[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M780Y2W33GVTQ9RVSDMJ10RV":3,"skill-same:01M780Y2W33GVTQ9RVSDMJ10RV":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":35,"commitSha":36,"skillDirectory":37,"forksCount":14,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":40,"install":41,"resources":53},"01M780Y2W33GVTQ9RVSDMJ10RV","perplexity-research",null,"Brain-augmented web research. Sends brain context about a topic to Perplexity, which searches the web with citations and returns what is NEW vs what the brain already knows. Use for entity enrichment, current-state checks, deal monitoring, and freshness deltas. NOT for simple URL fetches (use web_fetch) or brain-only queries (use gbrain query).","moonstachain\u002Fgbrain-yuanli","moonstachain","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F20961570?v=4","01M780RGGTEZZFR5F5PP9BY2RP","HAY2045","01M780RGHMKRKAX5KHNJN779EV",0,"MIT","https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli\u002Fblob\u002Fmain\u002Fskills\u002Fperplexity-research\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: perplexity-research\nversion: 0.1.0\ndescription: Brain-augmented web research. Sends brain context about a topic to Perplexity, which searches the web with citations and returns what is NEW vs what the brain already knows. Use for entity enrichment, current-state checks, deal monitoring, and freshness deltas. NOT for simple URL fetches (use web_fetch) or brain-only queries (use gbrain query).\ntriggers:\n  - \"perplexity research\"\n  - \"perplexity-research\"\n  - \"what's new about\"\n  - \"current state of\"\n  - \"web research\"\n  - \"what changed about\"\n  - \"surface new developments\"\nmutating: true\nwrites_pages: true\nwrites_to:\n  - research\u002F\n---\n\n# perplexity-research — Brain-Augmented Web Research\n\n> **Convention:** see [conventions\u002Fquality.md](..\u002Fconventions\u002Fquality.md) for\n> citation rules; every claim from web research lands with a verifiable\n> citation, not a paraphrase.\n>\n> **Convention:** see [conventions\u002Fbrain-first.md](..\u002Fconventions\u002Fbrain-first.md)\n> for the lookup chain. This skill ENFORCES brain-first by sending brain\n> context as part of the Perplexity prompt — the web search focuses on\n> the delta between brain knowledge and current web state.\n\n## What this does\n\nCombines existing brain knowledge with Perplexity's web search. The\nagent sends brain context about a topic into a Perplexity query;\nPerplexity searches + reads + synthesizes multiple pages with citations,\nfocused on what's NEW relative to the supplied context.\n\n**The key insight:** Perplexity doesn't just search — it reads and\nsynthesizes with citations. By sending brain context in the\ninstructions, it knows what you already know, so it surfaces the delta\ninstead of repeating settled fact.\n\n## When to use this vs other tools\n\n| Need | Use |\n|------|-----|\n| Deep research with citations | **This skill** — Perplexity + Opus |\n| Quick URL content | `web_fetch` |\n| Brain-only lookup | `gbrain query` \u002F `gbrain search` |\n| Real-time social monitoring | external X \u002F social-media collectors |\n| Structured data lookup against a tracker | `skills\u002Fdata-research\u002FSKILL.md` |\n\n## Output structure\n\nThe research output lands as a brain page under `research\u002F\u003Cslug>.md` with\nthis structure:\n\n```markdown\n---\ntitle: \"[Topic] — Research [YYYY-MM-DD]\"\ntype: research\ndate: YYYY-MM-DD\nbrain_context_slugs: [\"pages whose context was sent to Perplexity\"]\nrecency_filter: \"[hour|day|week|month|none]\"\n---\n\n# [Topic] — Research [YYYY-MM-DD]\n\n> Executive summary: 2-3 sentences on the delta between brain knowledge\n> and current web state.\n\n## Key New Developments\nWhat's changed since the brain was last updated on this topic.\n\n## Confirming Signals\nWeb evidence validating existing brain knowledge.\n\n## Contradictions or Updates\nThings that conflict with the brain — these need a closer look.