[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AE7G6DN5E99D2NKVFBSXH5":3,"skill-same:01M6AE7G6DN5E99D2NKVFBSXH5":67},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":48,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6AE7G6DN5E99D2NKVFBSXH5","signal-write",null,"Emit structured agent signals — hands-up, blocked, done, checkpoint, partnership. Signals are written as JSON to .signals\u002F for dashboard consumption and noted in the journal for persistence.","github\u002Fawesome-copilot","github","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9919?v=4","01M6AC83DS133TPXFSP1DHNCC6","GitHub","01M6AD3PBDYPK7NVFJNJ66Y8RS",41046,"MIT","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fsignal-write\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37],"signal write","write","signal","dashboard","persistence","checkpoint","json","up","done","signals","structured","journal","as","for","2026-11-10 10:12:30",false,"---\nname: signal-write\ndescription: 'Emit structured agent signals — hands-up, blocked, done, checkpoint, partnership. Signals are written as JSON to .signals\u002F for dashboard consumption and noted in the journal for persistence.'\n---\n\n# Agent Signals\n\nEmit structured signals from a desk to the operator or other desks.\n\n## When to use\n\n- A desk needs operator attention (hands-up, blocked)\n- Work is complete and ready for review (done)\n- Significant progress worth noting (checkpoint)\n- Two desks disagree and can't resolve it (hands-up)\n- The TA is reporting coordination quality (partnership)\n\n## Signal types\n\n### `hands-up`\nTwo desks disagree and can't settle it against external facts.\nThis is the system working — the operator reads where desks\n*disagree*, not where they perform confidence.\n\n### `blocked`\nA desk can't proceed without input — missing access, ambiguous\nscope, need a decision only the operator can make.\n\n### `done`\nWork is complete and ready for review. Artifacts are on the bench.\n\n### `checkpoint`\nSignificant progress worth the operator knowing about, but work\ncontinues. Not blocked, not done — just a marker.\n\n### `partnership`\nUsed by the TA (room coordinator) to report coordination quality.\nSelf-assessment scores reflect coordination, not code accuracy:\n- **intent** — understood what the operator needed\n- **confidence** — right work went to the right desks\n- **accuracy** — dispatched work produced the right outcome\n- **completeness** — nothing fell through the cracks\n\n## How to emit\n\n### 1. Write a JSON signal file to `.signals\u002F`\n\nThis is the primary output — it's what the dashboard reads.\nCreate `desks\u002F\u003Cdesk-name>\u002F.signals\u002F\u003Ctimestamp>.json` (for a desk in a\ngroup folder, `\u003Cgroup>-desks\u002F\u003Cdesk-name>\u002F.signals\u002F\u003Ctimestamp>.json`):\n\n```json\n{\n  \"signal_type\": \"execution\",\n  \"subtype\": \"checkpoint\",\n  \"timestamp\": \"2026-07-19T21:30:00Z\",\n  \"run_id\": \"\u003Coptional; set to pair this with an outcome signal>\",\n  \"agent_name\": \"\u003Cdesk-name>\",\n  \"self_assessment\": {\n    \"intent\": 4,\n    \"confidence\": 5,\n    \"accuracy\": 4,\n    \"completeness\": 3\n  },\n  \"patterns\": {\n    \"what_worked\": \"description of what went well\",\n    \"what_was_hard\": \"description of challenges\",\n    \"skill_gap\": \"areas for improvement\"\n  },\n  \"escalation\": {\n    \"reason\": null,\n    \"blocked_on\": null,\n    \"recommendation\": null\n  }\n}\n```\n\n### Signal type mapping\n\n| Signal    | `signal_type`   | `subtype`      |\n|-----------|-----------------|----------------|\n| hands-up  | `\"escalation\"`  | `\"hands-up\"`   |\n| blocked   | `\"escalation\"`  | `\"blocked\"`    |\n| done      | `\"execution\"`   | `\"done\"`       |\n| checkpoint| `\"execution\"`   | `\"checkpoint\"` |\n| partnership| `\"partnership\"` | `\"partnership\"`|\n\nThe `subtype` field preserves the specific signal state for\ndashboard consumers. `signal_type` controls sort priority\n(escalation → top).