[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-microsoft-review-plan":3,"mdc-ms8kxu-key":34,"related-repo-microsoft-review-plan":430,"related-org-microsoft-review-plan":522},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":29,"sourceUrl":32,"mdContent":33},"review-plan","review implementation plans for gaps","Review an implementation plan produced by the Plan agent. It is CRITICAL to review plans before handing off to implementation — plans often have gaps, incorrect assumptions, or suboptimal sequencing that are cheaper to catch now than after coding. Use when the user asks to 'review the plan', 'check my plan', 'is this plan ready', or after the Plan agent produces a plan.md.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"microsoft","Microsoft","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fmicrosoft.png",[12,16,19,20],{"name":13,"slug":14,"type":15},"Code Review","code-review","tag",{"name":17,"slug":18,"type":15},"Process Optimization","process-optimization",{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},"Engineering","engineering",25,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvscode-team-kit","2026-07-07T06:54:02.962612",null,5,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":31},[],"Plugins the VS Code team uses","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fvscode-team-kit\u002Ftree\u002FHEAD\u002Freview-plan\u002Fskills\u002Freview-plan","---\nname: review-plan\ndescription: \"Review an implementation plan produced by the Plan agent. It is CRITICAL to review plans before handing off to implementation — plans often have gaps, incorrect assumptions, or suboptimal sequencing that are cheaper to catch now than after coding. Use when the user asks to 'review the plan', 'check my plan', 'is this plan ready', or after the Plan agent produces a plan.md.\"\n---\n\n# Skill: Review Plan\n\nYour goal is to CRITICALLY review the given implementation plan. Provide thorough, constructive feedback that enhances the plan's quality and likelihood of successful execution and solving the stated goal.\n\nFan out parallel read-only subagents, each assigned a different plan-review area, then synthesize the highest-signal findings. Each subagent goes deep on one area, catching gaps a single pass misses.\n\n## Review Areas\n\nPick 2–4 areas based on the plan's complexity and risk profile.\n\n| Area | Focus |\n|------|-------|\n| **Completeness** | Missing requirements, unaddressed edge cases, gaps between the stated goal and proposed steps, unclear expected outcomes |\n| **Grounding** | Technical soundness and factual accuracy — references to nonexistent or deprecated APIs, hallucinated functions, incorrect codebase assumptions, outdated versions. Use web search to validate uncertain claims. Suggest alternative approaches when the plan is fundamentally wrong |\n| **Sequencing** | Dependency correctness between steps, parallelism opportunities missed, blocking-step identification, optimal ordering |\n| **Scope** | Over-engineering, gold-plating, scope creep or under-specification, scope disproportionate to value delivered |\n| **Verification** | Are verification steps specific, actionable, and covering the riskiest parts of the change? Missing test strategies |\n| **Risk** | Unaddressed failure modes, migration risks, backward compatibility gaps, missing rollback strategy |\n\n## Workflow\n\n### 1 — Scope\n\n- Look for a plan in session memory at `\u002Fmemories\u002Fsession\u002Fplan.md` first.\n- If no session plan exists, check for a plan file the user points to, or a plan visible in the conversation context.\n- If there is nothing to review, ask the user to run the Plan agent first or point at a plan file.\n\n### 2 — Fan Out\n\nLaunch 2–5 parallel subagents using the area prompts below. Each subagent works in isolation — do not share one area's findings with another before synthesis.\n\nEach gets a self-contained prompt with its area, the plan location, and the return format. Subagents read the full plan from session memory themselves. Subagents may surface findings their area doesn't explicitly list — don't constrain them to only the listed focus items.