\n\n## Recommended Brain Updates\nSpecific page updates the user might want to make based on this research.\nEach item: which page, what to add or change, source URL.\n\n## Citations\n- [Source title](URL) — accessed YYYY-MM-DD\n- [Source title](URL) — accessed YYYY-MM-DD\n- ...\n```\n\n## Invocation\n\nThe skill is markdown agent instructions; the agent uses Perplexity's\nAPI directly (or a host-provided `perplexity` CLI if installed):\n\n```bash\n# 1. Pull brain context\ngbrain get \u003Cslug>                    # or\ngbrain query \"\u003Ctopic keywords>\"\n\n# 2. Compose the Perplexity query with brain context inline:\n#    \"\"\"\n#    Topic: \u003Ctopic>\n#    Brain context (what we already know): \u003Cembedded gbrain content>\n#    Find: what's NEW since 2026-MM-DD that the brain doesn't reflect.\n#    Cite every claim.\n#    \"\"\"\n\n# 3. Call Perplexity API or the host's perplexity binary:\n#    curl https:\u002F\u002Fapi.perplexity.ai\u002Fchat\u002Fcompletions \\\n#      -H \"Authorization: Bearer $PERPLEXITY_API_KEY\" \\\n#      -H \"Content-Type: application\u002Fjson\" \\\n#      -d '{\"model\": \"sonar-pro\", \"messages\": [{\"role\":\"user\",\"content\":\"...\"}]}'\n\n# 4. Write the structured research page via put_page:\ngbrain put_page research\u002F\u003Cslug>      # via the put_page operation\n\n# 5. Cross-link entities mentioned (people, companies) per Iron Law.\n```\n\n## Models\n\n| Model | Cost \u002F query | Use when |\n|-------|-------------|----------|\n| Perplexity sonar-pro | ~\\$0.04 | Deep analysis, entity enrichment, deal research |\n| Perplexity sonar | ~\\$0.007 | Quick lookups, bulk monitoring, briefing pipelines |\n\nDefault to sonar-pro. Drop to sonar for bulk \u002F cron contexts where cost\nmatters more than depth.\n\n## Integration patterns\n\n### Entity enrichment\n\nCalled by `skills\u002Fenrich\u002FSKILL.md` when an entity page (person, company)\nneeds current web context:\n\n```bash\nBRAIN=$(gbrain get people\u002F\u003Cslug> 2>\u002Fdev\u002Fnull)\n# Send \u003Cslug>'s page content as brain_context to Perplexity, get current\n# news \u002F role \u002F context, then update the brain page with what's new.\n```\n\n### Deal \u002F company monitoring (cron)\n\nFor each active item under `deals\u002F` or `companies\u002F`:\n\n```bash\n# Weekly: pull recent news per company; flag changes for review.\n```\n\n### Morning briefing\n\nReplace raw `web_fetch` calls in briefing pipelines with this skill so\nthe agent doesn't re-narrate already-known facts.\n\n## Recency filter\n\nPass `recency_filter` to Perplexity: `hour | day | week | month`. Useful\nfor news-cycle topics; omit for evergreen research.\n\n## Anti-Patterns\n\n- ❌ Sending NO brain context. Then it's just a search — use `web_fetch`\n  instead.\n- ❌ Truncating the brain context. The whole point is \"knows what you\n  know.\" Send dense context.\n- ❌ Discarding citations. Every claim in the output must have a URL.\n- ❌ Skipping the cross-link step when entities are mentioned. Iron Law.\n\n## Environment\n\n- `PERPLEXITY_API_KEY` set in the agent's environment (or in\n  `~\u002F.gbrain\u002F.env`).\n- Optional: install Perplexity's official CLI for richer streaming output.\n\n## Related skills\n\n- `skills\u002Facademic-verify\u002FSKILL.md` — wraps perplexity-research for\n  citation-verified academic claim checking\n- `skills\u002Fenrich\u002FSKILL.md` — calls perplexity-research as part of the\n  entity-enrichment loop\n- `skills\u002Fdata-research\u002FSKILL.md` — structured-data trackers (different\n  shape: parameterized YAML recipes, not free-form research)\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","# perplexity-research — Brain-Augmented Web Research\n\n> **Convention:** see [conventions\u002Fquality.md](..\u002Fconventions\u002Fquality.md) for\n> citation rules; every claim from web research lands with a verifiable\n> citation, not a paraphrase.\n>\n> **Convention:** see [conventions\u002Fbrain-first.md](..