[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71GPP6GXACZESKAR9G4ZBTP":3,"skill-same:01M71GPP6GXACZESKAR9G4ZBTP":55},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":22,"linkOnly":23,"markdownContent":24,"markdownBody":25,"frontMatter":26,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M71GPP6GXACZESKAR9G4ZBTP","researcher-comparison-table",null,"lookatitude\u002Fguild","lookatitude","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F524917?v=4","01M71GJ2KGXFSJZKAZC5P1ZXXM","Miguel Pinto","01M71GJ2MH4SH9WJKP8M7XZZ0P",8,"MIT","https:\u002F\u002Fgithub.com\u002Flookatitude\u002Fguild\u002Fblob\u002Fmain\u002Fskills\u002Fspecialists\u002Fresearcher-comparison-table\u002FSKILL.md",[],[18,19,20,21],"table","researcher","comparison","researcher comparison table","2026-11-10 10:12:30",false,"---\nname: researcher-comparison-table\ndescription: Produces an N-option comparison table — libraries, vendors, frameworks, models — with named axes, cell rationale, and takeaways. Output: markdown table + 3–5 bullet takeaways + source list. Pulled by the `researcher` specialist. TRIGGER: \"compare these five libraries\", \"side-by-side of X vs Y vs Z\", \"give me a comparison table of the top options for X\", \"evaluate these vendors for X\", \"which of these frameworks fits us best\", \"benchmark these options on cost and features\". DO NOT TRIGGER for: scoring two *project-internal* architecture options for this codebase (use `architect-tradeoff-matrix`), open-ended topic research with multiple sources (use `researcher-deep-dive`), summarizing a single paper (use `researcher-paper-digest`), generating copy for a comparison landing page (copywriter-long-form or seo).\nwhen_to_use: The parent `researcher` specialist pulls this skill when the task is a structured comparison of named external options (3+), and a reusable table is the right artifact. Also fires on explicit user request.\ntype: specialist\nwork_class: research\n---\n\n# researcher-comparison-table\n\n**Work class: `research` (authoritative, non-downgradable).** Any lane pulling this skill is `purpose: research` and resolves `effective_complexity: hard` \u002F `tier: powerful` (`research_always_hard` — the frozen `guild.model_policy.v2` floor); the floor is transitive through every handoff and sub-dispatch and is recorded in the receipt (`forced_floor_reason: research_always_hard`).\n\nEvidence is a table whose every cell cites a source — no opinion cells, no unsourced \"best\" claims.\n\n## What you do\n\nReduce \"which of these 3–8 things should we pick?\" to a scannable table, with axes chosen for the actual decision, every cell tied to a source, and a short set of takeaways — not a ranking disguised as analysis.\n\n- Pick 4–8 axes that matter for the actual call — feature support, pricing tier, license, community size, benchmarks, maturity, ecosystem, lock-in.\n- Make sure the options are comparable — listing a paid SaaS next to an OSS library is apples-to-oranges unless you call out the category mismatch.\n- Cite every cell — version number and source URL for each claim. \"Supports X\" with no source is folklore.\n- Keep the table narrow enough to render — if you need 12 axes, split into two tables.\n- Takeaways at the bottom, not a single \"winner\" — the right pick depends on which axes the reader weights.\n- Disclose vendor bias when you see it — a comparison sourced only from one vendor's own marketing is not a comparison.\n\n## Output shape\n\nMarkdown fragment (inline return, optionally persisted at `.guild\u002Fruns\u002F\u003Crun-id>\u002Fresearch\u002Fcomparisons\u002F\u003Cslug>.md`):\n\n1. **Scope** — what question, what options, what's deliberately out.\n2. **Table** — rows = options, columns = axes, cells = short fact + source footnote.\n3. **Versions \u002F dates checked** — one row per option with version and check-date.\n4. **Takeaways** — 3–5 bullets keyed to reader priorities (\"if cost dominates → X; if ecosystem → Y\").\n5. **Sources** — numbered footnote list.