[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ADA7GCXMG52HW792Z831W6":3,"skill-same:01M6ADA7GCXMG52HW792Z831W6":88},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":49,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M6ADA7GCXMG52HW792Z831W6","build-evidence-map",null,"Build an auditable evidence map for a contested technical choice, research synthesis, proposal review, or consequential decision. Use when Copilot must preserve supporting, contradicting, qualifying, and missing evidence with exact source regions instead of collapsing disagreement into prose.","github\u002Fawesome-copilot","github","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9919?v=4","01M6AC83DS133TPXFSP1DHNCC6","GitHub","01M6AD3PBDYPK7NVFJNJ66Y8RS",41081,"MIT","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-evidence-map\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"build evidence map","evidence","build","map","prose","when","preserve","source","for","with","proposal","research synthesis","missing","review","use","technical","choice","decision","copilot","research","2026-11-10 10:12:30",false,"---\nname: build-evidence-map\ndescription: 'Build an auditable evidence map for a contested technical choice, research synthesis, proposal review, or consequential decision. Use when Copilot must preserve supporting, contradicting, qualifying, and missing evidence with exact source regions instead of collapsing disagreement into prose.'\n---\n\n# Build Evidence Map\n\nTurn one contested question into a portable decision artifact that shows what\nsupports the current position, what pushes against it, and what remains unknown.\nDo not use a graph to decorate an answer that has not been sourced.\n\nFor a simple factual claim or a general fact-checking request, use a verification\nworkflow such as `doublecheck` instead. Use this skill when the relationships\nbetween evidence, intermediate claims, trade-offs, and missing facts matter.\n\n## Workflow\n\n1. **Frame one decision.** Write one falsifiable question and one provisional\n   position. Narrow the question until a reader can identify what action or\n   belief the map is testing.\n2. **Collect bounded source regions.** Prefer direct observations and primary\n   sources. Record the URL or absolute local path, publisher, publication date,\n   retrieval date, section\u002Fpage\u002Fline\u002Ftimestamp locator, and a short checkable\n   excerpt. Read [references\u002Fevidence-ladder.md](references\u002Fevidence-ladder.md)\n   when source quality is disputed.\n3. **Atomize the reasoning.** Create only four node types:\n   - `position`: the single current verdict;\n   - `claim`: an intermediate proposition;\n   - `evidence`: a faithful statement of one source region;\n   - `unknown`: a specific missing fact that could change the verdict.\n4. **Type every edge.** Use `supports`, `contradicts`, `qualifies`, or\n   `missing`. Add a plain-language note explaining why the source node bears on\n   the target. Topical similarity is not support. Different scope, date, or\n   population is not automatically a contradiction.\n5. **Preserve counterevidence.** Do not delete contrary evidence because the\n   provisional verdict survives it. Represent scope differences with\n   `qualifies` edges.\n6. **Express uncertainty structurally.** Do not invent confidence percentages.\n   Add an `unknown`, narrow the position, or qualify a claim.\n7. **Write UTF-8 JSON** with a `.doubt.json` suffix. Follow\n   [references\u002Fmap-schema.md](references\u002Fmap-schema.md). Keep IDs short,\n   stable, and semantic.\n8. **Validate fail-closed.** Resolve\n   `scripts\u002Fvalidate.mjs` relative to this `SKILL.md`, then run it with Node.js\n   18 or newer:\n\n   ```bash\n   node \u003Cskill-directory>\u002Fscripts\u002Fvalidate.mjs decision.doubt.json\n   ```\n\n   The bundled validator uses only Node.js built-ins and does not require npm or\n   network access. Fix every finding before reporting success. Only say the map\n   is valid when the command exits `0` and prints `VALID` followed by a\n   64-character receipt. A file hash, node count, JSON parse, or manual schema\n   review is not a Doubt receipt. If deterministic validation cannot run, report\n   that block instead of inventing success.\n\n   Render the validated map only when the user has already installed\n   `doubt-ai@0.8.0`; do not install or execute a remote package implicitly:\n\n   ```bash\n   doubt map decision.doubt.json --out decision.html\n   ```\n9. **Verify source snapshots only with explicit network permission.** The\n   following command retrieves each recorded HTTP(S) source and fails closed if\n   an excerpt cannot be matched:\n\n   ```bash\n   doubt verify decision.doubt.json \\\n     --out decision.verified.doubt.json\n   ```\n\n   Never run this command implicitly. Local file verification does not use the\n   network. Do not write a `verification` object by hand or hide a mismatch.