\n\n> **Note:** The signals-dashboard canvas extension reads `subtype`\n> when present and falls back to `signal_type` for display. If\n> consuming signals in your own tooling, prefer `subtype` for the\n> specific state.\n\n> **Ordering:** include a `timestamp` (ISO 8601 UTC). The dashboard\n> orders signals by it and falls back to file mtime only when it's\n> absent — a git clone\u002Fcheckout resets mtimes, so mtime alone is not a\n> dependable clock.\n\n### 2. Note the signal in the journal\n\nAlso append a short marker to the desk's journal for persistence:\n\n```markdown\n## \u003Cdate> — [signal:\u003Ctype>] \u003Csummary>\n- \u003Ckey details>\n```\n\nThe journal note is the trail marker. The JSON file is the\nmachine-readable signal.\n\n## Outcome signals (calibration)\n\nThe signals-dashboard can pair a desk's self-assessment with an\n*outcome* — an independent rating of the realized result — and show\nthe **honesty gap** (how far the desk's confidence was from the\ndelivered quality). Outcome signals are optional and are usually\nemitted by a reviewer\u002Fevaluator, not the desk itself.\n\nWrite them to the **same** `.signals\u002F` directory:\n\n```json\n{\n  \"signal_type\": \"outcome\",\n  \"run_id\": \"\u003Csame run_id as the signal it rates>\",\n  \"agent_name\": \"\u003Creviewer name>\",\n  \"quality_rating\": 4,\n  \"effort_to_merge\": \"minimal\",\n  \"issues_found\": [\"optional short strings\"],\n  \"timestamp\": \"2026-07-19T22:00:00Z\"\n}\n```\n\n- **`run_id`** correlates an outcome with the execution\u002Fpartnership\n  signal it rates — set the same `run_id` on both. If it's absent, the\n  dashboard falls back to the nearest outcome emitted shortly after the\n  latest signal.\n- **`quality_rating`** (0–5) is the realized quality; the dashboard\n  compares it to the desk's self-assessed `confidence` to compute the\n  honesty gap.\n- **`effort_to_merge`** — `\"minimal\"`, `\"moderate\"`, or `\"significant\"`.\n- **`issues_found`** — optional array of short strings.\n\n## Principles\n\n- Signals are structured, not chatty. Short, factual, actionable.\n- hands-up is not failure — it's the most valuable signal. It\n  means the system caught something one frame alone would have\n  missed.\n- Don't signal for routine progress. Signals are for state\n  changes that affect the room, not status updates.\n- blocked means truly blocked — not \"I'd prefer input.\" If you\n  can proceed with a reasonable default, proceed and note it.\n- Self-assessment scores should be honest, not optimistic. A 3\u002F5\n  is fine. A 5\u002F5 on everything is suspicious.\n","# Agent Signals\n\nEmit structured signals from a desk to the operator or other desks.\n\n## When to use\n\n- A desk needs operator attention (hands-up, blocked)\n- Work is complete and ready for review (done)\n- Significant progress worth noting (checkpoint)\n- Two desks disagree and can't resolve it (hands-up)\n- The TA is reporting coordination quality (partnership)\n\n## Signal types\n\n### `hands-up`\nTwo desks disagree and can't settle it against external facts.\nThis is the system working — the operator reads where desks\n*disagree*, not where they perform confidence.\n\n### `blocked`\nA desk can't proceed without input — missing access, ambiguous\nscope, need a decision only the operator can make.\n\n### `done`\nWork is complete and ready for review. Artifacts are on the bench.\n\n### `checkpoint`\nSignificant progress worth the operator knowing about, but work\ncontinues. Not blocked, not done — just a marker.\n\n### `partnership`\nUsed by the TA (room coordinator) to report coordination quality.\nSelf-assessment scores reflect coordination, not code accuracy:\n- **intent** — understood what the operator needed\n- **confidence** — right work went to the right desks\n- **accuracy** — dispatched work produced the right outcome\n- **completeness** — nothing fell through the cracks\n\n## How to emit\n\n### 1. Write a JSON signal file to `.signals\u002F`\n\nThis is the primary output — it's what the dashboard reads.