\n\n## Anti-patterns\n\n- Apples-to-oranges — comparing a managed service, an OSS library, and a language feature in the same table without flagging the category mismatch.\n- Unweighted scoring pretending to be objective — a numeric total without axis weights reads neutral but smuggles in a preference.\n- Hiding vendor bias — sourcing only from the leader's own docs; not disclosing sponsored content.\n- Stale versions — comparing last year's version of one tool to this year's of another.\n- Missing axes — leaving out the axis where your preferred option scores badly.\n- Single \"winner\" call — a comparison table's job is to let the reader decide, not to pick for them.\n\n## Handoff\n\nReturn the table (inline or as a file path) to the invoking `researcher` specialist. The researcher may chain into `researcher-deep-dive` if a specific option needs broader investigation, or into `researcher-paper-digest` if a named paper backs one of the options. This skill does not dispatch.\n","# researcher-comparison-table\n\n**Work class: `research` (authoritative, non-downgradable).** Any lane pulling this skill is `purpose: research` and resolves `effective_complexity: hard` \u002F `tier: powerful` (`research_always_hard` — the frozen `guild.model_policy.v2` floor); the floor is transitive through every handoff and sub-dispatch and is recorded in the receipt (`forced_floor_reason: research_always_hard`).\n\nEvidence is a table whose every cell cites a source — no opinion cells, no unsourced \"best\" claims.\n\n## What you do\n\nReduce \"which of these 3–8 things should we pick?\" to a scannable table, with axes chosen for the actual decision, every cell tied to a source, and a short set of takeaways — not a ranking disguised as analysis.\n\n- Pick 4–8 axes that matter for the actual call — feature support, pricing tier, license, community size, benchmarks, maturity, ecosystem, lock-in.\n- Make sure the options are comparable — listing a paid SaaS next to an OSS library is apples-to-oranges unless you call out the category mismatch.\n- Cite every cell — version number and source URL for each claim. \"Supports X\" with no source is folklore.\n- Keep the table narrow enough to render — if you need 12 axes, split into two tables.\n- Takeaways at the bottom, not a single \"winner\" — the right pick depends on which axes the reader weights.\n- Disclose vendor bias when you see it — a comparison sourced only from one vendor's own marketing is not a comparison.\n\n## Output shape\n\nMarkdown fragment (inline return, optionally persisted at `.guild\u002Fruns\u002F\u003Crun-id>\u002Fresearch\u002Fcomparisons\u002F\u003Cslug>.md`):\n\n1. **Scope** — what question, what options, what's deliberately out.\n2. **Table** — rows = options, columns = axes, cells = short fact + source footnote.\n3. **Versions \u002F dates checked** — one row per option with version and check-date.\n4. **Takeaways** — 3–5 bullets keyed to reader priorities (\"if cost dominates → X; if ecosystem → Y\").\n5. **Sources** — numbered footnote list.\n\n## Anti-patterns\n\n- Apples-to-oranges — comparing a managed service, an OSS library, and a language feature in the same table without flagging the category mismatch.\n- Unweighted scoring pretending to be objective — a numeric total without axis weights reads neutral but smuggles in a preference.\n- Hiding vendor bias — sourcing only from the leader's own docs; not disclosing sponsored content.\n- Stale versions — comparing last year's version of one tool to this year's of another.\n- Missing axes — leaving out the axis where your preferred option scores badly.\n- Single \"winner\" call — a comparison table's job is to let the reader decide, not to pick for them.\n\n## Handoff\n\nReturn the table (inline or as a file path) to the invoking `researcher` specialist. The researcher may chain into `researcher-deep-dive` if a specific option needs broader investigation, or into `researcher-paper-digest` if a named paper backs one of the options. This skill does not dispatch.