[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CD34MCA0NDF3HT2BD6G23S":3,"skill-same:01M6CD34MCA0NDF3HT2BD6G23S":76},{"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":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":6,"ownerHtmlUrl":60,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":61,"install":62,"resources":75},"01M6CD34MCA0NDF3HT2BD6G23S","research-readwise-obsidian",null,"Use the Readwise CLI to run relevance-first research across Reader documents and highlights, then synthesize an Obsidian-ready note with source-linked evidence and explicit confidence gaps. Use when researching topics from Readwise content for PKM workflows in Obsidian.","cercova-studios\u002F10x-swe","cercova-studios","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F217108198?v=4","01M6CCYGHXTH80N3BXRW6KESTE","Cercova Studios","01M6CCYGPADH5MJDR0VNNR775C",1,"MIT","https:\u002F\u002Fgithub.com\u002Fcercova-studios\u002F10x-swe\u002Fblob\u002Fmain\u002Fplugins\u002F10x-swe\u002Fskills\u002Fresearch-readwise-obsidian\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],"obsidian","research","readwise","research readwise obsidian","paid","cli","when","gaps","for","with","across","synthesize","readwise reader","ready","evidence","pkm","use","reader","obsidian vault","vault","first","content","run","documents","workflows","2026-11-10 10:12:30",false,"---\nname: research-readwise-obsidian\ndescription: Use the Readwise CLI to run relevance-first research across Reader documents and highlights, then synthesize an Obsidian-ready note with source-linked evidence and explicit confidence gaps. Use when researching topics from Readwise content for PKM workflows in Obsidian.\ncompatibility: Requires the Readwise CLI signed in to a Readwise Reader subscription (paid) and an Obsidian vault.\n---\n\n\u003Cobjective>\nUse the `readwise` CLI to run deep research on a topic by searching both Reader documents and Readwise highlights, then synthesize an Obsidian-ready research note for PKM.\n\nScope for this skill is intentionally narrow: search, retrieval, evidence ranking, and synthesis. It does not perform inbox triage, tagging or metadata edits, exports, or archive maintenance unless the user explicitly overrides scope.\n\u003C\u002Fobjective>\n\n\u003Cquick_start>\n1. Run preflight and auth checks:\n```bash\ncommand -v readwise\nreadwise --help\n```\nIf authentication is missing, run `readwise login` or `readwise login-with-token \u003Ctoken>`.\n\n2. Run both searches for the same query in machine-readable mode:\n```bash\nreadwise --json reader-search-documents --query \"$TOPIC\" --limit 20\nreadwise --json readwise-search-highlights --vector-search-term \"$TOPIC\" --limit 30\n```\n\n3. Pull deeper context for top documents:\n```bash\nreadwise --json reader-get-document-details --document-id \"\u003Cdocument_id>\"\nreadwise --json reader-get-document-highlights --document-id \"\u003Cdocument_id>\"\n```\n\n4. Produce one Obsidian note using the fixed template in `\u003Cprocess>`.\n\u003C\u002Fquick_start>\n\n\u003Cprocess>\n1. Normalize the input topic into:\n- one primary research question\n- 3 to 6 subthemes for sectioning\n- 3 to 8 query variants (synonyms, alternate phrasings, opposing terms)\n\n2. Execute initial retrieval across both systems:\n- Reader documents: `reader-search-documents`\n- Readwise highlights: `readwise-search-highlights`\nUse relevance-focused limits first (documents 20, highlights 30). Increase only when recall is weak.\n\n3. Rank evidence by relevance before recency.\nScore each candidate snippet with this rubric:\n- `3`: directly answers the research question with specific claim or detail\n- `2`: supports a subtheme with useful context\n- `1`: tangential but potentially useful\n- `0`: irrelevant or noise\nKeep score `2-3` items first. Use recency only as a tiebreaker.\n\n4. Enrich top evidence with source context.\nFor top-ranked Reader documents, fetch:\n- full markdown and details (`reader-get-document-details`)\n- document highlights (`reader-get-document-highlights`)\nPrefer exact highlighted text over paraphrase whenever available.\n\n5. Run refinement loops only if evidence is weak.\nWeak evidence means any subtheme has fewer than 2 strong snippets (`score >= 2`) or conflicting claims without sufficient support.