[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6N01WJC9V5MCK9NV0HRBCWV":3,"skill-same:01M6N01WJC9V5MCK9NV0HRBCWV":96},{"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":23,"publishedAt":52,"linkOnly":53,"markdownContent":54,"markdownBody":55,"frontMatter":56,"refName":68,"commitSha":69,"skillDirectory":70,"forksCount":71,"repositoryHtmlUrl":72,"repositoryHomepageUrl":6,"ownerHtmlUrl":73,"ownerBlogUrl":74,"ownerDescription":75,"updatedAt":76,"install":77,"resources":89},"01M6N01WJC9V5MCK9NV0HRBCWV","academic-verify",null,"Verify a research claim or academic citation by tracing it through publication → methodology → raw data → independent replication. Routes through perplexity-research for the actual web lookup, then formats results as a citation-checked brain page. Use when a book\u002Farticle\u002Fconversation cites a study and you want to confirm the claim is real, replicated, and accurately characterized.","garrytan\u002Fgbrain","garrytan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F19957?v=4","01M6DJCCDDG53MTYYRTXAXFG17","Garry Tan","01M6MZQZCEN3RRMD33E1X9ZZR9",32977,"MIT","https:\u002F\u002Fgithub.com\u002Fgarrytan\u002Fgbrain\u002Fblob\u002Fmaster\u002Fplugin\u002Fskills\u002Facademic-verify\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"academic verify","verify","Academic","Publication","research","when","for","true","formats","concepts","you","replication","as","watch","article","brain","claim","study","conversation","use","results","check","page","verify this","perplexity","data","tracing","web","2026-11-10 10:12:30",false,"---\nname: academic-verify\nversion: 0.1.0\ndescription: Verify a research claim or academic citation by tracing it through publication → methodology → raw data → independent replication. Routes through perplexity-research for the actual web lookup, then formats results as a citation-checked brain page. Use when a book\u002Farticle\u002Fconversation cites a study and you want to confirm the claim is real, replicated, and accurately characterized.\ntriggers:\n  - \"verify this academic claim\"\n  - \"check this study\"\n  - \"academic verify\"\n  - \"validate citation\"\n  - \"is this study real\"\n  - \"Retraction Watch\"\nmutating: true\nwrites_pages: true\nwrites_to:\n  - concepts\u002F\nwhen_to_use: \"Use when the user asks: \\\"verify this academic claim\\\", \\\"check this study\\\", \\\"academic verify\\\", \\\"validate citation\\\", \\\"is this study real\\\".\"\n---\n\n# academic-verify — Trace Claims to Source Data\n\n> **Convention:** see [conventions\u002Fquality.md](..\u002Fconventions\u002Fquality.md) for\n> citation rules; every verdict cites the source data, not just the\n> author's claim about the source data.\n>\n> **Convention:** see [conventions\u002Fbrain-first.md](..\u002Fconventions\u002Fbrain-first.md)\n> for the lookup chain. This skill enforces brain-first by checking\n> existing brain pages before issuing a fresh web search.\n\n## What this is\n\nA claim-verification flow for academic \u002F research statements. When a\nbook, article, or speaker cites a study or quotes a number, this skill\ntraces the claim through:\n\n```\nclaim → publication → methodology section → raw data source → independent verification\n```\n\nAt each step, it answers:\n\n- **Where does this number come from?** (Self-generated? Survey? Government data?)\n- **What's the baseline?** (Reduction from what? Over what time period?)\n- **Is the raw data available?** (Public? Proprietary? \"Available on request\"?)\n- **Has anyone independently verified it?** (Replication study? Government audit?)\n- **Are there confounding factors?** (Other interventions, policy changes, COVID, sampling bias?)\n- **Is the comparison fair?** (Cherry-picked comparison group? Survivorship bias?)\n\nThe output is a brain page under `concepts\u002F\u003Cclaim-slug>.md` that records\nthe claim, the trace, and the verdict — so future references to the\nsame claim can re-use the verified analysis.