[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75K88AQJ1QFFPVGXECD4WMY":3,"skill-same:01M75K88AQJ1QFFPVGXECD4WMY":64},{"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":37,"commitSha":38,"skillDirectory":39,"forksCount":14,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":43,"updatedAt":44,"install":45,"resources":57},"01M75K88AQJ1QFFPVGXECD4WMY","article-enrichment",null,"Transform raw article text dumps in the brain into structured pages with executive summary, verbatim quotes, key insights, why-it-matters, and cross-references. Replaces walls-of-text with quotable, actionable brain pages.","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\u002Farticle-enrichment\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: article-enrichment\nversion: 0.1.0\ndescription: Transform raw article text dumps in the brain into structured pages with executive summary, verbatim quotes, key insights, why-it-matters, and cross-references. Replaces walls-of-text with quotable, actionable brain pages.\ntriggers:\n  - \"enrich this article\"\n  - \"enrich the article\"\n  - \"enriching the article\"\n  - \"enrich brain pages\"\n  - \"batch enrich\"\n  - \"enrich pass\"\n  - \"make brain pages useful\"\nmutating: true\nwrites_pages: true\nwrites_to:\n  - media\u002Farticles\u002F\nwhen_to_use: \"Use when the user asks: \\\"enrich this article\\\", \\\"enrich the article\\\", \\\"enriching the article\\\", \\\"enrich brain pages\\\", \\\"batch enrich\\\".\"\n---\n\n# article-enrichment — From Raw Dumps to Useful Brain Pages\n\n> **Convention:** see [conventions\u002Fquality.md](..\u002Fconventions\u002Fquality.md) for\n> citation rules, verbatim-quote requirements, and back-link enforcement.\n>\n> **Convention:** see [_brain-filing-rules.md](..\u002F_brain-filing-rules.md) for\n> filing rules. Article pages live under `media\u002Farticles\u002F` for raw ingest;\n> personalized one-of-one synthesis output uses the sanctioned\n> `media\u002Farticles\u002F\u003Cslug>-personalized.md` exception.\n\n## What this does\n\nTakes an article brain page that's a wall of raw extracted text and rewrites\nit as a structured page with:\n\n- **Executive Summary** — 2-3 sentences, the ONE thing worth remembering\n- **Why It Matters** — connects to the user's specific projects + interests\n  (read from brain context, not assumed)\n- **Quotable Lines** — 3-5 VERBATIM quotes worth referencing in essays\n- **Key Insights** — actual insights, not topic labels\n- **Surprising or Counterintuitive** — what makes this content unique\n- **See Also** — standard markdown links to related brain pages\n\nRaw source content is preserved in a collapsed `\u003Cdetails>` section so the\noriginal is never lost.\n\n## When to invoke\n\n- New article page lands in the brain via media-ingest with `needs_enrichment: true`\n- Existing article page is a wall of text under a `## Content` header with\n  no synthesis\n- User says a brain page is useless, boring, or a dump\n- An LLM-judge brain-quality eval fails on quotability or actionability for\n  an article page\n\n## The pipeline\n\n```\n1. READ      → Open the article brain page; parse frontmatter + body.\n2. SCAN      → Look for ## Content (raw dump) and absence of ## Executive Summary.\n3. CONTEXT   → gbrain query the article's key entities to ground \"Why It Matters\".\n4. ENRICH    → Sonnet (default) or Opus (for high-value content) restructures.\n5. WRITE     → Replace ## Content with the structured sections; preserve raw\n               source in \u003Cdetails>; clear needs_enrichment in frontmatter.\n6. CROSS-LINK→ Add back-links from referenced people\u002Fcompanies pages\n               (Iron Law per conventions\u002Fquality.md).\n```\n\n## Invocation\n\nThe skill itself is markdown instructions to the agent. It does NOT ship a\ndeterministic CLI command in v0.25.1. The agent uses gbrain's existing\noperations:\n\n```bash\n# 1. Find candidate pages\ngbrain query \"needs_enrichment: true type:article\" --limit 50\n\n# 2. For each candidate, read the page\ngbrain get media\u002Farticles\u002F\u003Cslug>\n\n# 3. Enrich via the agent's LLM (Sonnet by default; Opus for high-value)\n#    The agent reads the raw content + brain context + writes the structured page.\n\n# 4. Write the enriched page\n#    Use the put_page operation with the new structured markdown body.\n\n# 5. Cross-link entities\n#    For every person\u002Fcompany mentioned, add a timeline back-link.