\u002Fconventions\u002Fbrain-first.md)\n> for the lookup chain. This skill ENFORCES brain-first by sending brain\n> context as part of the Perplexity prompt — the web search focuses on\n> the delta between brain knowledge and current web state.\n\n## What this does\n\nCombines existing brain knowledge with Perplexity's web search. The\nagent sends brain context about a topic into a Perplexity query;\nPerplexity searches + reads + synthesizes multiple pages with citations,\nfocused on what's NEW relative to the supplied context.\n\n**The key insight:** Perplexity doesn't just search — it reads and\nsynthesizes with citations. By sending brain context in the\ninstructions, it knows what you already know, so it surfaces the delta\ninstead of repeating settled fact.\n\n## When to use this vs other tools\n\n| Need | Use |\n|------|-----|\n| Deep research with citations | **This skill** — Perplexity + Opus |\n| Quick URL content | `web_fetch` |\n| Brain-only lookup | `gbrain query` \u002F `gbrain search` |\n| Real-time social monitoring | external X \u002F social-media collectors |\n| Structured data lookup against a tracker | `skills\u002Fdata-research\u002FSKILL.md` |\n\n## Output structure\n\nThe research output lands as a brain page under `research\u002F\u003Cslug>.md` with\nthis structure:\n\n```markdown\n---\ntitle: \"[Topic] — Research [YYYY-MM-DD]\"\ntype: research\ndate: YYYY-MM-DD\nbrain_context_slugs: [\"pages whose context was sent to Perplexity\"]\nrecency_filter: \"[hour|day|week|month|none]\"\n---\n\n# [Topic] — Research [YYYY-MM-DD]\n\n> Executive summary: 2-3 sentences on the delta between brain knowledge\n> and current web state.\n\n## Key New Developments\nWhat's changed since the brain was last updated on this topic.\n\n## Confirming Signals\nWeb evidence validating existing brain knowledge.\n\n## Contradictions or Updates\nThings that conflict with the brain — these need a closer look.\n\n## Recommended Brain Updates\nSpecific page updates the user might want to make based on this research.\nEach item: which page, what to add or change, source URL.\n\n## Citations\n- [Source title](URL) — accessed YYYY-MM-DD\n- [Source title](URL) — accessed YYYY-MM-DD\n- ...\n```\n\n## Invocation\n\nThe skill is markdown agent instructions; the agent uses Perplexity's\nAPI directly (or a host-provided `perplexity` CLI if installed):\n\n```bash\n# 1. Pull brain context\ngbrain get \u003Cslug>                    # or\ngbrain query \"\u003Ctopic keywords>\"\n\n# 2. Compose the Perplexity query with brain context inline:\n#    \"\"\"\n#    Topic: \u003Ctopic>\n#    Brain context (what we already know): \u003Cembedded gbrain content>\n#    Find: what's NEW since 2026-MM-DD that the brain doesn't reflect.\n#    Cite every claim.\n#    \"\"\"\n\n# 3. Call Perplexity API or the host's perplexity binary:\n#    curl https:\u002F\u002Fapi.perplexity.ai\u002Fchat\u002Fcompletions \\\n#      -H \"Authorization: Bearer $PERPLEXITY_API_KEY\" \\\n#      -H \"Content-Type: application\u002Fjson\" \\\n#      -d '{\"model\": \"sonar-pro\", \"messages\": [{\"role\":\"user\",\"content\":\"...\"}]}'\n\n# 4. Write the structured research page via put_page:\ngbrain put_page research\u002F\u003Cslug>      # via the put_page operation\n\n# 5. Cross-link entities mentioned (people, companies) per Iron Law.\n```\n\n## Models\n\n| Model | Cost \u002F query | Use when |\n|-------|-------------|----------|\n| Perplexity sonar-pro | ~\\$0.04 | Deep analysis, entity enrichment, deal research |\n| Perplexity sonar | ~\\$0.007 | Quick lookups, bulk monitoring, briefing pipelines |\n\nDefault to sonar-pro. Drop to sonar for bulk \u002F cron contexts where cost\nmatters more than depth.\n\n## Integration patterns\n\n### Entity enrichment\n\nCalled by `skills\u002Fenrich\u002FSKILL.md` when an entity page (person, company)\nneeds current web context:\n\n```bash\nBRAIN=$(gbrain get people\u002F\u003Cslug> 2>\u002Fdev\u002Fnull)\n# Send \u003Cslug>'s page content as brain_context to Perplexity, get current\n# news \u002F role \u002F context, then update the brain page with what's new.