\n\n## When to use this\n\n- A book quotes a study and you want to confirm it's real and not\n  miscited\n- An article makes a quantified claim (\"X reduced Y by 40%\") that you\n  want traced to the source data\n- You're writing something that depends on a piece of research and you\n  want to verify the underlying paper holds up\n- You're updating a brain page that cites a research claim and you want\n  to record the verification status alongside\n\n## What this skill is NOT\n\n- Not adversarial \u002F oppo work. The point is rigor, not takedown.\n- Not generic web research — use `perplexity-research` directly for\n  open-ended topic exploration.\n- Not a brain-only lookup — that's `gbrain query`.\n\n## How it works (D7\u002Fα: pure routing through perplexity-research)\n\nacademic-verify is a thin orchestrator. The actual web search is done\nby [perplexity-research](..\u002Fperplexity-research\u002FSKILL.md). academic-verify's\njob is the *workflow*: scoping the claim precisely, sending it through\nperplexity-research with citation-mode, then formatting the response\ninto a verdict-shaped brain page.\n\n```\nStep 1: Scope the claim\n  Pin down EXACTLY what's being claimed:\n    • Quote: who said what?\n    • Source: which paper \u002F dataset \u002F survey?\n    • Number: what specific quantity is claimed?\n    • Period: over what time range?\n\nStep 2: Brain-first lookup\n  gbrain query \"\u003Cpaper title> OR \u003Cauthor name> OR \u003Cclaim keywords>\"\n  If the brain has prior verification of this claim, reuse it.\n\nStep 3: Invoke perplexity-research with citation-mode prompt\n  Send the claim + brain context to perplexity-research with a prompt\n  that explicitly asks for:\n    • Original publication (title, authors, journal, year, DOI)\n    • Methodology section summary\n    • Raw data availability (public repo? proprietary?)\n    • Independent replication status (Retraction Watch \u002F PubPeer hits)\n    • Citations of the paper that critique or contextualize it\n\nStep 4: Format the verdict\n  Write the result to concepts\u002F\u003Cclaim-slug>.md. The verdict is one of:\n    • Verified — claim is accurate; raw data available; replication exists\n    • Partially verified — claim correct on the underlying paper but\n      methodology has known limits; record limits explicitly\n    • Unverifiable — no public data, no replication; not enough to act\n    • Misattributed — the claim cites a paper but the paper doesn't say that\n    • Retracted \u002F disputed — paper has known retraction or\n      well-documented critique\n\nStep 5: Cross-link to original sources\n  Add the paper authors to people\u002F if they have brain pages, or create\n  one if notable. Iron Law per conventions\u002Fquality.md.\n```\n\n## Output: brain page format\n\n```markdown\n---\ntitle: \"[Claim summary] — Verified\"\ntype: research\ndate: YYYY-MM-DD\nverdict: \"verified|partial|unverifiable|misattributed|retracted\"\nbrain_context_slugs: [\"pages cited as context\"]\n---\n\n# [Claim summary] — Verified\n\n> One-line: the verdict + the bottom-line reason.\n\n## The Claim\n\n> Exact quote, exactly as stated, with source attribution.\n\n## Trace\n\n| Step | Finding | Source |\n|------|---------|--------|\n| Original publication | [Title, authors, year, DOI] | [URL] |\n| Methodology | [1-line summary; flag obvious limits] | [URL] |\n| Raw data | [Public repo \u002F proprietary \u002F available-on-request] | [URL] |\n| Independent replication | [Replication studies and their results] | [URL] |\n| Critical citations | [Papers that critique this work] | [URL] |\n\n## Verdict\n\n[Verified \u002F Partially verified \u002F Unverifiable \u002F Misattributed \u002F Retracted]\n\n[1-2 paragraphs explaining WHY the verdict, with specific evidence.]\n\n## Caveats\n\n[Honest limits: what we couldn't verify, what would change the verdict.]\n\n## See Also\n\n- Original paper: [Title](DOI URL)\n- Authors' brain pages: [Author 1](people\u002Fauthor-1.md), ...\n- Related claims (verified or otherwise): [...]