\n\n### 3 — Synthesize\n\nWhen all subagents return:\n\n1. Deduplicate findings that overlap across areas (e.g., a feasibility gap that also shows up as a sequencing problem).\n2. Order by severity: missing requirements > incorrect assumptions > sequencing errors > scope issues > weak verification > minor risks.\n3. Apply the signal filter — drop anything that wouldn't actually cause problems during implementation.\n4. If no blocking issues survive, say so and note any areas where the plan could be strengthened.\n\n### 4 — Save Findings\n\nAlways save the synthesized findings to session memory at `\u002Fmemories\u002Fsession\u002Fplan-review.md`. This makes them available for follow-up turns, plan revision, and cross-referencing during implementation.\n\n### 5 — Revise or Report\n\n- **Review-only**: if the user said \"only review\", \"just review\", or \"read-only\", stop after reporting.\n- **Default (review-and-revise)**:\n  1. For each actionable finding, propose a specific revision to the plan — what to add, remove, reorder, or clarify.\n  2. Apply revisions to the plan in session memory (`\u002Fmemories\u002Fsession\u002Fplan.md`), preserving the plan's existing structure.\n  3. After revising, re-read the updated plan to confirm the revisions are coherent.\n  4. Report what was revised and any remaining items that need the user's input or a decision.\n\n## Signal Filter\n\nBefore reporting a finding, ask: *Does this change what a developer would actually do — or how likely the plan is to succeed?* Ground every finding in something observable: a file that doesn't exist, an API that behaves differently, a requirement the steps don't cover, a sequence that creates rework.\n\nIf a concern is speculative, cosmetic, or unrelated to the plan's goal, leave it out.\n\n## Area Prompt\n\nEach subagent gets this prompt with `{AREA}` and `{FOCUS}` filled in from the Review Areas table.\n\n```text\nYou are a focused plan-review subagent. Your area is: {AREA}\n\n## Where to find the plan\nThe plan is in session memory at `\u002Fmemories\u002Fsession\u002Fplan.md`. Read it with your memory tools first. Then explore the codebase to validate the plan's assumptions — check that referenced files, functions, and patterns actually exist.\n\nFocus on: {FOCUS}\n\nUse your tools to read the full plan, inspect the codebase, verify assumptions, and run existing tests or check lint\u002Fcompile errors for evidence. Use web search to validate uncertain API or version claims.\n\nRules:\n- Stay read-only. Do not edit files.\n- Only flag issues that would change what a developer actually does or how likely the plan is to succeed.\n- Do not report issues outside your area, but do surface unexpected findings within it.\n- Do not rewrite the plan — describe the problem and why it matters.\n- Keep your response short. No preamble, no formatting commentary.\n\nReturn format:\n\n**Area**: {AREA}\n\n**Findings** (0–5 items, severity order):\n- One-sentence description. Why it matters. Evidence from the codebase if applicable.\n\nIf the plan is sound for your area: \"No issues found in {AREA}.\"\n```\n",{"data":35,"body":36},{"name":4,"description":6},{"type":37,"children":38},"root",[39,48,54,59,66,71,196,202,209,238,244,249,254,260,265,289,295,308,314,367,373,386,391,397,418],{"type":40,"tag":41,"props":42,"children":44},"element","h1",{"id":43},"skill-review-plan",[45],{"type":46,"value":47},"text","Skill: Review Plan",{"type":40,"tag":49,"props":50,"children":51},"p",{},[52],{"type":46,"value":53},"Your goal is to CRITICALLY review the given implementation plan. Provide thorough, constructive feedback that enhances the plan's quality and likelihood of successful execution and solving the stated goal.",{"type":40,"tag":49,"props":55,"children":56},{},[57],{"type":46,"value":58},"Fan out parallel read-only subagents, each assigned a different plan-review area, then synthesize the highest-signal findings. Each subagent goes deep on one area, catching gaps a