\n```\n\n### Deal \u002F company monitoring (cron)\n\nFor each active item under `deals\u002F` or `companies\u002F`:\n\n```bash\n# Weekly: pull recent news per company; flag changes for review.\n```\n\n### Morning briefing\n\nReplace raw `web_fetch` calls in briefing pipelines with this skill so\nthe agent doesn't re-narrate already-known facts.\n\n## Recency filter\n\nPass `recency_filter` to Perplexity: `hour | day | week | month`. Useful\nfor news-cycle topics; omit for evergreen research.\n\n## Anti-Patterns\n\n- ❌ Sending NO brain context. Then it's just a search — use `web_fetch`\n  instead.\n- ❌ Truncating the brain context. The whole point is \"knows what you\n  know.\" Send dense context.\n- ❌ Discarding citations. Every claim in the output must have a URL.\n- ❌ Skipping the cross-link step when entities are mentioned. Iron Law.\n\n## Environment\n\n- `PERPLEXITY_API_KEY` set in the agent's environment (or in\n  `~\u002F.gbrain\u002F.env`).\n- Optional: install Perplexity's official CLI for richer streaming output.\n\n## Related skills\n\n- `skills\u002Facademic-verify\u002FSKILL.md` — wraps perplexity-research for\n  citation-verified academic claim checking\n- `skills\u002Fenrich\u002FSKILL.md` — calls perplexity-research as part of the\n  entity-enrichment loop\n- `skills\u002Fdata-research\u002FSKILL.md` — structured-data trackers (different\n  shape: parameterized YAML recipes, not free-form research)\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":33,"description":7,"writes_pages":25},"0.1.0",true,[27,5,28,29,30,31,32],"perplexity research","what's new about","current state of","web research","what changed about","surface new developments",[34],"research\u002F","main","8a1ba5bf6fb27ae3c622d36b4287f8a96555c805","skills\u002Fperplexity-research","https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli","https:\u002F\u002Fgithub.com\u002Fmoonstachain","2026-09-16 09:55:03",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":25},[43,46,49],{"tool":44,"command":45},"npx","npx skills add moonstachain\u002Fgbrain-yuanli --skill perplexity-research",{"tool":47,"command":48},"bunx","bunx skills add moonstachain\u002Fgbrain-yuanli --skill perplexity-research",{"tool":50,"command":51},"pnpm","pnpm dlx skills add moonstachain\u002Fgbrain-yuanli --skill perplexity-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli\u002Fblob\u002Fmain\u002Fskills\u002Fperplexity-research\u002FSKILL.md",[54],{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"routing-eval.jsonl","OTHER","其他",760,"https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli\u002Fblob\u002Fmain\u002Fskills\u002Fperplexity-research\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},"01M7813JZE1PE2C5VYE92ENW0K","query-helper","https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli\u002Fblob\u002Fmain\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},"01M7813J1CEF860359MM2X0E9F","broken","https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli\u002Fblob\u002Fmain\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},"01M7813EM189HRGPS6JMYWGDBY","brain-ops","Read, enrich, and write brain pages with source attribution.","https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli\u002Fblob\u002Fmain\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},"01M7813BNHV1F88ZSEZC7FVE30","signal-detector","Always-on ambient signal capture for the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fsignal-detector\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},"01M78138QAK5AM8ZJV3DEYZZZN","query","Look up brain pages in the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fquery\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},"01M78135RC63M8RZNK0TTHRBTS","context-now","ALWAYS-ON time-sensitivity discipline for the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002Fmoonstachain\u002Fgbrain-yuanli\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fcontext-now\u002FSKILL.md",[],[]]