\n```\n\n## Useful databases (the agent uses these via perplexity-research)\n\n| Database | What it has | URL pattern |\n|----------|-------------|-------------|\n| Retraction Watch | Retractions, corrections, expressions of concern | retractionwatch.com\u002F?s=NAME |\n| PubPeer | Anonymous post-publication peer review | pubpeer.com\u002Fsearch?q=NAME |\n| OSF | Pre-registrations, open data, open materials | osf.io\u002Fsearch\u002F?q=QUERY |\n| Semantic Scholar | Citation analysis, paper metadata | api.semanticscholar.org |\n| OpenAlex | Open citation data, institutional affiliations | api.openalex.org |\n| Many Labs | Replication results for social psychology | osf.io\u002Fwx7ck\u002F |\n\n## Standards (the rigor bar)\n\n- **Verified** — only when the underlying paper exists, raw data is\n  public OR an independent lab has confirmed the result, and the citing\n  source represents the claim accurately.\n- **Partial** — paper is real and findings stand, but the citation\n  context oversells (e.g., \"X causes Y\" when the paper shows\n  correlation, or \"all studies find X\" when it's one underpowered study).\n- **Unverifiable** — the underlying number can't be traced to source\n  data, no replication has been done, no independent confirmation\n  exists. Not the same as \"wrong\" — say \"we couldn't verify.\"\n- **Misattributed** — the citation points to a paper, but the paper\n  doesn't actually say what the citation claims. Common in policy briefs.\n- **Retracted \u002F disputed** — paper has been retracted, has a major\n  expression-of-concern, or has well-documented critique that\n  contradicts the headline finding.\n\nNever claim a problem without evidence. The verification document\nitself is the artifact — if the claim holds up, say so plainly. If it\ndoesn't, the trace speaks for itself.\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- The brain pass (`gbrain query`) comes back empty with a degraded notice (keyword-only, embeddings off): paraphrased study titles miss on keywords, so retry with the author, journal or year before saying the brain has no prior notes on the claim.\n- The web pass through perplexity-research fails (no `PERPLEXITY_API_KEY`, `rate_limited`): mark the claim UNVERIFIED, never \"false\", and tell the user which step could not run; on `rate_limited` retry once after the stated delay.\n- Saving the verdict returns `write_pending` (exit 10): the write is accepted; poll `gbrain write-request \u003Crequest_id>` instead of writing a second verdict page.\n\n## Anti-Patterns\n\n- ❌ Skipping the brain-first lookup. Re-doing verification we've\n  already done is wasted Perplexity spend.\n- ❌ Bypassing perplexity-research and inventing the lookup. The\n  citations from Perplexity are the evidence — without them, the\n  verdict is just opinion.\n- ❌ Stating \"Verified\" without confirming raw data availability.\n  Replication trumps any single paper.\n- ❌ Stating \"Unverifiable\" when you simply didn't look hard enough.\n  The verdict is on the source, not on your search effort.\n\n## Related skills\n\n- `skills\u002Fperplexity-research\u002FSKILL.md` — the actual web-search engine\n  this skill routes through (D7\u002Fα: pure routing, no new infrastructure)\n- `skills\u002Fcitation-fixer\u002FSKILL.md` — fixes citation FORMATTING; this\n  skill checks whether the cited claim is true\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","# academic-verify — Trace Claims to Source Data\n\n> **Convention:** see [conventions\u002Fquality.md](..\u002Fconventions\u002Fquality.md) for\n> citation rules; every verdict cites the source data, not just the\n> author's claim about the source data.\n>\n> **Convention:** see [conventions\u002Fbrain-first.md](..\u002Fconventions\u002Fbrain-first.md)\n> for the lookup chain. This skill enforces brain-first by checking\n> existing brain pages before issuing a fresh web search.\n\n## What this is\n\nA claim-verification flow for academic \u002F research statements. When a\nbook, article, or speaker cites a study or quotes a number, this skill\ntraces the claim through:\n\n```\nclaim → publication → methodology section → raw data source → independent verification\n```\n\nAt each step, it answers:\n\n- **Where does this number come from?** (Self-generated? Survey? Government data?)\n- **What's the baseline?** (Reduction from what? Over what time period?)\n- **Is the raw data available?