single pass misses.",{"type":40,"tag":60,"props":61,"children":63},"h2",{"id":62},"review-areas",[64],{"type":46,"value":65},"Review Areas",{"type":40,"tag":49,"props":67,"children":68},{},[69],{"type":46,"value":70},"Pick 2–4 areas based on the plan's complexity and risk profile.",{"type":40,"tag":72,"props":73,"children":74},"table",{},[75,94],{"type":40,"tag":76,"props":77,"children":78},"thead",{},[79],{"type":40,"tag":80,"props":81,"children":82},"tr",{},[83,89],{"type":40,"tag":84,"props":85,"children":86},"th",{},[87],{"type":46,"value":88},"Area",{"type":40,"tag":84,"props":90,"children":91},{},[92],{"type":46,"value":93},"Focus",{"type":40,"tag":95,"props":96,"children":97},"tbody",{},[98,116,132,148,164,180],{"type":40,"tag":80,"props":99,"children":100},{},[101,111],{"type":40,"tag":102,"props":103,"children":104},"td",{},[105],{"type":40,"tag":106,"props":107,"children":108},"strong",{},[109],{"type":46,"value":110},"Completeness",{"type":40,"tag":102,"props":112,"children":113},{},[114],{"type":46,"value":115},"Missing requirements, unaddressed edge cases, gaps between the stated goal and proposed steps, unclear expected outcomes",{"type":40,"tag":80,"props":117,"children":118},{},[119,127],{"type":40,"tag":102,"props":120,"children":121},{},[122],{"type":40,"tag":106,"props":123,"children":124},{},[125],{"type":46,"value":126},"Grounding",{"type":40,"tag":102,"props":128,"children":129},{},[130],{"type":46,"value":131},"Technical soundness and factual accuracy — references to nonexistent or deprecated APIs, hallucinated functions, incorrect codebase assumptions, outdated versions. Use web search to validate uncertain claims. Suggest alternative approaches when the plan is fundamentally wrong",{"type":40,"tag":80,"props":133,"children":134},{},[135,143],{"type":40,"tag":102,"props":136,"children":137},{},[138],{"type":40,"tag":106,"props":139,"children":140},{},[141],{"type":46,"value":142},"Sequencing",{"type":40,"tag":102,"props":144,"children":145},{},[146],{"type":46,"value":147},"Dependency correctness between steps, parallelism opportunities missed, blocking-step identification, optimal ordering",{"type":40,"tag":80,"props":149,"children":150},{},[151,159],{"type":40,"tag":102,"props":152,"children":153},{},[154],{"type":40,"tag":106,"props":155,"children":156},{},[157],{"type":46,"value":158},"Scope",{"type":40,"tag":102,"props":160,"children":161},{},[162],{"type":46,"value":163},"Over-engineering, gold-plating, scope creep or under-specification, scope disproportionate to value delivered",{"type":40,"tag":80,"props":165,"children":166},{},[167,175],{"type":40,"tag":102,"props":168,"children":169},{},[170],{"type":40,"tag":106,"props":171,"children":172},{},[173],{"type":46,"value":174},"Verification",{"type":40,"tag":102,"props":176,"children":177},{},[178],{"type":46,"value":179},"Are verification steps specific, actionable, and covering the riskiest parts of the change? Missing test strategies",{"type":40,"tag":80,"props":181,"children":182},{},[183,191],{"type":40,"tag":102,"props":184,"children":185},{},[186],{"type":40,"tag":106,"props":187,"children":188},{},[189],{"type":46,"value":190},"Risk",{"type":40,"tag":102,"props":192,"children":193},{},[194],{"type":46,"value":195},"Unaddressed failure modes, migration risks, backward compatibility gaps, missing rollback strategy",{"type":40,"tag":60,"props":197,"children":199},{"id":198},"workflow",[200],{"type":46,"value":201},"Workflow",{"type":40,"tag":203,"props":204,"children":206},"h3",{"id":205},"_1-scope",[207],{"type":46,"value":208},"1 — Scope",{"type":40,"tag":210,"props":211,"children":212},"ul",{},[213,228,233],{"type":40,"tag":214,"props":215,"children":216},"li",{},[217,219,226],{"type":46,"value":218},"Look for a plan in session memory at ",{"type":40,"tag":220,"props":221,"children":223},"code",{"className":222},[],[224],{"type":46,"value":225},"\u002Fmemories\u002Fsession\u002Fplan.md",{"type":46,"value":227}," first.",{"type":40,"tag":214,"props":229,"children":230},{},[231],{"type":46,"value":232},"If no session plan