[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69BW451AAT4733XGCA486KM":3,"skill-same:01M69BW451AAT4733XGCA486KM":72},{"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":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":43,"ownerDescription":44,"updatedAt":45,"install":46,"resources":59},"01M69BW451AAT4733XGCA486KM","pr-report",null,"Review a pull request or contribution deeply, explain it tutorial-style for a maintainer, and produce a polished report artifact such as HTML or Markdown. Use when asked to analyze a PR, explain a contributor's design decisions, compare it with similar systems, or prepare a merge recommendation.","microsoft\u002Famplifier-app-paperclip","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69BVQW2AS8MMMYW9A4DSSHW",1,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-paperclip\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpr-report\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[24,25,26,27,28,29,30,31],"pr","report","pr report","design","review","merge","prepare","pull request","2026-11-10 10:12:30",false,"---\nname: pr-report\ndescription: >\n  Review a pull request or contribution deeply, explain it tutorial-style for a\n  maintainer, and produce a polished report artifact such as HTML or Markdown.\n  Use when asked to analyze a PR, explain a contributor's design decisions,\n  compare it with similar systems, or prepare a merge recommendation.\n---\n\n# PR Report Skill\n\nProduce a maintainer-grade review of a PR, branch, or large contribution.\n\nDefault posture:\n\n- understand the change before judging it\n- explain the system as built, not just the diff\n- separate architectural problems from product-scope objections\n- make a concrete recommendation, not a vague impression\n\n## When to Use\n\nUse this skill when the user asks for things like:\n\n- \"review this PR deeply\"\n- \"explain this contribution to me\"\n- \"make me a report or webpage for this PR\"\n- \"compare this design to similar systems\"\n- \"should I merge this?\"\n\n## Outputs\n\nCommon outputs:\n\n- standalone HTML report in `tmp\u002Freports\u002F...`\n- Markdown report in `report\u002F` or another requested folder\n- short maintainer summary in chat\n\nIf the user asks for a webpage, build a polished standalone HTML artifact with\nclear sections and readable visual hierarchy.\n\nResources bundled with this skill:\n\n- `references\u002Fstyle-guide.md` for visual direction and report presentation rules\n- `assets\u002Fhtml-report-starter.html` for a reusable standalone HTML\u002FCSS starter\n\n## Workflow\n\n### 1. Acquire and frame the target\n\nWork from local code when possible, not just the GitHub PR page.\n\nGather:\n\n- target branch or worktree\n- diff size and changed subsystems\n- relevant repo docs, specs, and invariants\n- contributor intent if it is documented in PR text or design docs\n\nStart by answering: what is this change *trying* to become?\n\n### 2. Build a mental model of the system\n\nDo not stop at file-by-file notes. Reconstruct the design:\n\n- what new runtime or contract exists\n- which layers changed: db, shared types, server, UI, CLI, docs\n- lifecycle: install, startup, execution, UI, failure, disablement\n- trust boundary: what code runs where, under what authority\n\nFor large contributions, include a tutorial-style section that teaches the\nsystem from first principles.\n\n### 3. Review like a maintainer\n\nFindings come first. Order by severity.\n\nPrioritize:\n\n- behavioral regressions\n- trust or security gaps\n- misleading abstractions\n- lifecycle and operational risks\n- coupling that will be hard to unwind\n- missing tests or unverifiable claims\n\nAlways cite concrete file references when possible.\n\n### 4. Distinguish the objection type\n\nBe explicit about whether a concern is:\n\n- product direction\n- architecture\n- implementation quality\n- rollout strategy\n- documentation honesty\n\nDo not hide an architectural objection inside a scope objection.\n\n### 5. Compare to external precedents when needed\n\nIf the contribution introduces a framework or platform concept, compare it to\nsimilar open-source systems.\n\nWhen comparing:\n\n- prefer official docs or source\n- focus on extension boundaries, context passing, trust model, and UI ownership\n- extract lessons, not just similarities\n\nGood comparison questions:\n\n- Who owns lifecycle?\n- Who owns UI composition?\n- Is context explicit or ambient?\n- Are plugins trusted code or sandboxed code?