\n```\n\n## Quality bar\n\nAn enriched page passes if it has:\n\n- ✅ `## Executive Summary` (2-3 sentences)\n- ✅ `## Quotable Lines` with ≥3 verbatim quotes (literal quotes, not paraphrase)\n- ✅ `## Key Insights` with ≥3 bullets (insights, not topic labels)\n- ✅ `## Why It Matters` connecting to specific brain context (not generic)\n- ✅ `## See Also` with standard markdown links (NOT `[[wiki-links]]`)\n- ✅ `\u003Cdetails>` block preserving the raw source content\n\n## Model selection\n\n| Model | Use when | Quote accuracy |\n|-------|----------|----------------|\n| **Sonnet** (default) | Bulk enrichment, most articles | Good — occasionally paraphrases |\n| **Opus** | High-value content, original-thinking pieces, longreads | Excellent — respects \"verbatim\" instruction |\n\nRule: for bulk enrichment, do a Sonnet draft pass and spot-check 5 with\nthe LLM-judge brain-quality eval. If quotes are paraphrased, switch to\nOpus for that batch.\n\n## Link convention\n\nAll cross-references use standard markdown links: `[Title](relative\u002Fpath.md)`.\nNEVER use `[[wiki-links]]` — they don't render on GitHub.\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- `get_page` returns `page_not_found`: the raw dump moved or the slug is wrong; search for the title before reporting the article missing.\n- The rewrite returns `revision_conflict`: someone else edited the page since you read it. Re-read, re-apply the enrichment to the new text, and save with the new revision; never overwrite blind.\n- `write_pending` (exit 10): poll `gbrain write-request \u003Crequest_id>`; only report the page enriched once the receipt commits.\n\n## Anti-Patterns\n\n- ❌ Paraphrasing quotes (\"the author argues that…\"). Quotes are verbatim\n  or they're not quotes.\n- ❌ Generic \"Why It Matters\" (\"this is important because innovation\").\n  Tie to specific brain context or remove the section.\n- ❌ Inventing topic labels and calling them insights. An insight is a\n  thing the article says that you didn't already know.\n- ❌ Discarding the raw source. Always wrap it in `\u003Cdetails>`.\n- ❌ Re-enriching non-idempotently — check the `needs_enrichment` flag in\n  frontmatter; skip if already false.\n\n## Related skills\n\n- `skills\u002Fmedia-ingest\u002FSKILL.md` — creates the raw article pages this skill enriches\n- `skills\u002Fidea-ingest\u002FSKILL.md` — link\u002Farticle ingestion with author people-page enforcement\n- `skills\u002Fconventions\u002Fquality.md` — citation + back-link rules\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","# article-enrichment — From Raw Dumps to Useful Brain Pages\n\n> **Convention:** see [conventions\u002Fquality.md](..\u002Fconventions\u002Fquality.md) for\n> citation rules, verbatim-quote requirements, and back-link enforcement.\n>\n> **Convention:** see [_brain-filing-rules.md](..\u002F_brain-filing-rules.md) for\n> filing rules. Article pages live under `media\u002Farticles\u002F` for raw ingest;\n> personalized one-of-one synthesis output uses the sanctioned\n> `media\u002Farticles\u002F\u003Cslug>-personalized.md` exception.\n\n## What this does\n\nTakes an article brain page that's a wall of raw extracted text and rewrites\nit as a structured page with:\n\n- **Executive Summary** — 2-3 sentences, the ONE thing worth remembering\n- **Why It Matters** — connects to the user's specific projects + interests\n  (read from brain context, not assumed)\n- **Quotable Lines** — 3-5 VERBATIM quotes worth referencing in essays\n- **Key Insights** — actual insights, not topic labels\n- **Surprising or Counterintuitive** — what makes this content unique\n- **See Also** — standard markdown links to related brain pages\n\nRaw source content is preserved in a collapsed `\u003Cdetails>` section so the\noriginal is never lost.\n\n## When to invoke\n\n- New article page lands in the brain via media-ingest with `needs_enrichment: true`\n- Existing article page is a wall of text under a `## Content` header with\n  no synthesis\n- User says a brain page is useless, boring, or a dump\n- An LLM-judge brain-quality eval fails on quotability or actionability for\n  an article page\n\n## The pipeline\n\n```\n1. READ      → Open the article brain page; parse frontmatter + body.\n2. SCAN      → Look for ## Content (raw dump) and absence of ## Executive Summary.\n3. CONTEXT   → gbrain query the article's key entities to ground \"Why It Matters\".\n4. ENRICH    → Sonnet (default) or Opus (for high-value content) restructures.\n5. WRITE     → Replace ## Content with the structured sections; preserve raw\n               source in \u003Cdetails>; clear needs_enrichment in frontmatter.\n6. CROSS-LINK→ Add back-links from referenced people\u002Fcompanies pages\n               (Iron Law per conventions\u002Fquality.md).\n```\n\n## Invocation\n\nThe skill itself is markdown instructions to the agent. It does NOT ship a\ndeterministic CLI command in v0.25.1. The agent uses gbrain's existing\noperations:\n\n```bash\n# 1. Find candidate pages\ngbrain query \"needs_enrichment: true type:article\" --limit 50\n\n# 2. For each candidate, read the page\ngbrain get media\u002Farticles\u002F\u003Cslug>\n\n# 3. Enrich via the agent's LLM (Sonnet by default; Opus for high-value)\n#    The agent reads the raw content + brain context + writes the structured page.