a briefing or report with running headers and page numbers\n- Archiving a long-form essay in a portable format\n\n## Prerequisite: gstack make-pdf\n\nThis skill depends on the gstack `make-pdf` binary at:\n\n```\n$HOME\u002F.claude\u002Fskills\u002Fgstack\u002Fmake-pdf\u002Fdist\u002Fpdf\n```\n\nThe user must have gstack co-installed. If absent, the skill cannot run.\nA future v0.26+ may bundle a fallback PDF renderer; for v0.25.1 gstack\nis a soft prereq.\n\nVerify it exists before invoking:\n\n```bash\nP=\"$HOME\u002F.claude\u002Fskills\u002Fgstack\u002Fmake-pdf\u002Fdist\u002Fpdf\"\n[ -x \"$P\" ] || { echo \"make-pdf not installed; install gstack\" >&2; exit 1; }\n```\n\n## Workflow\n\n```\n1. RESOLVE  → Confirm the brain page exists (gbrain get \u003Cslug>).\n2. STRIP    → Remove YAML frontmatter — the renderer would otherwise\n              dump it as a full page of raw metadata text.\n3. RENDER   → Invoke make-pdf with sane defaults (no --cover, no --toc).\n4. DELIVER  → Hand the PDF to the requester via the agent's preferred\n              channel (do not use raw `MEDIA:` tags on Telegram —\n              they fail silently).\n```\n\n## Invocation\n\n```bash\nSLUG=\"path\u002Fto\u002Fpage\"\nP=\"$HOME\u002F.claude\u002Fskills\u002Fgstack\u002Fmake-pdf\u002Fdist\u002Fpdf\"\n\n# 1. Confirm the page exists.\ngbrain get \"$SLUG\" > \u002Fdev\u002Fnull || { echo \"Page $SLUG not found\" >&2; exit 1; }\n\n# 2. Get the raw markdown. Two paths: read from the brain repo (if user\n#    syncs locally) OR ask gbrain for the body via the API.\nBRAIN_DIR=$(gbrain config get sync.repo_path 2>\u002Fdev\u002Fnull || echo)\nif [ -n \"$BRAIN_DIR\" ] && [ -f \"$BRAIN_DIR\u002F$SLUG.md\" ]; then\n  RAW=\"$BRAIN_DIR\u002F$SLUG.md\"\nelse\n  RAW=$(mktemp \u002Ftmp\u002Fbrain-page-XXXXXX.md)\n  gbrain get \"$SLUG\" > \"$RAW\"   # prints the page as markdown with frontmatter\nfi\n\n# 3. Strip the leading YAML frontmatter block only: line 1 '---' through\n#    the next '---'. A later '---' (a horizontal rule) and a page without\n#    frontmatter are kept as written. Plain awk, so it behaves the same with\n#    BSD (macOS) and GNU tools. Stop if nothing is left to render.\nCLEAN=$(mktemp \u002Ftmp\u002Fbrain-page-clean-XXXXXX.md)\nawk 'NR==1 && \u002F^---[[:space:]]*$\u002F {f=1; next} f==1 && \u002F^---[[:space:]]*$\u002F {f=2; next} f!=1' \"$RAW\" > \"$CLEAN\"\n[ -s \"$CLEAN\" ] || { echo \"brain-pdf: nothing to render for $SLUG after removing frontmatter\" >&2; exit 1; }\n\n# 4. Render. NO --cover, NO --toc by default — they look corporate\n#    and waste space. Add them only if explicitly requested.\nOUT=\"\u002Ftmp\u002F$(basename \"$SLUG\").pdf\"\nCONTAINER=1 \"$P\" generate \"$CLEAN\" \"$OUT\"\n\necho \"Rendered: $OUT\"\n```\n\n`CONTAINER=1` is mandatory in containerized environments — it tells\nPlaywright to skip Chromium sandboxing. Harmless on bare-metal.\n\n## Common patterns\n\n```bash\n# Default — clean PDF, no cover, no TOC\nbrain-pdf \u003Cslug>\n\n# Draft watermark for in-progress work\nCONTAINER=1 \"$P\" generate --watermark DRAFT \"$CLEAN\" \"$OUT\"\n\n# Optional cover + TOC if the user explicitly asks\nCONTAINER=1 \"$P\" generate --cover --toc \"$CLEAN\" \"$OUT\"\n\n# Custom title + author override (otherwise pulled from frontmatter)\nCONTAINER=1 \"$P\" generate --title \"Custom Title\" --author \"Custom Author\" \"$CLEAN\" \"$OUT\"\n```\n\n## Defaults: NO cover, NO TOC\n\nThese flags are off by default because they look corporate and waste\nspace on most personal-knowledge content. Only add them when the user\nexplicitly asks for \"formal\" output (e.g., something they're sending to\na board or printing as a deliverable).\n\n## Font requirements\n\nThe renderer needs:\n\n- `fonts-liberation` (Helvetica\u002FArial substitute)\n- `fonts-noto-cjk` (Chinese\u002FJapanese\u002FKorean characters)\n- Minimum body font size: 10pt (page chrome 9pt)\n- Body text: 11pt\n\nIf running in an environment without these fonts, install them via the\nhost's package manager (`apt install fonts-liberation fonts-noto-cjk` on\nDebian\u002FUbuntu containers).\n\n## Delivery\n\nAfter rendering, deliver via the agent's preferred channel:\n\n- **Telegram:** use the `message` tool with `filePath=\"\u002Ftmp\u002F\u003Cslug>.pdf\"`\n  attachment. NEVER use raw `MEDIA:` tags — they fail silently.\n- **Email:** attach via the host's email tool.\n- **Direct file response:** print the PDF path; the user can pull it\n  manually.\n\nAlways include the brain page link in the delivery message so the user\ncan also see it on GitHub \u002F locally. The PDF is a rendering; the source\nis the artifact.\n\n## When it fails\n\nFollow the [agent operator protocol](..