\n- Are extension points named and typed?\n\n### 6. Make the recommendation actionable\n\nDo not stop at \"merge\" or \"do not merge.\"\n\nChoose one:\n\n- merge as-is\n- merge after specific redesign\n- salvage specific pieces\n- keep as design research\n\nIf rejecting or narrowing, say what should be kept.\n\nUseful recommendation buckets:\n\n- keep the protocol\u002Ftype model\n- redesign the UI boundary\n- narrow the initial surface area\n- defer third-party execution\n- ship a host-owned extension-point model first\n\n### 7. Build the artifact\n\nSuggested report structure:\n\n1. Executive summary\n2. What the PR actually adds\n3. Tutorial: how the system works\n4. Strengths\n5. Main findings\n6. Comparisons\n7. Recommendation\n\nFor HTML reports:\n\n- use intentional typography and color\n- make navigation easy for long reports\n- favor strong section headings and small reference labels\n- avoid generic dashboard styling\n\nBefore building from scratch, read `references\u002Fstyle-guide.md`.\nIf a fast polished starter is helpful, begin from `assets\u002Fhtml-report-starter.html`\nand replace the placeholder content with the actual report.\n\n### 8. Verify before handoff\n\nCheck:\n\n- artifact path exists\n- findings still match the actual code\n- any requested forbidden strings are absent from generated output\n- if tests were not run, say so explicitly\n\n## Review Heuristics\n\n### Plugin and platform work\n\nWatch closely for:\n\n- docs claiming sandboxing while runtime executes trusted host processes\n- module-global state used to smuggle React context\n- hidden dependence on render order\n- plugins reaching into host internals instead of using explicit APIs\n- \"capabilities\" that are really policy labels on top of fully trusted code\n\n### Good signs\n\n- typed contracts shared across layers\n- explicit extension points\n- host-owned lifecycle\n- honest trust model\n- narrow first rollout with room to grow\n\n## Final Response\n\nIn chat, summarize:\n\n- where the report is\n- your overall call\n- the top one or two reasons\n- whether verification or tests were skipped\n\nKeep the chat summary shorter than the report itself.\n","# PR Report Skill\n\nProduce a maintainer-grade review of a PR, branch, or large contribution.\n\nDefault posture:\n\n- understand the change before judging it\n- explain the system as built, not just the diff\n- separate architectural problems from product-scope objections\n- make a concrete recommendation, not a vague impression\n\n## When to Use\n\nUse this skill when the user asks for things like:\n\n- \"review this PR deeply\"\n- \"explain this contribution to me\"\n- \"make me a report or webpage for this PR\"\n- \"compare this design to similar systems\"\n- \"should I merge this?\"\n\n## Outputs\n\nCommon outputs:\n\n- standalone HTML report in `tmp\u002Freports\u002F...`\n- Markdown report in `report\u002F` or another requested folder\n- short maintainer summary in chat\n\nIf the user asks for a webpage, build a polished standalone HTML artifact with\nclear sections and readable visual hierarchy.\n\nResources bundled with this skill:\n\n- `references\u002Fstyle-guide.md` for visual direction and report presentation rules\n- `assets\u002Fhtml-report-starter.html` for a reusable standalone HTML\u002FCSS starter\n\n## Workflow\n\n### 1. Acquire and frame the target\n\nWork from local code when possible, not just the GitHub PR page.\n\nGather:\n\n- target branch or worktree\n- diff size and changed subsystems\n- relevant repo docs, specs, and invariants\n- contributor intent if it is documented in PR text or design docs\n\nStart by answering: what is this change *trying* to become?\n\n### 2. Build a mental model of the system\n\nDo not stop at file-by-file notes. Reconstruct the design:\n\n- what new runtime or contract exists\n- which layers changed: db, shared types, server, UI, CLI, docs\n- lifecycle: install, startup, execution, UI, failure, disablement\n- trust boundary: what code runs where, under what authority\n\nFor large contributions, include a tutorial-style section that teaches the\nsystem from first principles.\n\n### 3. Review like a maintainer\n\nFindings come first. Order by severity.\n\nPrioritize:\n\n- behavioral regressions\n- trust or security gaps\n- misleading abstractions\n- lifecycle and operational risks\n- coupling that will be hard to unwind\n- missing tests or unverifiable claims\n\nAlways cite concrete file references when possible.