exists, check for a plan file the user points to, or a plan visible in the conversation context.",{"type":40,"tag":214,"props":234,"children":235},{},[236],{"type":46,"value":237},"If there is nothing to review, ask the user to run the Plan agent first or point at a plan file.",{"type":40,"tag":203,"props":239,"children":241},{"id":240},"_2-fan-out",[242],{"type":46,"value":243},"2 — Fan Out",{"type":40,"tag":49,"props":245,"children":246},{},[247],{"type":46,"value":248},"Launch 2–5 parallel subagents using the area prompts below. Each subagent works in isolation — do not share one area's findings with another before synthesis.",{"type":40,"tag":49,"props":250,"children":251},{},[252],{"type":46,"value":253},"Each gets a self-contained prompt with its area, the plan location, and the return format. Subagents read the full plan from session memory themselves. Subagents may surface findings their area doesn't explicitly list — don't constrain them to only the listed focus items.",{"type":40,"tag":203,"props":255,"children":257},{"id":256},"_3-synthesize",[258],{"type":46,"value":259},"3 — Synthesize",{"type":40,"tag":49,"props":261,"children":262},{},[263],{"type":46,"value":264},"When all subagents return:",{"type":40,"tag":266,"props":267,"children":268},"ol",{},[269,274,279,284],{"type":40,"tag":214,"props":270,"children":271},{},[272],{"type":46,"value":273},"Deduplicate findings that overlap across areas (e.g., a feasibility gap that also shows up as a sequencing problem).",{"type":40,"tag":214,"props":275,"children":276},{},[277],{"type":46,"value":278},"Order by severity: missing requirements > incorrect assumptions > sequencing errors > scope issues > weak verification > minor risks.",{"type":40,"tag":214,"props":280,"children":281},{},[282],{"type":46,"value":283},"Apply the signal filter — drop anything that wouldn't actually cause problems during implementation.",{"type":40,"tag":214,"props":285,"children":286},{},[287],{"type":46,"value":288},"If no blocking issues survive, say so and note any areas where the plan could be strengthened.",{"type":40,"tag":203,"props":290,"children":292},{"id":291},"_4-save-findings",[293],{"type":46,"value":294},"4 — Save Findings",{"type":40,"tag":49,"props":296,"children":297},{},[298,300,306],{"type":46,"value":299},"Always save the synthesized findings to session memory at ",{"type":40,"tag":220,"props":301,"children":303},{"className":302},[],[304],{"type":46,"value":305},"\u002Fmemories\u002Fsession\u002Fplan-review.md",{"type":46,"value":307},". This makes them available for follow-up turns, plan revision, and cross-referencing during implementation.",{"type":40,"tag":203,"props":309,"children":311},{"id":310},"_5-revise-or-report",[312],{"type":46,"value":313},"5 — Revise or Report",{"type":40,"tag":210,"props":315,"children":316},{},[317,327],{"type":40,"tag":214,"props":318,"children":319},{},[320,325],{"type":40,"tag":106,"props":321,"children":322},{},[323],{"type":46,"value":324},"Review-only",{"type":46,"value":326},": if the user said \"only review\", \"just review\", or \"read-only\", stop after reporting.",{"type":40,"tag":214,"props":328,"children":329},{},[330,335,337],{"type":40,"tag":106,"props":331,"children":332},{},[333],{"type":46,"value":334},"Default (review-and-revise)",{"type":46,"value":336},":\n",{"type":40,"tag":266,"props":338,"children":339},{},[340,345,357,362],{"type":40,"tag":214,"props":341,"children":342},{},[343],{"type":46,"value":344},"For each actionable finding, propose a specific revision to the plan — what to add, remove, reorder, or clarify.",{"type":40,"tag":214,"props":346,"children":347},{},[348,350,355],{"type":46,"value":349},"Apply revisions to the plan in session memory (",{"type":40,"tag":220,"props":351,"children":353},{"className":352},[],[354],{"type":46,"value":225},{"type":46,"value":356},"), preserving the plan's existing structure.",{"type":40,"tag":214,"props":358,"children":359},{},[360],{"type":46,"value":361},"After revising, re-read the updated plan to confirm the revisions are