\n10. **Inspect the deliverable.** Confirm that the question, verdict,\n    counterevidence, unknowns, edge notes, and exact source regions remain\n    readable. Treat JSON as the canonical editable artifact; HTML is a\n    shareable view.\n\n## Quality gates\n\nA finished map must satisfy all of these:\n\n- exactly one `position` has incoming reasoning;\n- every evidence node names one source and participates in an edge;\n- every source is used and has dates, a bounded locator, and a substantive\n  excerpt;\n- every non-position node has a directed path to the position;\n- the reasoning graph has no duplicate edges or directed cycles;\n- contrary or qualifying evidence is present when the source set contains it;\n- each decision-changing gap is an explicit `unknown` node;\n- every edge note explains support, contradiction, qualification, or absence;\n- the verdict is no broader than the evidence.\n\n## Deliver the result\n\nReport:\n\n- the current position in one sentence;\n- the strongest counterevidence or qualification;\n- the most important unresolved unknown;\n- paths to the canonical JSON and any rendered HTML;\n- whether deterministic validation and explicit source verification ran.\n\nNever describe a structurally valid map as proven true. Validation establishes\ntraceability and graph integrity; source quality and inference quality still\nrequire human review.\n","# Build Evidence Map\n\nTurn one contested question into a portable decision artifact that shows what\nsupports the current position, what pushes against it, and what remains unknown.\nDo not use a graph to decorate an answer that has not been sourced.\n\nFor a simple factual claim or a general fact-checking request, use a verification\nworkflow such as `doublecheck` instead. Use this skill when the relationships\nbetween evidence, intermediate claims, trade-offs, and missing facts matter.\n\n## Workflow\n\n1. **Frame one decision.** Write one falsifiable question and one provisional\n   position. Narrow the question until a reader can identify what action or\n   belief the map is testing.\n2. **Collect bounded source regions.** Prefer direct observations and primary\n   sources. Record the URL or absolute local path, publisher, publication date,\n   retrieval date, section\u002Fpage\u002Fline\u002Ftimestamp locator, and a short checkable\n   excerpt. Read [references\u002Fevidence-ladder.md](references\u002Fevidence-ladder.md)\n   when source quality is disputed.\n3. **Atomize the reasoning.** Create only four node types:\n   - `position`: the single current verdict;\n   - `claim`: an intermediate proposition;\n   - `evidence`: a faithful statement of one source region;\n   - `unknown`: a specific missing fact that could change the verdict.\n4. **Type every edge.** Use `supports`, `contradicts`, `qualifies`, or\n   `missing`. Add a plain-language note explaining why the source node bears on\n   the target. Topical similarity is not support. Different scope, date, or\n   population is not automatically a contradiction.\n5. **Preserve counterevidence.** Do not delete contrary evidence because the\n   provisional verdict survives it. Represent scope differences with\n   `qualifies` edges.\n6. **Express uncertainty structurally.** Do not invent confidence percentages.\n   Add an `unknown`, narrow the position, or qualify a claim.\n7. **Write UTF-8 JSON** with a `.doubt.json` suffix. Follow\n   [references\u002Fmap-schema.md](references\u002Fmap-schema.md). Keep IDs short,\n   stable, and semantic.\n8. **Validate fail-closed.** Resolve\n   `scripts\u002Fvalidate.mjs` relative to this `SKILL.md`, then run it with Node.js\n   18 or newer:\n\n   ```bash\n   node \u003Cskill-directory>\u002Fscripts\u002Fvalidate.mjs decision.doubt.json\n   ```\n\n   The bundled validator uses only Node.js built-ins and does not require npm or\n   network access. Fix every finding before reporting success. Only say the map\n   is valid when the command exits `0` and prints `VALID` followed by a\n   64-character receipt. A file hash, node count, JSON parse, or manual schema\n   review is not a Doubt receipt. If deterministic validation cannot run, report\n   that block instead of inventing success.\n\n   Render the validated map only when the user has already installed\n   `doubt-ai@0.8.0`; do not install or execute a remote package implicitly:\n\n   ```bash\n   doubt map decision.doubt.json --out decision.html\n   ```\n9. **Verify source snapshots only with explicit network permission.