\n\n### 4. Distinguish the objection type\n\nBe explicit about whether a concern is:\n\n- product direction\n- architecture\n- implementation quality\n- rollout strategy\n- documentation honesty\n\nDo not hide an architectural objection inside a scope objection.\n\n### 5. Compare to external precedents when needed\n\nIf the contribution introduces a framework or platform concept, compare it to\nsimilar open-source systems.\n\nWhen comparing:\n\n- prefer official docs or source\n- focus on extension boundaries, context passing, trust model, and UI ownership\n- extract lessons, not just similarities\n\nGood comparison questions:\n\n- Who owns lifecycle?\n- Who owns UI composition?\n- Is context explicit or ambient?\n- Are plugins trusted code or sandboxed code?\n- Are extension points named and typed?\n\n### 6. Make the recommendation actionable\n\nDo not stop at \"merge\" or \"do not merge.\"\n\nChoose one:\n\n- merge as-is\n- merge after specific redesign\n- salvage specific pieces\n- keep as design research\n\nIf rejecting or narrowing, say what should be kept.\n\nUseful recommendation buckets:\n\n- keep the protocol\u002Ftype model\n- redesign the UI boundary\n- narrow the initial surface area\n- defer third-party execution\n- ship a host-owned extension-point model first\n\n### 7. Build the artifact\n\nSuggested report structure:\n\n1. Executive summary\n2. What the PR actually adds\n3. Tutorial: how the system works\n4. Strengths\n5. Main findings\n6. Comparisons\n7. Recommendation\n\nFor HTML reports:\n\n- use intentional typography and color\n- make navigation easy for long reports\n- favor strong section headings and small reference labels\n- avoid generic dashboard styling\n\nBefore building from scratch, read `references\u002Fstyle-guide.md`.\nIf a fast polished starter is helpful, begin from `assets\u002Fhtml-report-starter.html`\nand replace the placeholder content with the actual report.\n\n### 8. Verify before handoff\n\nCheck:\n\n- artifact path exists\n- findings still match the actual code\n- any requested forbidden strings are absent from generated output\n- if tests were not run, say so explicitly\n\n## Review Heuristics\n\n### Plugin and platform work\n\nWatch closely for:\n\n- docs claiming sandboxing while runtime executes trusted host processes\n- module-global state used to smuggle React context\n- hidden dependence on render order\n- plugins reaching into host internals instead of using explicit APIs\n- \"capabilities\" that are really policy labels on top of fully trusted code\n\n### Good signs\n\n- typed contracts shared across layers\n- explicit extension points\n- host-owned lifecycle\n- honest trust model\n- narrow first rollout with room to grow\n\n## Final Response\n\nIn chat, summarize:\n\n- where the report is\n- your overall call\n- the top one or two reasons\n- whether verification or tests were skipped\n\nKeep the chat summary shorter than the report itself.\n",{"name":5,"description":7},"main","d1d0e5a045f856af95eb693add053cc329774806",".agents\u002Fskills\u002Fpr-report",2,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-paperclip","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-10-30 04:25:15",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add microsoft\u002Famplifier-app-paperclip --skill pr-report",{"tool":52,"command":53},"bunx","bunx skills add microsoft\u002Famplifier-app-paperclip --skill pr-report",{"tool":55,"command":56},"pnpm","pnpm dlx skills add microsoft\u002Famplifier-app-paperclip --skill pr-report","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-paperclip\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpr-report\u002FSKILL.md",true,[60,66],{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"assets\u002Fhtml-report-starter.html","ASSET","资产文件",10588,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-paperclip\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpr-report\u002Fassets\u002Fhtml-report-starter.html",{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fstyle-guide.md","REFERENCE","参考文档",2948,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-paperclip\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpr-report\u002Freferences\u002Fstyle-guide.md",[73,88,103,115,124,138],{"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":32},"01M69BXXE3997X52Z13XH9ZCK4","terminal-bench-loop","Run a single Terminal-Bench problem through Paperclip in a bounded, human-in-the-loop improvement cycle until the smoke passes, the board rejects the next fix, the iteration budget is exhausted, or a real blocker is named. Each iteration runs a bounded smoke against an isolated Paperclip App worktree, captures artifacts, diagnoses the exact stop point with `\u002Fdiagnose-why-work-stopped`, requests board confirmation before any product fix, then reruns against the same worktree. Use whenever an issue asks to \"run Terminal-Bench in a loop\", \"drive Terminal-Bench until it passes\", \"loop fix-git through Paperclip\", or otherwise points at a Terminal-Bench task and asks for bounded iteration with diagnosis.