\nPerform up to 2 refinement rounds:\n- round strategy A: broaden terms (synonyms, adjacent concepts)\n- round strategy B: narrow terms (specific entities, date constraints)\nStop early once evidence quality is sufficient.\n\n6. Enforce section-level snippet caps.\nFor each subtheme section, include at most 5 snippets. Select highest relevance first, then maximize source diversity.\n\n7. Resolve conflicting evidence explicitly.\nWhen sources disagree:\n- present both views\n- attach source-linked evidence for each view\n- explain likely reasons for disagreement (timeframe, domain, methodology, or context)\n\n8. Produce the final fixed Obsidian note.\nUse this structure exactly:\n\n```markdown\n---\ntitle: \"{{YYYY-MM-DD topic-slug}}\"\ncreated: \"{{ISO-8601 datetime}}\"\ntopic: \"{{research topic}}\"\nsource_system: \"readwise-cli\"\ntags:\n  - research\n  - readwise\n  - obsidian\n  - pkm\n---\n\n# {{research topic}}\n\n## Research Question\n{{one-sentence question}}\n\n## Key Findings\n- {{finding 1}}\n- {{finding 2}}\n- {{finding 3}}\n\n## Evidence by Theme\n### {{theme 1}}\n1. \"{{verbatim snippet}}\" — [{{source title}}]({{source url}}) _(author: {{author|unknown}}, category: {{category|unknown}}, document_id: {{document_id|n\u002Fa}}, highlight_id: {{highlight_id|n\u002Fa}})_\n2. \"{{verbatim snippet}}\" — [{{source title}}]({{source url}}) _(author: {{author|unknown}}, category: {{category|unknown}}, document_id: {{document_id|n\u002Fa}}, highlight_id: {{highlight_id|n\u002Fa}})_\n\n### {{theme 2}}\n1. \"{{verbatim snippet}}\" — [{{source title}}]({{source url}}) _(author: {{author|unknown}}, category: {{category|unknown}}, document_id: {{document_id|n\u002Fa}}, highlight_id: {{highlight_id|n\u002Fa}})_\n\n## Conflicting Evidence\n- **View A:** {{claim summary}}\n  Evidence: [{{source title}}]({{source url}}) _(author: {{author|unknown}}, category: {{category|unknown}}, document_id: {{document_id|n\u002Fa}}, highlight_id: {{highlight_id|n\u002Fa}})_\n- **View B:** {{claim summary}}\n  Evidence: [{{source title}}]({{source url}}) _(author: {{author|unknown}}, category: {{category|unknown}}, document_id: {{document_id|n\u002Fa}}, highlight_id: {{highlight_id|n\u002Fa}})_\n- **Why they differ:** {{reason grounded in source context}}\n\n## Confidence and Gaps\n- **Confidence:** {{High|Medium|Low}} — {{justification}}\n- **Known gaps:** {{missing or underrepresented evidence}}\n- **Next queries:**\n  - {{query refinement 1}}\n  - {{query refinement 2}}\n\n## Sources\n- [{{source title}}]({{source url}}) — author: {{author|unknown}}, category: {{category|unknown}}, location: {{location|n\u002Fa}}, document_id: {{document_id|n\u002Fa}}, highlight_id: {{highlight_id|n\u002Fa}}\n- [{{source title}}]({{source url}}) — author: {{author|unknown}}, category: {{category|unknown}}, location: {{location|n\u002Fa}}, document_id: {{document_id|n\u002Fa}}, highlight_id: {{highlight_id|n\u002Fa}}\n```\n\n9. Citation requirements are mandatory:\n- citations must be markdown links to source URLs\n- each citation must include Readwise metadata inline (author, category, document_id, highlight_id when available)\n- if a URL is unavailable, explicitly mark `url unavailable` and keep metadata\n\n10. Obsidian naming guidance:\n- recommended note filename format: `YYYY-MM-DD topic-slug.md`\n- keep slugs lowercase with hyphens\n- keep note title aligned with filename stem\n\u003C\u002Fprocess>\n\n\u003Csuccess_criteria>\nThis skill is successful when all conditions are true:\n\n- Searches both Reader documents and Readwise highlights for the topic.\n- Uses relevance-first ranking and only uses recency as secondary ordering.\n- Runs at most 2 query refinement rounds, and only when evidence is weak.\n- Limits evidence to a maximum of 5 snippets per theme section.\n- Produces the fixed Obsidian note structure without omitting sections.\n- Includes a `Conflicting Evidence` section with both views when disagreement exists.\n- Always includes a `Confidence and Gaps` section, even when confidence is high.\n- Uses markdown-link citations with Readwise metadata for every evidence item.\n- Stays within scope: search, retrieval, and synthesis only unless user explicitly requests broader workflows.