** (Public? Proprietary? \"Available on request\"?)\n- **Has anyone independently verified it?** (Replication study? Government audit?)\n- **Are there confounding factors?** (Other interventions, policy changes, COVID, sampling bias?)\n- **Is the comparison fair?** (Cherry-picked comparison group? Survivorship bias?)\n\nThe output is a brain page under `concepts\u002F\u003Cclaim-slug>.md` that records\nthe claim, the trace, and the verdict — so future references to the\nsame claim can re-use the verified analysis.\n\n## When to use this\n\n- A book quotes a study and you want to confirm it's real and not\n  miscited\n- An article makes a quantified claim (\"X reduced Y by 40%\") that you\n  want traced to the source data\n- You're writing something that depends on a piece of research and you\n  want to verify the underlying paper holds up\n- You're updating a brain page that cites a research claim and you want\n  to record the verification status alongside\n\n## What this skill is NOT\n\n- Not adversarial \u002F oppo work. The point is rigor, not takedown.\n- Not generic web research — use `perplexity-research` directly for\n  open-ended topic exploration.\n- Not a brain-only lookup — that's `gbrain query`.\n\n## How it works (D7\u002Fα: pure routing through perplexity-research)\n\nacademic-verify is a thin orchestrator. The actual web search is done\nby [perplexity-research](..\u002Fperplexity-research\u002FSKILL.md). academic-verify's\njob is the *workflow*: scoping the claim precisely, sending it through\nperplexity-research with citation-mode, then formatting the response\ninto a verdict-shaped brain page.\n\n```\nStep 1: Scope the claim\n  Pin down EXACTLY what's being claimed:\n    • Quote: who said what?\n    • Source: which paper \u002F dataset \u002F survey?\n    • Number: what specific quantity is claimed?\n    • Period: over what time range?\n\nStep 2: Brain-first lookup\n  gbrain query \"\u003Cpaper title> OR \u003Cauthor name> OR \u003Cclaim keywords>\"\n  If the brain has prior verification of this claim, reuse it.\n\nStep 3: Invoke perplexity-research with citation-mode prompt\n  Send the claim + brain context to perplexity-research with a prompt\n  that explicitly asks for:\n    • Original publication (title, authors, journal, year, DOI)\n    • Methodology section summary\n    • Raw data availability (public repo? proprietary?)\n    • Independent replication status (Retraction Watch \u002F PubPeer hits)\n    • Citations of the paper that critique or contextualize it\n\nStep 4: Format the verdict\n  Write the result to concepts\u002F\u003Cclaim-slug>.md. The verdict is one of:\n    • Verified — claim is accurate; raw data available; replication exists\n    • Partially verified — claim correct on the underlying paper but\n      methodology has known limits; record limits explicitly\n    • Unverifiable — no public data, no replication; not enough to act\n    • Misattributed — the claim cites a paper but the paper doesn't say that\n    • Retracted \u002F disputed — paper has known retraction or\n      well-documented critique\n\nStep 5: Cross-link to original sources\n  Add the paper authors to people\u002F if they have brain pages, or create\n  one if notable. Iron Law per conventions\u002Fquality.md.\n```\n\n## Output: brain page format\n\n```markdown\n---\ntitle: \"[Claim summary] — Verified\"\ntype: research\ndate: YYYY-MM-DD\nverdict: \"verified|partial|unverifiable|misattributed|retracted\"\nbrain_context_slugs: [\"pages cited as context\"]\n---\n\n# [Claim summary] — Verified\n\n> One-line: the verdict + the bottom-line reason.\n\n## The Claim\n\n> Exact quote, exactly as stated, with source attribution.\n\n## Trace\n\n| Step | Finding | Source |\n|------|---------|--------|\n| Original publication | [Title, authors, year, DOI] | [URL] |\n| Methodology | [1-line summary; flag obvious limits] | [URL] |\n| Raw data | [Public repo \u002F proprietary \u002F available-on-request] | [URL] |\n| Independent replication | [Replication studies and their results] | [URL] |\n| Critical citations | [Papers that critique this work] | [URL] |\n\n## Verdict\n\n[Verified \u002F Partially verified \u002F Unverifiable \u002F Misattributed \u002F Retracted]\n\n[1-2 paragraphs explaining WHY the verdict, with specific evidence.]