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-paperclip\u002Fblob\u002Fmain\u002Fskills\u002Fterminal-bench-loop\u002FSKILL.md",[],[80,81,82,83,84,85,86,87],"terminal bench loop","terminal","git","artifacts","paperclip","diagnose","run","product",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":32},"01M69BXV7WMFG9YEPBB50Q40JY","para-memory-files","File-based memory system using Tiago Forte's PARA method. Use this skill whenever you need to store, retrieve, update, or organize knowledge across sessions. Covers three memory layers: (1) Knowledge graph in PARA folders with atomic YAML facts, (2) Daily notes as raw timeline, (3) Tacit knowledge about user patterns. Also handles planning files, memory decay, weekly synthesis, and recall via qmd. Trigger on any memory operation: saving facts, writing daily notes, creating entities, running weekly synthesis, recalling past context, or managing plans.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-paperclip\u002Fblob\u002Fmain\u002Fskills\u002Fpara-memory-files\u002FSKILL.md",[],[95,96,97,98,99,100,101,102],"memory","para memory files","planning","update","notes","sessions","qmd","writing",{"skillNo":104,"name":84,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":32},"01M69BXRE769BJ5W05W2XQ85T6","Interact with the Paperclip control plane API to manage tasks, coordinate with other agents, and follow company governance. Use when you need to check assignments, update task status, delegate work, post comments, set up or manage routines (recurring scheduled tasks), or call any Paperclip API endpoint. Do NOT use for the actual domain work itself (writing code, research, etc.) — only for Paperclip coordination.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-paperclip\u002Fblob\u002Fmain\u002Fskills\u002Fpaperclip\u002FSKILL.md",[],[84,109,110,98,111,112,113,114,102],"status","code","tasks","governance","research","routines",{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":32},"01M69BXMREYNEVHE276GFTMFBZ","paperclip-dev","Develop and operate a local Paperclip instance — start and stop servers, pull updates from master, run builds and tests, manage worktrees, back up databases, and diagnose problems. Use whenever you need to work on the Paperclip codebase itself or keep a running instance healthy.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-paperclip\u002Fblob\u002Fmain\u002Fskills\u002Fpaperclip-dev\u002FSKILL.md",[],[122,84,123,86,85],"paperclip dev","dev",{"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":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":32},"01M69BXHSPWG60R76MMXJCBRG2","paperclip-create-plugin","Create and develop external Paperclip plugins with the CLI-first workflow. Use when scaffolding a new plugin, working on a local plugin against a running Paperclip instance, or updating plugin authoring docs. Covers `paperclipai plugin init`, the local install loop via `paperclipai plugin install \u003Cpath>`, worker\u002FUI rebuild and reload semantics, and the required success checklist.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-paperclip\u002Fblob\u002Fmain\u002Fskills\u002Fpaperclip-create-plugin\u002FSKILL.md",[],[131,84,132,133,134,135,136,137],"paperclip create plugin","plugin","create","init","workflow","docs","cli",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":149,"publishedAt":32},"01M69BXF0D8J59MN3MF30F6NGW","paperclip-create-agent","Create new agents in Paperclip with governance-aware hiring. Use when you need to inspect adapter configuration options, compare existing agent configs, draft a new agent prompt\u002Fconfig, and submit a hire request.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Famplifier-app-paperclip\u002Fblob\u002Fmain\u002Fskills\u002Fpaperclip-create-agent\u002FSKILL.md",[144],{"categoryNo":145,"categoryName":146,"taxonomyType":147,"taxonomyTypeDesc":148},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[150,133,84,151,112,152],"create agent","paperclip create agent","config"]