\n\n# 4. Write the enriched page\n#    Use the put_page operation with the new structured markdown body.\n\n# 5. Cross-link entities\n#    For every person\u002Fcompany mentioned, add a timeline back-link.\n```\n\n## Quality bar\n\nAn enriched page passes if it has:\n\n- ✅ `## Executive Summary` (2-3 sentences)\n- ✅ `## Quotable Lines` with ≥3 verbatim quotes (literal quotes, not paraphrase)\n- ✅ `## Key Insights` with ≥3 bullets (insights, not topic labels)\n- ✅ `## Why It Matters` connecting to specific brain context (not generic)\n- ✅ `## See Also` with standard markdown links (NOT `[[wiki-links]]`)\n- ✅ `\u003Cdetails>` block preserving the raw source content\n\n## Model selection\n\n| Model | Use when | Quote accuracy |\n|-------|----------|----------------|\n| **Sonnet** (default) | Bulk enrichment, most articles | Good — occasionally paraphrases |\n| **Opus** | High-value content, original-thinking pieces, longreads | Excellent — respects \"verbatim\" instruction |\n\nRule: for bulk enrichment, do a Sonnet draft pass and spot-check 5 with\nthe LLM-judge brain-quality eval. If quotes are paraphrased, switch to\nOpus for that batch.\n\n## Link convention\n\nAll cross-references use standard markdown links: `[Title](relative\u002Fpath.md)`.\nNEVER use `[[wiki-links]]` — they don't render on GitHub.\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- `get_page` returns `page_not_found`: the raw dump moved or the slug is wrong; search for the title before reporting the article missing.\n- The rewrite returns `revision_conflict`: someone else edited the page since you read it. Re-read, re-apply the enrichment to the new text, and save with the new revision; never overwrite blind.\n- `write_pending` (exit 10): poll `gbrain write-request \u003Crequest_id>`; only report the page enriched once the receipt commits.\n\n## Anti-Patterns\n\n- ❌ Paraphrasing quotes (\"the author argues that…\"). Quotes are verbatim\n  or they're not quotes.\n- ❌ Generic \"Why It Matters\" (\"this is important because innovation\").\n  Tie to specific brain context or remove the section.\n- ❌ Inventing topic labels and calling them insights. An insight is a\n  thing the article says that you didn't already know.\n- ❌ Discarding the raw source. Always wrap it in `\u003Cdetails>`.\n- ❌ Re-enriching non-idempotently — check the `needs_enrichment` flag in\n  frontmatter; skip if already false.\n\n## Related skills\n\n- `skills\u002Fmedia-ingest\u002FSKILL.md` — creates the raw article pages this skill enriches\n- `skills\u002Fidea-ingest\u002FSKILL.md` — link\u002Farticle ingestion with author people-page enforcement\n- `skills\u002Fconventions\u002Fquality.md` — citation + back-link rules\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,"mutating":25,"triggers":26,"writes_to":34,"description":7,"when_to_use":36,"writes_pages":25},"0.1.0",true,[27,28,29,30,31,32,33],"enrich this article","enrich the article","enriching the article","enrich brain pages","batch enrich","enrich pass","make brain pages useful",[35],"media\u002Farticles\u002F","Use when the user asks: \"enrich this article\", \"enrich the article\", \"enriching the article\", \"enrich brain pages\", \"batch enrich\".","feat\u002Flink-chat-distiller","b7935e119783c2f35d6d182ede452faf32de675c","plugin\u002Fskills\u002Farticle-enrichment","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":46,"prompt":56,"zipAvailable":25},[47,50,53],{"tool":48,"command":49},"npx","npx skills add cheRoma\u002Fgbrain-link-chat --skill article-enrichment",{"tool":51,"command":52},"bunx","bunx skills add cheRoma\u002Fgbrain-link-chat --skill article-enrichment",{"tool":54,"command":55},"pnpm","pnpm dlx skills add cheRoma\u002Fgbrain-link-chat --skill article-enrichment","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Fplugin\u002Fskills\u002Farticle-enrichment\u002FSKILL.md",[58],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"routing-eval.jsonl","OTHER","其他",1029,"https:\u002F\u002Fgithub.com\u002FcheRoma\u002Fgbrain-link-chat\u002Fblob\u002Ffeat\u002Flink-chat-distiller\u002Fplugin\u002Fskills\u002Farticle-enrichment\u002Frouting-eval.jsonl",[65,71,77,84,91,98],{"skillNo":66,"name":67,"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":68,"categories":69,"keywords":70,"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":72,"name":73,"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":74,"categories":75,"keywords":76,"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":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"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":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"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",[],[]]