\u002Fconventions\u002Fagent-operator-protocol.md) for any gbrain error `code`, exit code, `[AGENT]` block or notice block. Specific to this skill:\n\n- `gbrain get \u003Cslug>` fails with `page_not_found`: stop before rendering and resolve the real slug; report the page missing only after a title search.\n- The make-pdf binary is missing: this is a gstack dependency, not a gbrain error. Tell the user to install gstack; do not hand-roll a PDF.\n\n## Anti-Patterns\n\n- ❌ Generating a PDF without first confirming the brain page exists.\n  No source = no PDF.\n- ❌ Skipping the frontmatter strip. The renderer dumps frontmatter as\n  raw text on the first page; ugly.\n- ❌ Skipping emoji sanitization. Emoji that don't map to the rendering\n  font show up as `□` boxes.\n- ❌ Adding `--cover` or `--toc` by default. Off unless asked.\n- ❌ Using raw `MEDIA:` tags for Telegram delivery. Use the `message`\n  tool with `filePath`.\n\n## Related skills\n\n- `skills\u002Fbook-mirror\u002FSKILL.md` — produces a brain page that's a\n  natural input to brain-pdf (chapter-by-chapter personalized analysis).\n- `skills\u002Fstrategic-reading\u002FSKILL.md` — same shape, problem-lens variant.\n- `skills\u002Fpublish\u002FSKILL.md` — share brain pages as password-protected\n  HTML (different rendering target).\n\n\n## Contract\n\nThis skill guarantees:\n\n- Routing matches the canonical triggers in the frontmatter.\n- Output written under the directories listed in `writes_to:` (when applicable).\n- Conventions referenced (`quality.md`, `brain-first.md`, `_brain-filing-rules.md`) are followed.\n- Privacy contract preserved: no real names, no fork-specific filesystem path literals, no upstream-fork references.\n\nThe full behavior contract is documented in the body sections above; this section exists for the conformance test.\n\n## Output Format\n\nThe skill's output shape is documented inline in the body sections above (see \"Output\", \"Brain page format\", or equivalent). The literal section header here exists for the conformance test (`test\u002Fskills-conformance.test.ts`).\n",{"name":5,"version":24,"triggers":25,"description":7,"when_to_use":31},"0.1.0",[26,27,28,29,30],"make pdf from brain","brain pdf","convert brain page to pdf","publish this page as pdf","export brain page","Use when the user asks: \"make pdf from brain\", \"brain pdf\", \"convert brain page to pdf\", \"publish this page as pdf\", \"export brain page\".","feat\u002Flink-chat-distiller","b7935e119783c2f35d6d182ede452faf32de675c","plugin\u002Fskills\u002Fbrain-pdf","https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat","https:\u002F\u002Fgithub.com\u002FcheRoma","https:\u002F\u002Fostov.dev","Engineer and founder of Ostov. Websites, Telegram apps, business automation and ERP\u002FCRM integrations.","2026-11-12 20:40:42",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add cheRoma\u002Fgbrain-link-chat --skill brain-pdf",{"tool":46,"command":47},"bunx","bunx skills add cheRoma\u002Fgbrain-link-chat --skill brain-pdf",{"tool":49,"command":50},"pnpm","pnpm dlx skills add cheRoma\u002Fgbrain-link-chat --skill brain-pdf","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Fplugin\u002Fskills\u002Fbrain-pdf\u002FSKILL.md",true,[54],{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"routing-eval.jsonl","OTHER","其他",589,"https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Fplugin\u002Fskills\u002Fbrain-pdf\u002Frouting-eval.jsonl",[61,67,73,80,87,94],{"skillNo":62,"name":63,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M75M5HR90P229V66Q4Q1GM0W","query-helper","https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fquery-helper\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M75M5GZ1WQB7NHR07QV38YB8","broken","https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fbroken\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M75M5FDJV3M4GP71SKD31P33","brain-ops","Read, enrich, and write brain pages with source attribution.","https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fbrain-ops\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M75M5DYW3WBGDC6M90YMC843","meeting-prep","Build a briefing before you meet someone, from their recent threads, open loops and what they care about.","https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Ftest\u002Ffixtures\u002Fskill-catalog-query\u002Fskills\u002Fmeeting-prep\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M75M5CJZX22MV7XKJQYEMC9Y","inbox-zero","Triage the inbox into replies, delegations and archives.","https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Ftest\u002Ffixtures\u002Fskill-catalog-query\u002Fskills\u002Finbox-zero\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M75M5B953478ACM9X3MPAX3P","deal-memo","Draft an investment memo from the deal pages and the founder history already in the brain.","https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Ftest\u002Ffixtures\u002Fskill-catalog-query\u002Fskills\u002Fdeal-memo\u002FSKILL.md",[],[]]