\n",{},"main","2e58b0360ca51ca3c96ca8e015ef5aba5738803d","skills\u002Fspecialists\u002Fresearcher-comparison-table",0,"https:\u002F\u002Fgithub.com\u002Flookatitude\u002Fguild","https:\u002F\u002Fgithub.com\u002Flookatitude","https:\u002F\u002Flookatitude.com","2026-11-06 03:55:18",{"source":7,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add lookatitude\u002Fguild --skill researcher-comparison-table",{"tool":41,"command":42},"bunx","bunx skills add lookatitude\u002Fguild --skill researcher-comparison-table",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lookatitude\u002Fguild --skill researcher-comparison-table","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flookatitude\u002Fguild\u002Fblob\u002Fmain\u002Fskills\u002Fspecialists\u002Fresearcher-comparison-table\u002FSKILL.md",true,[49],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"evals.json","REFERENCE","参考文档",691,"https:\u002F\u002Fgithub.com\u002Flookatitude\u002Fguild\u002Fblob\u002Fmain\u002Fskills\u002Fspecialists\u002Fresearcher-comparison-table\u002Fevals.json",[56,68,78,98,116,127],{"skillNo":57,"name":58,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":22},"01M71GQQ1ZAND0XQBS4GTSWYFK","technical-writer-user-manual","https:\u002F\u002Fgithub.com\u002Flookatitude\u002Fguild\u002Fblob\u002Fmain\u002Fskills\u002Fspecialists\u002Ftechnical-writer-user-manual\u002FSKILL.md",[],[62,63,64,65,66,67],"writer","technical","technical writer","technical writer user manual","manual","user",{"skillNo":69,"name":70,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":22},"01M71GQMQ71DQNH4A7REXRVFCB","technical-writer-release-notes","https:\u002F\u002Fgithub.com\u002Flookatitude\u002Fguild\u002Fblob\u002Fmain\u002Fskills\u002Fspecialists\u002Ftechnical-writer-release-notes\u002FSKILL.md",[],[74,62,75,76,77,63,64],"release","notes","technical writer release notes","release notes",{"skillNo":79,"name":80,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":93,"publishedAt":22},"01M71GQJQT9G8QHE0A9SN01VE4","technical-writer-api-docs","https:\u002F\u002Fgithub.com\u002Flookatitude\u002Fguild\u002Fblob\u002Fmain\u002Fskills\u002Fspecialists\u002Ftechnical-writer-api-docs\u002FSKILL.md",[83,88],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[94,63,64,95,96,97,62],"technical writer api docs","docs","api docs","api",{"skillNo":99,"name":100,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":109,"publishedAt":22},"01M71GQH3T5F23M2M298WXVAQ5","social-media-platform-post","https:\u002F\u002Fgithub.com\u002Flookatitude\u002Fguild\u002Fblob\u002Fmain\u002Fskills\u002Fspecialists\u002Fsocial-media-platform-post\u002FSKILL.md",[103,106],{"categoryNo":104,"categoryName":105,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000019","营销推广",{"categoryNo":107,"categoryName":108,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000035","市场营销",[110,111,112,113,114,115],"social media platform post","post","Media","platform","social","social media",{"skillNo":117,"name":118,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":123,"publishedAt":22},"01M71GQFS4MJ4S8ZRK7KQNNPJE","social-media-engagement-templates","https:\u002F\u002Fgithub.com\u002Flookatitude\u002Fguild\u002Fblob\u002Fmain\u002Fskills\u002Fspecialists\u002Fsocial-media-engagement-templates\u002FSKILL.md",[121,122],{"categoryNo":104,"categoryName":105,"taxonomyType":86,"taxonomyTypeDesc":87},{"categoryNo":107,"categoryName":108,"taxonomyType":91,"taxonomyTypeDesc":92},[114,124,112,125,126,115],"engagement","social media engagement templates","templates",{"skillNo":128,"name":129,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":137,"publishedAt":22},"01M71GQEPZ5GX6NBFQ9H0W5E0C","social-media-content-calendar","https:\u002F\u002Fgithub.com\u002Flookatitude\u002Fguild\u002Fblob\u002Fmain\u002Fskills\u002Fspecialists\u002Fsocial-media-content-calendar\u002FSKILL.md",[132,133,134],{"categoryNo":104,"categoryName":105,"taxonomyType":86,"taxonomyTypeDesc":87},{"categoryNo":107,"categoryName":108,"taxonomyType":91,"taxonomyTypeDesc":92},{"categoryNo":135,"categoryName":136,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000036","内容创作者",[138,139,114,115,140,141,112],"calendar","content calendar","social media content calendar","content"]