coherent.",{"type":40,"tag":214,"props":363,"children":364},{},[365],{"type":46,"value":366},"Report what was revised and any remaining items that need the user's input or a decision.",{"type":40,"tag":60,"props":368,"children":370},{"id":369},"signal-filter",[371],{"type":46,"value":372},"Signal Filter",{"type":40,"tag":49,"props":374,"children":375},{},[376,378,384],{"type":46,"value":377},"Before reporting a finding, ask: ",{"type":40,"tag":379,"props":380,"children":381},"em",{},[382],{"type":46,"value":383},"Does this change what a developer would actually do — or how likely the plan is to succeed?",{"type":46,"value":385}," Ground every finding in something observable: a file that doesn't exist, an API that behaves differently, a requirement the steps don't cover, a sequence that creates rework.",{"type":40,"tag":49,"props":387,"children":388},{},[389],{"type":46,"value":390},"If a concern is speculative, cosmetic, or unrelated to the plan's goal, leave it out.",{"type":40,"tag":60,"props":392,"children":394},{"id":393},"area-prompt",[395],{"type":46,"value":396},"Area Prompt",{"type":40,"tag":49,"props":398,"children":399},{},[400,402,408,410,416],{"type":46,"value":401},"Each subagent gets this prompt with ",{"type":40,"tag":220,"props":403,"children":405},{"className":404},[],[406],{"type":46,"value":407},"{AREA}",{"type":46,"value":409}," and ",{"type":40,"tag":220,"props":411,"children":413},{"className":412},[],[414],{"type":46,"value":415},"{FOCUS}",{"type":46,"value":417}," filled in from the Review Areas table.",{"type":40,"tag":419,"props":420,"children":425},"pre",{"className":421,"code":423,"language":46,"meta":424},[422],"language-text","You are a focused plan-review subagent. Your area is: {AREA}\n\n## Where to find the plan\nThe plan is in session memory at `\u002Fmemories\u002Fsession\u002Fplan.md`. Read it with your memory tools first. Then explore the codebase to validate the plan's assumptions — check that referenced files, functions, and patterns actually exist.\n\nFocus on: {FOCUS}\n\nUse your tools to read the full plan, inspect the codebase, verify assumptions, and run existing tests or check lint\u002Fcompile errors for evidence. Use web search to validate uncertain API or version claims.\n\nRules:\n- Stay read-only. Do not edit files.\n- Only flag issues that would change what a developer actually does or how likely the plan is to succeed.\n- Do not report issues outside your area, but do surface unexpected findings within it.\n- Do not rewrite the plan — describe the problem and why it matters.\n- Keep your response short. No preamble, no formatting commentary.\n\nReturn format:\n\n**Area**: {AREA}\n\n**Findings** (0–5 items, severity order):\n- One-sentence description. Why it matters. Evidence from the codebase if applicable.\n\nIf the plan is sound for your area: \"No issues found in {AREA}.\"\n","",[426],{"type":40,"tag":220,"props":427,"children":428},{"__ignoreMap":424},[429],{"type":46,"value":423},{"items":431,"total":521},[432,449,462,476,487,498,507],{"slug":433,"name":433,"fn":434,"description":435,"org":436,"tags":437,"stars":23,"repoUrl":24,"updatedAt":448},"council-plan","perform multi-model council planning","Multi-model council planning for implementation and architecture decisions. Use when the user asks to 'plan with council', 'multi-model plan', 'get different perspectives on approach', 'council plan', or wants multiple models to independently propose plans for the same task. Also use when the user asks to 'debate approaches', 'compare strategies', or 'cross-plan'.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[438,441,442,445],{"name":439,"slug":440,"type":15},"Architecture","architecture",{"name":21,"slug":22,"type":15},{"name":443,"slug":444,"type":15},"Multi-Agent","multi-agent",{"name":446,"slug":447,"type":15},"System Design","system-design","2026-05-13T06:14:08.529779",{"slug":450,"name":450,"fn":451,"description":452,"org":453,"tags":454,"stars":23,"repoUrl":24,"updatedAt":461},"council-review","perform multi-model council code reviews","Multi-model council review for diffs, pull requests, and risky changes. It is CRITICAL to use this skill after ANY non-trivial development phase — changes are usually not 100% correct. Development CANNOT be called done until the code has been reviewed. Use whenever the user asks for a review, PR feedback, a bug hunt in recent edits, or wants multiple models to inspect the same change independently. Also use when the user asks to 'discuss findings', 'cross-review', or 'debate' review results between models.