\n\u003C\u002Fsuccess_criteria>\n","\u003Cobjective>\nUse the `readwise` CLI to run deep research on a topic by searching both Reader documents and Readwise highlights, then synthesize an Obsidian-ready research note for PKM.\n\nScope for this skill is intentionally narrow: search, retrieval, evidence ranking, and synthesis. It does not perform inbox triage, tagging or metadata edits, exports, or archive maintenance unless the user explicitly overrides scope.\n\u003C\u002Fobjective>\n\n\u003Cquick_start>\n1. Run preflight and auth checks:\n```bash\ncommand -v readwise\nreadwise --help\n```\nIf authentication is missing, run `readwise login` or `readwise login-with-token \u003Ctoken>`.\n\n2. Run both searches for the same query in machine-readable mode:\n```bash\nreadwise --json reader-search-documents --query \"$TOPIC\" --limit 20\nreadwise --json readwise-search-highlights --vector-search-term \"$TOPIC\" --limit 30\n```\n\n3. Pull deeper context for top documents:\n```bash\nreadwise --json reader-get-document-details --document-id \"\u003Cdocument_id>\"\nreadwise --json reader-get-document-highlights --document-id \"\u003Cdocument_id>\"\n```\n\n4. Produce one Obsidian note using the fixed template in `\u003Cprocess>`.\n\u003C\u002Fquick_start>\n\n\u003Cprocess>\n1. Normalize the input topic into:\n- one primary research question\n- 3 to 6 subthemes for sectioning\n- 3 to 8 query variants (synonyms, alternate phrasings, opposing terms)\n\n2. Execute initial retrieval across both systems:\n- Reader documents: `reader-search-documents`\n- Readwise highlights: `readwise-search-highlights`\nUse relevance-focused limits first (documents 20, highlights 30). Increase only when recall is weak.\n\n3. Rank evidence by relevance before recency.\nScore each candidate snippet with this rubric:\n- `3`: directly answers the research question with specific claim or detail\n- `2`: supports a subtheme with useful context\n- `1`: tangential but potentially useful\n- `0`: irrelevant or noise\nKeep score `2-3` items first. Use recency only as a tiebreaker.\n\n4. Enrich top evidence with source context.\nFor top-ranked Reader documents, fetch:\n- full markdown and details (`reader-get-document-details`)\n- document highlights (`reader-get-document-highlights`)\nPrefer exact highlighted text over paraphrase whenever available.\n\n5. Run refinement loops only if evidence is weak.\nWeak evidence means any subtheme has fewer than 2 strong snippets (`score >= 2`) or conflicting claims without sufficient support.\nPerform up to 2 refinement rounds:\n- round strategy A: broaden terms (synonyms, adjacent concepts)\n- round strategy B: narrow terms (specific entities, date constraints)\nStop early once evidence quality is sufficient.\n\n6. Enforce section-level snippet caps.\nFor each subtheme section, include at most 5 snippets. Select highest relevance first, then maximize source diversity.\n\n7. Resolve conflicting evidence explicitly.\nWhen sources disagree:\n- present both views\n- attach source-linked evidence for each view\n- explain likely reasons for disagreement (timeframe, domain, methodology, or context)\n\n8. Produce the final fixed Obsidian note.\nUse this structure exactly:\n\n```markdown\n---\ntitle: \"{{YYYY-MM-DD topic-slug}}\"\ncreated: \"{{ISO-8601 datetime}}\"\ntopic: \"{{research topic}}\"\nsource_system: \"readwise-cli\"\ntags:\n  - research\n  - readwise\n  - obsidian\n  - pkm\n---\n\n# {{research topic}}\n\n## Research Question\n{{one-sentence question}}\n\n## Key Findings\n- {{finding 1}}\n- {{finding 2}}\n- {{finding 3}}\n\n## Evidence by Theme\n### {{theme 1}}\n1. \"{{verbatim snippet}}\" — [{{source title}}]({{source url}}) _(author: {{author|unknown}}, category: {{category|unknown}}, document_id: {{document_id|n\u002Fa}}, highlight_id: {{highlight_id|n\u002Fa}})_\n2. \"{{verbatim snippet}}\" — [{{source title}}]({{source url}}) _(author: {{author|unknown}}, category: {{category|unknown}}, document_id: {{document_id|n\u002Fa}}, highlight_id: {{highlight_id|n\u002Fa}})_\n\n### {{theme 2}}\n1. \"{{verbatim snippet}}\" — [{{source title}}]({{source url}}) _(author: {{author|unknown}}, category: {{category|unknown}}, document_id: {{document_id|n\u002Fa}}, highlight_id: {{highlight_id|n\u002Fa}})_\n\n## Conflicting Evidence\n- **View