\nCreate `desks\u002F\u003Cdesk-name>\u002F.signals\u002F\u003Ctimestamp>.json` (for a desk in a\ngroup folder, `\u003Cgroup>-desks\u002F\u003Cdesk-name>\u002F.signals\u002F\u003Ctimestamp>.json`):\n\n```json\n{\n  \"signal_type\": \"execution\",\n  \"subtype\": \"checkpoint\",\n  \"timestamp\": \"2026-07-19T21:30:00Z\",\n  \"run_id\": \"\u003Coptional; set to pair this with an outcome signal>\",\n  \"agent_name\": \"\u003Cdesk-name>\",\n  \"self_assessment\": {\n    \"intent\": 4,\n    \"confidence\": 5,\n    \"accuracy\": 4,\n    \"completeness\": 3\n  },\n  \"patterns\": {\n    \"what_worked\": \"description of what went well\",\n    \"what_was_hard\": \"description of challenges\",\n    \"skill_gap\": \"areas for improvement\"\n  },\n  \"escalation\": {\n    \"reason\": null,\n    \"blocked_on\": null,\n    \"recommendation\": null\n  }\n}\n```\n\n### Signal type mapping\n\n| Signal    | `signal_type`   | `subtype`      |\n|-----------|-----------------|----------------|\n| hands-up  | `\"escalation\"`  | `\"hands-up\"`   |\n| blocked   | `\"escalation\"`  | `\"blocked\"`    |\n| done      | `\"execution\"`   | `\"done\"`       |\n| checkpoint| `\"execution\"`   | `\"checkpoint\"` |\n| partnership| `\"partnership\"` | `\"partnership\"`|\n\nThe `subtype` field preserves the specific signal state for\ndashboard consumers. `signal_type` controls sort priority\n(escalation → top).\n\n> **Note:** The signals-dashboard canvas extension reads `subtype`\n> when present and falls back to `signal_type` for display. If\n> consuming signals in your own tooling, prefer `subtype` for the\n> specific state.\n\n> **Ordering:** include a `timestamp` (ISO 8601 UTC). The dashboard\n> orders signals by it and falls back to file mtime only when it's\n> absent — a git clone\u002Fcheckout resets mtimes, so mtime alone is not a\n> dependable clock.\n\n### 2. Note the signal in the journal\n\nAlso append a short marker to the desk's journal for persistence:\n\n```markdown\n## \u003Cdate> — [signal:\u003Ctype>] \u003Csummary>\n- \u003Ckey details>\n```\n\nThe journal note is the trail marker. The JSON file is the\nmachine-readable signal.\n\n## Outcome signals (calibration)\n\nThe signals-dashboard can pair a desk's self-assessment with an\n*outcome* — an independent rating of the realized result — and show\nthe **honesty gap** (how far the desk's confidence was from the\ndelivered quality). Outcome signals are optional and are usually\nemitted by a reviewer\u002Fevaluator, not the desk itself.\n\nWrite them to the **same** `.signals\u002F` directory:\n\n```json\n{\n  \"signal_type\": \"outcome\",\n  \"run_id\": \"\u003Csame run_id as the signal it rates>\",\n  \"agent_name\": \"\u003Creviewer name>\",\n  \"quality_rating\": 4,\n  \"effort_to_merge\": \"minimal\",\n  \"issues_found\": [\"optional short strings\"],\n  \"timestamp\": \"2026-07-19T22:00:00Z\"\n}\n```\n\n- **`run_id`** correlates an outcome with the execution\u002Fpartnership\n  signal it rates — set the same `run_id` on both. If it's absent, the\n  dashboard falls back to the nearest outcome emitted shortly after the\n  latest signal.\n- **`quality_rating`** (0–5) is the realized quality; the dashboard\n  compares it to the desk's self-assessed `confidence` to compute the\n  honesty gap.\n- **`effort_to_merge`** — `\"minimal\"`, `\"moderate\"`, or `\"significant\"`.\n- **`issues_found`** — optional array of short strings.\n\n## Principles\n\n- Signals are structured, not chatty. Short, factual, actionable.\n- hands-up is not failure — it's the most valuable signal. It\n  means the system caught something one frame alone would have\n  missed.\n- Don't signal for routine progress. Signals are for state\n  changes that affect the room, not status updates.