** The\n   following command retrieves each recorded HTTP(S) source and fails closed if\n   an excerpt cannot be matched:\n\n   ```bash\n   doubt verify decision.doubt.json \\\n     --out decision.verified.doubt.json\n   ```\n\n   Never run this command implicitly. Local file verification does not use the\n   network. Do not write a `verification` object by hand or hide a mismatch.\n10. **Inspect the deliverable.** Confirm that the question, verdict,\n    counterevidence, unknowns, edge notes, and exact source regions remain\n    readable. Treat JSON as the canonical editable artifact; HTML is a\n    shareable view.\n\n## Quality gates\n\nA finished map must satisfy all of these:\n\n- exactly one `position` has incoming reasoning;\n- every evidence node names one source and participates in an edge;\n- every source is used and has dates, a bounded locator, and a substantive\n  excerpt;\n- every non-position node has a directed path to the position;\n- the reasoning graph has no duplicate edges or directed cycles;\n- contrary or qualifying evidence is present when the source set contains it;\n- each decision-changing gap is an explicit `unknown` node;\n- every edge note explains support, contradiction, qualification, or absence;\n- the verdict is no broader than the evidence.\n\n## Deliver the result\n\nReport:\n\n- the current position in one sentence;\n- the strongest counterevidence or qualification;\n- the most important unresolved unknown;\n- paths to the canonical JSON and any rendered HTML;\n- whether deterministic validation and explicit source verification ran.\n\nNever describe a structurally valid map as proven true. Validation establishes\ntraceability and graph integrity; source quality and inference quality still\nrequire human review.\n",{"name":5,"description":7},"main","5269f7ea2d6c3a9bfda5ed878b6726cf509121fd","skills\u002Fbuild-evidence-map",5344,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot","https:\u002F\u002Fawesome-copilot.github.com\u002F","https:\u002F\u002Fgithub.com\u002Fgithub","https:\u002F\u002Fgithub.com\u002Fabout","How people build software.","2026-11-13 02:05:36",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add github\u002Fawesome-copilot --skill build-evidence-map",{"tool":60,"command":61},"bunx","bunx skills add github\u002Fawesome-copilot --skill build-evidence-map",{"tool":63,"command":64},"pnpm","pnpm dlx skills add github\u002Fawesome-copilot --skill build-evidence-map","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-evidence-map\u002FSKILL.md",true,[68,74,78,84],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fevidence-ladder.md","REFERENCE","参考文档",1812,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-evidence-map\u002Freferences\u002Fevidence-ladder.md",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fmap-schema.md",3254,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-evidence-map\u002Freferences\u002Fmap-schema.md",{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"scripts\u002Fcontract.mjs","SCRIPT","脚本",18270,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-evidence-map\u002Fscripts\u002Fcontract.mjs",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"scripts\u002Fvalidate.mjs",2886,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-evidence-map\u002Fscripts\u002Fvalidate.mjs",[89,120,147,177,211,228],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":103,"publishedAt":39},"01M70KXZNX9ES38N2A8M58ZZMZ","supabase-rls-policies","Write, review, and test Supabase Row Level Security (RLS) policies so that one user cannot read or change another user's rows. Use when creating or changing tables, policies, views, or security definer functions in a Supabase project, when reviewing a migration that touches RLS, or when asked to prove user isolation with pgTAP tests that sign in as two users.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fsupabase-rls-policies\u002FSKILL.md",[95,100],{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":101,"categoryName":102,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000023","Skill与智能体开发",[104,105,106,107,108,24,32,109,110,111,112,113,114,115,116,117,33,118,119,28],"supabase","rls","supabase rls","supabase rls policies","project","change","read","write","security","isolation","tables","as","tests","prove","users","functions",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":127,"publishedAt":39},"01M70KWA5YWXDV6V8DZ19E3T2Y","skill-distribution-audit","Audit a skill collection before release or investigate installer omissions, archived\u002Ftemplate leakage, duplicate identities, and manifest drift. Reconcile the intended public source set, distribution manifest, and actual discovery output for a specified consumer version. Includes a deterministic set-comparison helper.