A:** {{claim summary}}\n  Evidence: [{{source title}}]({{source url}}) _(author: {{author|unknown}}, category: {{category|unknown}}, document_id: {{document_id|n\u002Fa}}, highlight_id: {{highlight_id|n\u002Fa}})_\n- **View B:** {{claim summary}}\n  Evidence: [{{source title}}]({{source url}}) _(author: {{author|unknown}}, category: {{category|unknown}}, document_id: {{document_id|n\u002Fa}}, highlight_id: {{highlight_id|n\u002Fa}})_\n- **Why they differ:** {{reason grounded in source context}}\n\n## Confidence and Gaps\n- **Confidence:** {{High|Medium|Low}} — {{justification}}\n- **Known gaps:** {{missing or underrepresented evidence}}\n- **Next queries:**\n  - {{query refinement 1}}\n  - {{query refinement 2}}\n\n## Sources\n- [{{source title}}]({{source url}}) — author: {{author|unknown}}, category: {{category|unknown}}, location: {{location|n\u002Fa}}, document_id: {{document_id|n\u002Fa}}, highlight_id: {{highlight_id|n\u002Fa}}\n- [{{source title}}]({{source url}}) — author: {{author|unknown}}, category: {{category|unknown}}, location: {{location|n\u002Fa}}, document_id: {{document_id|n\u002Fa}}, highlight_id: {{highlight_id|n\u002Fa}}\n```\n\n9. Citation requirements are mandatory:\n- citations must be markdown links to source URLs\n- each citation must include Readwise metadata inline (author, category, document_id, highlight_id when available)\n- if a URL is unavailable, explicitly mark `url unavailable` and keep metadata\n\n10. Obsidian naming guidance:\n- recommended note filename format: `YYYY-MM-DD topic-slug.md`\n- keep slugs lowercase with hyphens\n- keep note title aligned with filename stem\n\u003C\u002Fprocess>\n\n\u003Csuccess_criteria>\nThis skill is successful when all conditions are true:\n\n- Searches both Reader documents and Readwise highlights for the topic.\n- Uses relevance-first ranking and only uses recency as secondary ordering.\n- Runs at most 2 query refinement rounds, and only when evidence is weak.\n- Limits evidence to a maximum of 5 snippets per theme section.\n- Produces the fixed Obsidian note structure without omitting sections.\n- Includes a `Conflicting Evidence` section with both views when disagreement exists.\n- Always includes a `Confidence and Gaps` section, even when confidence is high.\n- Uses markdown-link citations with Readwise metadata for every evidence item.\n- Stays within scope: search, retrieval, and synthesis only unless user explicitly requests broader workflows.\n\u003C\u002Fsuccess_criteria>\n",{"name":5,"description":7,"compatibility":54},"Requires the Readwise CLI signed in to a Readwise Reader subscription (paid) and an Obsidian vault.","main","12441d84a8a292fcc94f47bc98877cbefd9b52e2","plugins\u002F10x-swe\u002Fskills\u002Fresearch-readwise-obsidian",0,"https:\u002F\u002Fgithub.com\u002Fcercova-studios\u002F10x-swe","https:\u002F\u002Fgithub.com\u002Fcercova-studios","2026-11-12 00:33:06",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add cercova-studios\u002F10x-swe --skill research-readwise-obsidian",{"tool":68,"command":69},"bunx","bunx skills add cercova-studios\u002F10x-swe --skill research-readwise-obsidian",{"tool":71,"command":72},"pnpm","pnpm dlx skills add cercova-studios\u002F10x-swe --skill research-readwise-obsidian","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcercova-studios\u002F10x-swe\u002Fblob\u002Fmain\u002Fplugins\u002F10x-swe\u002Fskills\u002Fresearch-readwise-obsidian\u002FSKILL.md",true,[],[77,115,151,169,188,200],{"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":81,"licenseFileUrl":82,"sourceHtmlUrl":83,"categories":84,"keywords":88,"publishedAt":49},"01M6CD3T6EQ9N5KPNXCM6ABHVA","turnstile-spin","Set up Cloudflare Turnstile end-to-end in a project. Scan the codebase, create the widget via the Cloudflare API, embed it where user requests need bot verification (form submissions, SPA actions, API endpoints, download links, comment or vote submissions, etc.), wire canonical server-side siteverify in the customer's existing backend, validate, and persist the skill. Load this when a user asks to add Turnstile, set up CAPTCHA, protect a form or endpoint from bots, or fix a Turnstile integration. Uses Cloudflare's documented Turnstile contract.