\n\n## Caveats\n\n[Honest limits: what we couldn't verify, what would change the verdict.]\n\n## See Also\n\n- Original paper: [Title](DOI URL)\n- Authors' brain pages: [Author 1](people\u002Fauthor-1.md), ...\n- Related claims (verified or otherwise): [...]\n```\n\n## Useful databases (the agent uses these via perplexity-research)\n\n| Database | What it has | URL pattern |\n|----------|-------------|-------------|\n| Retraction Watch | Retractions, corrections, expressions of concern | retractionwatch.com\u002F?s=NAME |\n| PubPeer | Anonymous post-publication peer review | pubpeer.com\u002Fsearch?q=NAME |\n| OSF | Pre-registrations, open data, open materials | osf.io\u002Fsearch\u002F?q=QUERY |\n| Semantic Scholar | Citation analysis, paper metadata | api.semanticscholar.org |\n| OpenAlex | Open citation data, institutional affiliations | api.openalex.org |\n| Many Labs | Replication results for social psychology | osf.io\u002Fwx7ck\u002F |\n\n## Standards (the rigor bar)\n\n- **Verified** — only when the underlying paper exists, raw data is\n  public OR an independent lab has confirmed the result, and the citing\n  source represents the claim accurately.\n- **Partial** — paper is real and findings stand, but the citation\n  context oversells (e.g., \"X causes Y\" when the paper shows\n  correlation, or \"all studies find X\" when it's one underpowered study).\n- **Unverifiable** — the underlying number can't be traced to source\n  data, no replication has been done, no independent confirmation\n  exists. Not the same as \"wrong\" — say \"we couldn't verify.\"\n- **Misattributed** — the citation points to a paper, but the paper\n  doesn't actually say what the citation claims. Common in policy briefs.\n- **Retracted \u002F disputed** — paper has been retracted, has a major\n  expression-of-concern, or has well-documented critique that\n  contradicts the headline finding.\n\nNever claim a problem without evidence. The verification document\nitself is the artifact — if the claim holds up, say so plainly. If it\ndoesn't, the trace speaks for itself.\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- The brain pass (`gbrain query`) comes back empty with a degraded notice (keyword-only, embeddings off): paraphrased study titles miss on keywords, so retry with the author, journal or year before saying the brain has no prior notes on the claim.\n- The web pass through perplexity-research fails (no `PERPLEXITY_API_KEY`, `rate_limited`): mark the claim UNVERIFIED, never \"false\", and tell the user which step could not run; on `rate_limited` retry once after the stated delay.\n- Saving the verdict returns `write_pending` (exit 10): the write is accepted; poll `gbrain write-request \u003Crequest_id>` instead of writing a second verdict page.\n\n## Anti-Patterns\n\n- ❌ Skipping the brain-first lookup. Re-doing verification we've\n  already done is wasted Perplexity spend.\n- ❌ Bypassing perplexity-research and inventing the lookup. The\n  citations from Perplexity are the evidence — without them, the\n  verdict is just opinion.\n- ❌ Stating \"Verified\" without confirming raw data availability.\n  Replication trumps any single paper.\n- ❌ Stating \"Unverifiable\" when you simply didn't look hard enough.\n  The verdict is on the source, not on your search effort.\n\n## Related skills\n\n- `skills\u002Fperplexity-research\u002FSKILL.md` — the actual web-search engine\n  this skill routes through (D7\u002Fα: pure routing, no new infrastructure)\n- `skills\u002Fcitation-fixer\u002FSKILL.md` — fixes citation FORMATTING; this\n  skill checks whether the cited claim is true\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":57,"mutating":58,"triggers":59,"writes_to":65,"description":7,"when_to_use":67,"writes_pages":58},"0.1.0",true,[60,61,24,62,63,64],"verify this academic claim","check this study","validate citation","is this study real","Retraction Watch",[66],"concepts\u002F","Use when the user asks: \"verify this