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fskill-distribution-audit\u002FSKILL.md",[126],{"categoryNo":101,"categoryName":102,"taxonomyType":98,"taxonomyTypeDesc":99},[128,129,130,131,132,133,27,134,135,136,137,138,139,140,141,142,143,144,145,146],"distribution","skill distribution audit","audit","SET","deterministic","installer","discovery","comparison","helper","manifest","version","collection","drift","output","investigate","duplicate","template","release","reconcile",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":151,"sourceHtmlUrl":152,"categories":153,"keywords":159,"publishedAt":39},"01M70KCJPFVW7PPQ49CC5R8JGK","logicapps-custom-code-net10-migration","Migrate Azure Logic Apps Standard local-function custom-code projects from .NET 8 to .NET 10. Use for legacy Logic Apps custom-code workspace upgrades, project\u002Fpackage configuration, custom-worker settings, publication, and integrated VS Code debugging. Not for ordinary .NET applications, standalone Azure Functions, Consumption workflows, or cloud deployment.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Flogicapps-custom-code-net10-migration\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Flogicapps-custom-code-net10-migration\u002FSKILL.md",[154],{"categoryNo":155,"categoryName":156,"taxonomyType":157,"taxonomyTypeDesc":158},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[160,161,162,163,164,165,27,108,166,167,168,169,170,171,172,33,173,174,175,176],"custom","code","logicapps custom code net10 migration","migration","projects","standalone","deployment","applications","local","azure","worker","upgrades","package","apps","Legacy","debugging","workflows",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":181,"sourceHtmlUrl":182,"categories":183,"keywords":188,"publishedAt":39},"01M6AEBN37RQMXJ3298PEY7PG1","winmd-api-search","Find and explore Windows desktop APIs. Use when building features that need platform capabilities — camera, file access, notifications, UI controls, AI\u002FML, sensors, networking, etc. Discovers the right API for a task and retrieves full type details (methods, properties, events, enumeration values).","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fwinmd-api-search\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fwinmd-api-search\u002FSKILL.md",[184,187],{"categoryNo":185,"categoryName":186,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":155,"categoryName":156,"taxonomyType":157,"taxonomyTypeDesc":158},[189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,24,204,205,206,207,208,27,209,210],"winmd api search","search","api","windows","desktop","file access","enumeration","ui","ml","file","networking","capabilities","notifications","explore","access","features","full","camera","events","platform","methods","controls",{"skillNo":212,"name":213,"nameZh":6,"description":214,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":215,"licenseFileUrl":216,"sourceHtmlUrl":217,"categories":218,"keywords":224,"publishedAt":39},"01M6AE571R3SC1ZGE202B3NB5S","resemble-detect","Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using Resemble AI","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fresemble-detect\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fresemble-detect\u002FSKILL.md",[219,220,223],{"categoryNo":185,"categoryName":186,"taxonomyType":98,"taxonomyTypeDesc":99},{"categoryNo":221,"categoryName":222,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":101,"categoryName":102,"taxonomyType":98,"taxonomyTypeDesc":99},[225,131,198,226,227],"resemble detect","https","identity",{"skillNo":229,"name":230,"nameZh":6,"description":231,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":215,"licenseFileUrl":232,"sourceHtmlUrl":233,"categories":234,"keywords":239,"publishedAt":39},"01M6AE30BSK2HCY4TQQ22Z8JRD","quality-playbook","Run a complete quality engineering audit on any codebase. Derives behavioral requirements from the code, generates spec-traced functional tests, runs a three-pass code review with regression tests, executes a multi-model spec audit (Council of Three), and produces a consolidated bug report with TDD-verified patches. Finds the 35% of real defects that structural code review alone cannot catch. Works with any language. Trigger on 'quality playbook', 'spec audit', 'Council of Three', 'fitness-to-purpose', or 'coverage theater'.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fquality-playbook\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fquality-playbook\u002FSKILL.md",[235,238],{"categoryNo":236,"categoryName":237,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":101,"categoryName":102,"taxonomyType":98,"taxonomyTypeDesc":99},[240,241,242,243,161,32,9,130,244,245,226,246,247,248,249,250,251,252,253,254,255,256,116,257,258,259,260],"playbook","quality playbook","quality","code review","tdd","run","report","spec","bug report","council","engineering","functional","spec audit","bug","verified","multi-model","three","coverage","model","regression","structural"]