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fcercova-studios\u002F10x-swe\u002Fblob\u002Fmain\u002Fplugins\u002F10x-swe\u002Fskills\u002Fturnstile-spin\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fcercova-studios\u002F10x-swe\u002Fblob\u002Fmain\u002Fplugins\u002F10x-swe\u002Fskills\u002Fturnstile-spin\u002FSKILL.md",[85],{"categoryNo":86,"categoryName":87,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",[89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,30],"turnstile spin","SET","nextjs","actions","up","fix","cloudflare","bot","api","permissions","create","astro","server","verification","plugin","endpoints","customer","backend","sveltekit","integration","app","bots","spa","project","end","SWE",{"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":81,"licenseFileUrl":119,"sourceHtmlUrl":120,"categories":121,"keywords":133,"publishedAt":49},"01M6CD0BJYRNV610HYYPX933RE","frontend-design","Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.","https:\u002F\u002Fgithub.com\u002Fcercova-studios\u002F10x-swe\u002Fblob\u002Fmain\u002Fplugins\u002F10x-swe\u002Fskills\u002Ffrontend-design\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fcercova-studios\u002F10x-swe\u002Fblob\u002Fmain\u002Fplugins\u002F10x-swe\u002Fskills\u002Ffrontend-design\u002FSKILL.md",[122,125,128],{"categoryNo":123,"categoryName":124,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":126,"categoryName":127,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":129,"categoryName":130,"taxonomyType":131,"taxonomyTypeDesc":132},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[134,135,136,99,137,138,139,140,141,142,40,143,144,145,146,147,148,30,33,149,150],"frontend design","frontend","design","web","quality","applications","creative","web components","Production","code","components","user","generic","aesthetics","pages","high","build",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":157,"publishedAt":49},"01M6CD4QX8C4DST98AY21HEYCM","source-insights","Prepare inspected source evidence, preserve exact citations, and publish reviewed insights into an explicit local library.","https:\u002F\u002Fgithub.com\u002Fcercova-studios\u002F10x-swe\u002Fblob\u002Fmain\u002Fplugins\u002Fknowledge\u002Fskills\u002Fsource-insights\u002FSKILL.md",[],[158,159,160,161,162,38,163,48,164,165,166,167,168],"source insights","insights","source","publish","Citations","library","prepare","session","global","local","preserve",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":178,"publishedAt":49},"01M6CD4N1HVNC1EXPEBZT7YS31","skill-graph","Discover skills and workflows through independent lexical search, relationship paths and a terminal graph.","https:\u002F\u002Fgithub.com\u002Fcercova-studios\u002F10x-swe\u002Fblob\u002Fmain\u002Fplugins\u002Fknowledge\u002Fskills\u002Fskill-graph\u002FSKILL.md",[175],{"categoryNo":176,"categoryName":177,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[179,180,103,48,181,182,183,166,184,185,186,114,187],"graph","skill graph","terminal","10x","search","discover skills","discover","paths","relationship",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":194,"publishedAt":49},"01M6CD4HQKXNZ57YEGD8QVK6Z6","session-search","Recall public session turns with exact provenance, bounded excerpts and independent piped exports.","https:\u002F\u002Fgithub.com\u002Fcercova-studios\u002F10x-swe\u002Fblob\u002Fmain\u002Fplugins\u002Fknowledge\u002Fskills\u002Fsession-search\u002FSKILL.md",[],[183,165,195,196,48,197,198,166,33,159,160,199],"session search","public","provenance","recall","bounded",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":210,"publishedAt":49},"01M6CD4ET7DVNBYPDAMAYMSK2T","newsletter","Produce a private local AI newsletter from bounded public research, with cited deep dives, HTML\u002FMarkdown output, Dagu scheduling and seven-day retention.","https:\u002F\u002Fgithub.com\u002Fcercova-studios\u002F10x-swe\u002Fblob\u002Fmain\u002Fplugins\u002Fknowledge\u002Fskills\u002Fnewsletter\u002FSKILL.md",[206,209],{"categoryNo":207,"categoryName":208,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000005","邮件与沟通",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[202,211,212,213,25,196,48,214,215,216,217,166,33,218,219,167,199,220],"local ai","dagu","produce","markdown","scheduling","html","daily","deep","retention","output"]