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[455,456,457,458],{"name":13,"slug":14,"type":15},{"name":21,"slug":22,"type":15},{"name":443,"slug":444,"type":15},{"name":459,"slug":460,"type":15},"Pull Requests","pull-requests","2026-05-13T06:14:07.202801",{"slug":463,"name":463,"fn":464,"description":465,"org":466,"tags":467,"stars":23,"repoUrl":24,"updatedAt":475},"follow-goal","manage agent goals and stopping conditions","Give the agent a durable objective with a verifiable stopping condition, then keep iterating across turns until that condition is met. Use when the user says 'set a goal', 'follow a goal', '\u002Fgoal …', 'keep working until …', or asks for a long-running task with a clear end state (migrations, large refactors, retry-until-green loops, experiments).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[468,471,472],{"name":469,"slug":470,"type":15},"Agents","agents",{"name":9,"slug":8,"type":15},{"name":473,"slug":474,"type":15},"Productivity","productivity","2026-07-07T06:54:04.263607",{"slug":477,"name":477,"fn":478,"description":479,"org":480,"tags":481,"stars":23,"repoUrl":24,"updatedAt":486},"inbox-add-reaction","add reactions to GitHub issues and PRs","Add a reaction to a GitHub issue or pull request",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[482,485],{"name":483,"slug":484,"type":15},"GitHub","github",{"name":459,"slug":460,"type":15},"2026-07-07T06:53:33.958298",{"slug":488,"name":488,"fn":489,"description":490,"org":491,"tags":492,"stars":23,"repoUrl":24,"updatedAt":497},"inbox-install-gh-cli","install GitHub CLI","Install the GitHub CLI (gh) if not already installed",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[493,496],{"name":494,"slug":495,"type":15},"CLI","cli",{"name":483,"slug":484,"type":15},"2026-05-13T06:14:05.911879",{"slug":499,"name":499,"fn":500,"description":501,"org":502,"tags":503,"stars":23,"repoUrl":24,"updatedAt":506},"inbox-mark-all-read","mark GitHub notifications as read","Mark all GitHub notifications as read",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[504,505],{"name":483,"slug":484,"type":15},{"name":473,"slug":474,"type":15},"2026-05-13T06:14:02.019522",{"slug":508,"name":508,"fn":509,"description":510,"org":511,"tags":512,"stars":23,"repoUrl":24,"updatedAt":520},"inbox-memory","manage agent memory and rules","Read and write agent storage — memory and rules with environment-aware fallback",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[513,514,517],{"name":469,"slug":470,"type":15},{"name":515,"slug":516,"type":15},"Configuration","configuration",{"name":518,"slug":519,"type":15},"Memory","memory","2026-05-13T06:14:00.740431",14,{"items":523,"total":712},[524,544,563,584,599,616,627,640,655,668,687,700],{"slug":525,"name":525,"fn":526,"description":527,"org":528,"tags":529,"stars":541,"repoUrl":542,"updatedAt":543},"rushstack-best-practices","manage Rush monorepos with best practices","Provides best practices and guidance for working with Rush monorepos. Use when the user is working in a Rush-based repository, asks about Rush commands (install, update, build, rebuild), needs help with project selection, dependency management, build caching, subspace configuration, or troubleshooting Rush-specific issues.