\n- blocked means truly blocked — not \"I'd prefer input.\" If you\n  can proceed with a reasonable default, proceed and note it.\n- Self-assessment scores should be honest, not optimistic. A 3\u002F5\n  is fine. A 5\u002F5 on everything is suspicious.\n",{"name":5,"description":7},"main","227949a7542a55d2155c00e7cdb998d9a0fee4f3","skills\u002Fsignal-write",5340,"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.","2026-11-11 13:41:32",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add github\u002Fawesome-copilot --skill signal-write",{"tool":59,"command":60},"bunx","bunx skills add github\u002Fawesome-copilot --skill signal-write",{"tool":62,"command":63},"pnpm","pnpm dlx skills add github\u002Fawesome-copilot --skill signal-write","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fsignal-write\u002FSKILL.md",true,[],[68,97,124,154,188,205],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":78,"publishedAt":38},"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",[74,77],{"categoryNo":75,"categoryName":76,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[79,80,81,82,83,84,85,86,87,25,88,89,90,36,91,92,93,94,95,96],"supabase","rls","supabase rls","supabase rls policies","project","when","review","change","read","security","isolation","tables","tests","prove","use","users","functions","with",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":104,"publishedAt":38},"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",[103],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[105,106,107,108,109,110,37,111,112,113,114,115,116,117,118,119,120,121,122,123],"distribution","skill distribution audit","audit","SET","deterministic","installer","discovery","comparison","helper","manifest","version","collection","drift","output","investigate","duplicate","template","release","reconcile",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":128,"sourceHtmlUrl":129,"categories":130,"keywords":136,"publishedAt":38},"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",[131],{"categoryNo":132,"categoryName":133,"taxonomyType":134,"taxonomyTypeDesc":135},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[137,138,139,140,141,142,37,83,143,144,145,146,147,148,149,93,150,151,152,153],"custom","code","logicapps custom code net10 migration","migration","projects","standalone","deployment","applications","local","azure","worker","upgrades","package","apps","Legacy","debugging","workflows",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":158,"sourceHtmlUrl":159,"categories":160,"keywords":165,"publishedAt":38},"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",[161,164],{"categoryNo":162,"categoryName":163,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":132,"categoryName":133,"taxonomyType":134,"taxonomyTypeDesc":135},[166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,84,181,182,183,184,185,37,186,187],"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":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":192,"licenseFileUrl":193,"sourceHtmlUrl":194,"categories":195,"keywords":201,"publishedAt":38},"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",[196,197,200],{"categoryNo":162,"categoryName":163,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":198,"categoryName":199,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[202,108,175,203,204],"resemble detect","https","identity",{"skillNo":206,"name":207,"nameZh":6,"description":208,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":192,"licenseFileUrl":209,"sourceHtmlUrl":210,"categories":211,"keywords":216,"publishedAt":38},"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",[212,215],{"categoryNo":213,"categoryName":214,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[217,218,219,220,138,85,9,107,221,222,203,223,224,225,226,227,228,229,230,231,232,233,91,234,235,236,237],"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"]