academic claim\", \"check this study\", \"academic verify\", \"validate citation\", \"is this study real\".","master","074ec301549ded4930f04d2c3b22d709a6c095cc","plugin\u002Fskills\u002Facademic-verify",4929,"https:\u002F\u002Fgithub.com\u002Fgarrytan\u002Fgbrain","https:\u002F\u002Fgithub.com\u002Fgarrytan","https:\u002F\u002Fblog.garrytan.com","Writes software, dreams. ","2026-11-15 03:57:03",{"source":8,"skillName":5,"commands":78,"prompt":88,"zipAvailable":58},[79,82,85],{"tool":80,"command":81},"npx","npx skills add garrytan\u002Fgbrain --skill academic-verify",{"tool":83,"command":84},"bunx","bunx skills add garrytan\u002Fgbrain --skill academic-verify",{"tool":86,"command":87},"pnpm","pnpm dlx skills add garrytan\u002Fgbrain --skill academic-verify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgarrytan\u002Fgbrain\u002Fblob\u002Fmaster\u002Fplugin\u002Fskills\u002Facademic-verify\u002FSKILL.md",[90],{"path":91,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":94,"sourceHtmlUrl":95},"routing-eval.jsonl","OTHER","其他",699,"https:\u002F\u002Fgithub.com\u002Fgarrytan\u002Fgbrain\u002Fblob\u002Fmaster\u002Fplugin\u002Fskills\u002Facademic-verify\u002Frouting-eval.jsonl",[97,109,115,135,160,174],{"skillNo":98,"name":99,"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":100,"categories":101,"keywords":102,"publishedAt":52},"01M6N109FNGH1PK49T734PZXGB","query-helper","https:\u002F\u002Fgithub.com\u002Fgarrytan\u002Fgbrain\u002Fblob\u002Fmaster\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fquery-helper\u002FSKILL.md",[],[103,104,105,106,46,107,108],"query helper","helper","query","search","find","false",{"skillNo":110,"name":111,"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":112,"categories":113,"keywords":114,"publishedAt":52},"01M6N108A23GW6NGQEQ0E7GV0A","broken","https:\u002F\u002Fgithub.com\u002Fgarrytan\u002Fgbrain\u002Fblob\u002Fmaster\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fbroken\u002FSKILL.md",[],[111],{"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":52},"01M6N105E88C5K2H03H0CC79G1","brain-ops","Read, enrich, and write brain pages with source attribution.","https:\u002F\u002Fgithub.com\u002Fgarrytan\u002Fgbrain\u002Fblob\u002Fmaster\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fbrain-ops\u002FSKILL.md",[],[122,39,123,31,124,46,125,126,127,128,105,129,130,131,132,51,133,134,106],"brain ops","ops","attribution","read","write","up","look","pages","people","with","enrich","path","source",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":146,"publishedAt":52},"01M6N102GRMF22TVCNT6RK5MRD","meeting-prep","Build a briefing before you meet someone, from their recent threads, open loops and what they care about.","https:\u002F\u002Fgithub.com\u002Fgarrytan\u002Fgbrain\u002Fblob\u002Fmaster\u002Ftest\u002Ffixtures\u002Fskill-catalog-query\u002Fskills\u002Fmeeting-prep\u002FSKILL.md",[141],{"categoryNo":142,"categoryName":143,"taxonomyType":144,"taxonomyTypeDesc":145},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[147,148,149,150,151,106,152,153,154,105,108,155,156,34,157,158,30,159],"meeting","prep","meeting prep","me","prepare","brief","open","build","loops","about","briefing","threads","Meet",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":166,"publishedAt":52},"01M6N1005QK7REHX5KGMNR5PF0","inbox-zero","Triage the inbox into replies, delegations and archives.","https:\u002F\u002Fgithub.com\u002Fgarrytan\u002Fgbrain\u002Fblob\u002Fmaster\u002Ftest\u002Ffixtures\u002Fskill-catalog-query\u002Fskills\u002Finbox-zero\u002FSKILL.md",[],[167,168,169,106,170,108,171,172,173],"inbox zero","ZeRO","inbox","clear","replies","my","triage",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":52},"01M6N0ZXQ8RRRW71PNV61T57GP","deal-memo","Draft an investment memo from the deal pages and the founder history already in the brain.","https:\u002F\u002Fgithub.com\u002Fgarrytan\u002Fgbrain\u002Fblob\u002Fmaster\u002Ftest\u002Ffixtures\u002Fskill-catalog-query\u002Fskills\u002Fdeal-memo\u002FSKILL.md",[],[181,182,183,129,39,184,185,126,186,31,106,187],"deal memo","deal","memo","draft","investment","history","founder"]