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[530,531,534,535,538],{"name":21,"slug":22,"type":15},{"name":532,"slug":533,"type":15},"Local Development","local-development",{"name":9,"slug":8,"type":15},{"name":536,"slug":537,"type":15},"Project Management","project-management",{"name":539,"slug":540,"type":15},"Rush","rush",6484,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Frushstack","2026-04-06T18:34:44.965032",{"slug":545,"name":545,"fn":546,"description":547,"org":548,"tags":549,"stars":560,"repoUrl":561,"updatedAt":562},"azure-ai-agents-persistent-dotnet","build AI agents with Azure .NET SDK","Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Use for agent CRUD, conversation threads, streaming responses, function calling, file search, and code interpreter. Triggers: \"PersistentAgentsClient\", \"persistent agents\", \"agent threads\", \"agent runs\", \"streaming agents\", \"function calling agents .NET\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[550,553,554,557],{"name":551,"slug":552,"type":15},".NET","net",{"name":469,"slug":470,"type":15},{"name":555,"slug":556,"type":15},"Azure","azure",{"name":558,"slug":559,"type":15},"LLM","llm",2804,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills","2026-07-03T16:32:10.297433",{"slug":564,"name":564,"fn":565,"description":566,"org":567,"tags":568,"stars":560,"repoUrl":561,"updatedAt":583},"azure-ai-anomalydetector-java","build anomaly detection applications with Java","Build anomaly detection applications with Azure AI Anomaly Detector SDK for Java. Use when implementing univariate\u002Fmultivariate anomaly detection, time-series analysis, or AI-powered monitoring.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[569,572,573,576,579,580],{"name":570,"slug":571,"type":15},"Analytics","analytics",{"name":555,"slug":556,"type":15},{"name":574,"slug":575,"type":15},"Data Analysis","data-analysis",{"name":577,"slug":578,"type":15},"Java","java",{"name":9,"slug":8,"type":15},{"name":581,"slug":582,"type":15},"Monitoring","monitoring","2026-05-13T06:14:16.261754",{"slug":585,"name":585,"fn":586,"description":587,"org":588,"tags":589,"stars":560,"repoUrl":561,"updatedAt":598},"azure-ai-contentsafety-java","build content moderation applications with Azure AI","Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text\u002Fimage analysis, blocklist management, or harm detection for hate, violence, sexual content, and self-harm.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[590,593,594,595],{"name":591,"slug":592,"type":15},"AI Infrastructure","ai-infrastructure",{"name":555,"slug":556,"type":15},{"name":577,"slug":578,"type":15},{"name":596,"slug":597,"type":15},"Security","security","2026-07-07T06:53:31.293235",{"slug":600,"name":600,"fn":601,"description":602,"org":603,"tags":604,"stars":560,"repoUrl":561,"updatedAt":615},"azure-ai-contentsafety-py","detect harmful content with Azure AI Content Safety","Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification.\nTriggers: \"azure-ai-contentsafety\", \"ContentSafetyClient\", \"content moderation\", \"harmful content\", \"text analysis\", \"image analysis\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[605,606,609,610,611,614],{"name":555,"slug":556,"type":15},{"name":607,"slug":608,"type":15},"Compliance","compliance",{"name":558,"slug":559,"type":15},{"name":9,"slug":8,"type":15},{"name":612,"slug":613,"type":15},"Python","python",{"name":596,"slug":597,"type":15},"2026-07-18T05:14:23.017504",{"slug":617,"name":617,"fn":618,"description":619,"org":620,"tags":621,"stars":560,"repoUrl":561,"updatedAt":626},"azure-ai-language-conversations-py","implement conversational language understanding with Python","Implement Conversational Language Understanding (CLU) using the azure-ai-language-conversations Python SDK. Use when working with ConversationAnalysisClient to analyze conversation intent and entities, building NLP features, or integrating language understanding into applications.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[622,623,624,625],{"name":570,"slug":571,"type":15},{"name":555,"slug":556,"type":15},{"name":558,"slug":559,"type":15},{"name":612,"slug":613,"type":15},"2026-07-31T05:54:29.068751",{"slug":628,"name":628,"fn":629,"description":630,"org":631,"tags":632,"stars":560,"repoUrl":561,"updatedAt":639},"azure-ai-translation-text-py","translate text using Azure AI services","Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications.\nTriggers: \"text translation\", \"translator\", \"translate text\", \"transliterate\", \"TextTranslationClient\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[633,636,637,638],{"name":634,"slug":635,"type":15},"API Development","api-development",{"name":555,"slug":556,"type":15},{"name":9,"slug":8,"type":15},{"name":612,"slug":613,"type":15},"2026-07-18T05:14:16.988376",{"slug":641,"name":641,"fn":642,"description":643,"org":644,"tags":645,"stars":560,"repoUrl":561,"updatedAt":654},"azure-ai-vision-imageanalysis-py","analyze images with Azure AI Vision","Azure AI Vision Image Analysis SDK for captions, tags, objects, OCR, people detection, and smart cropping. Use for computer vision and image understanding tasks.\nTriggers: \"image analysis\", \"computer vision\", \"OCR\", \"object detection\", \"ImageAnalysisClient\", \"image caption\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[646,647,650,653],{"name":555,"slug":556,"type":15},{"name":648,"slug":649,"type":15},"Computer Vision","computer-vision",{"name":651,"slug":652,"type":15},"Images","images",{"name":612,"slug":613,"type":15},"2026-07-18T05:14:18.007737",{"slug":656,"name":656,"fn":657,"description":658,"org":659,"tags":660,"stars":560,"repoUrl":561,"updatedAt":667},"azure-appconfiguration-java","manage configuration with Azure App Configuration","Azure App Configuration SDK for Java. Centralized application configuration management with key-value settings, feature flags, and snapshots.\nTriggers: \"ConfigurationClient java\", \"app configuration java\", \"feature flag java\", \"configuration setting java\", \"azure config java\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[661,662,663,666],{"name":555,"slug":556,"type":15},{"name":515,"slug":516,"type":15},{"name":664,"slug":665,"type":15},"Feature Flags","feature-flags",{"name":577,"slug":578,"type":15},"2026-07-03T16:32:01.278468",{"slug":669,"name":669,"fn":670,"description":671,"org":672,"tags":673,"stars":560,"repoUrl":561,"updatedAt":686},"azure-cosmos-rust","build applications with Azure Cosmos DB","Azure Cosmos DB library for Rust (NoSQL API). Document CRUD, containers, and globally distributed data.\nTriggers: \"cosmos db rust\", \"CosmosClient rust\", \"document crud rust\", \"NoSQL rust\", \"partition key rust\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[674,677,680,683],{"name":675,"slug":676,"type":15},"Cosmos DB","cosmos-db",{"name":678,"slug":679,"type":15},"Database","database",{"name":681,"slug":682,"type":15},"NoSQL","nosql",{"name":684,"slug":685,"type":15},"Rust","rust","2026-07-31T05:54:27.021432",{"slug":688,"name":688,"fn":670,"description":689,"org":690,"tags":691,"stars":560,"repoUrl":561,"updatedAt":699},"azure-cosmos-ts","Azure Cosmos DB JavaScript\u002FTypeScript SDK (@azure\u002Fcosmos) for data plane operations. Use for CRUD operations on documents, queries, bulk operations, and container management. Triggers: \"Cosmos DB\", \"@azure\u002Fcosmos\", \"CosmosClient\", \"document CRUD\", \"NoSQL queries\", \"bulk operations\", \"partition key\", \"container.items\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[692,693,694,695,696],{"name":675,"slug":676,"type":15},{"name":678,"slug":679,"type":15},{"name":9,"slug":8,"type":15},{"name":681,"slug":682,"type":15},{"name":697,"slug":698,"type":15},"TypeScript","typescript","2026-07-03T16:31:19.368382",{"slug":701,"name":701,"fn":702,"description":703,"org":704,"tags":705,"stars":560,"repoUrl":561,"updatedAt":711},"azure-data-tables-java","build table storage applications with Java","Build table storage applications with Azure Tables SDK for Java. Use when working with Azure Table Storage or Cosmos DB Table API for NoSQL key-value data, schemaless storage, or structured data at scale.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[706,707,708,709,710],{"name":555,"slug":556,"type":15},{"name":675,"slug":676,"type":15},{"name":678,"slug":679,"type":15},{"name":577,"slug":578,"type":15},{"name":681,"slug":682,"type":15},"2026-05-13T06:14:17.582229",267]