- Mcs FixUse this skill to fix an agent after eval failures. Classifies root causes (instruction gaps, boundary violations, routing failures, knowledge gaps, scoring issues, decision mismatches), applies targeted fixes via PE and TE, then re-evaluates. Use after /mcs-eval shows failures, not during initial build (which has its own fix loop).microsoft/MCS-Agent-Builder10
- Mcs InitUse this skill to start a new MCS agent project. Creates the folder structure in Build-Guides/, copies template files, and detects the intake path (SDR documents, wizard, or manual). Use when the user says 'new project', 'start a build', or provides intake documents.microsoft/MCS-Agent-Builder10
- Mcs IterateUse this skill to autonomously build, evaluate, and fix an MCS agent until it reaches SHIP verdict. Composite of /mcs-build → /mcs-eval → /mcs-fix → re-eval, max 3 fix cycles per agent. Reuses the iterate-orchestrator audit + verdict primitives. Use after /mcs-research when agentspec.json is ready and the user wants the agent shipped without manual phase transitions. Use when the user says 'ship it', 'iterate to SHIP', 'build and evaluate this agent', or to resume a partially-built agent. Notifymicrosoft/MCS-Agent-Builder10
- Mcs Pipeline TestUse this skill to run the MCS build pipeline verify-fix harness against the canonical kitchen-sink agent. The harness reads back every component from MCS via API, classifies any drift against a fixed taxonomy, and auto-applies fixes for confirmed classifications. Use when validating the build pipeline end-to-end, after touching tools/mcs-lsp.js, tools/island-client.js, tools/add-tool.js, or app/lib/build-runner.js, or when component pushes are silent-failing in real builds.microsoft/MCS-Agent-Builder10
- Mcs ReportUse this skill to generate an export from agentspec.json without running a build. Produces a single self-contained HTML file with three tabs: Brief (design state), Evaluations (test sets and results), and How-To Guide (step-by-step MCS build instructions). Use when the user wants a summary, status update, or shareable document.microsoft/MCS-Agent-Builder10
- Mcs ResearchUse this skill to research and design an agent before building it. Reads project documents, identifies agents, researches MCS components, scores architecture, writes instructions, and generates eval sets. Use after /mcs-init, when documents change, when the user wants to analyze requirements, or when agentspec.json needs enrichment.microsoft/MCS-Agent-Builder10
- Mcs SyncUse this skill to detect changes across all external dependencies (knowledge cache, upstream repos, Elevate, eval-guide plugin, MCP servers, om-cli binary, MS Learn docs, Claude Code plugins) and produce a triage board so a human can decide TAKE or REJECT per change. Never auto-applies. Use when the user asks to 'refresh everything', 'check what's new upstream', 'run dependency sync', 'sync', or when you want to see what has drifted since the last manual review.microsoft/MCS-Agent-Builder10
- Playwright CliAutomate browser interactions, test web pages and work with Playwright tests.microsoft/MCS-Agent-Builder10
- Share ScreenshotUse this only when a user explicitly asks to upload or share a screenshot image file to the Lab 502 Community Hub. Resolve the image path before uploading.microsoft/Build26-LAB502-make-github-copilot-work-your-way-custom-tools-context-and-workflows10
- UI DesignerReact + TypeScript + Tailwind CSS chat interface specialist for this project's streaming chat UImicrosoft/Build26-BRK242-turn-your-agents-into-action-connect-tools-apis-and-documents10
- Work Order ManagementHandle work order operations — viewing, listing, creating, and updating work orders. Use when the technician asks about work orders, assignments, scheduling, job status, or needs to create or update a WO.microsoft/Build26-BRK242-turn-your-agents-into-action-connect-tools-apis-and-documents10
- Work Order PreparationPrepare for a work order by fetching the WO details and checking stock availability for all required parts. Use when the technician wants to get ready for a job, check if parts are available for a WO, or asks "what do I need for WO-XXX".microsoft/Build26-BRK242-turn-your-agents-into-action-connect-tools-apis-and-documents10
- Implement Agent IdGuide for Microsoft Entra Agent ID and Agent User integration. Covers certificate authentication, stable Graph creation endpoints, sponsors, BlueprintPrincipal creation, permissions, consent, and the three-hop user_fic token flow.microsoft/entrabot9
- Refresh PersonaRe-read current session digest + carry-forward + MEMORY.md index and pin into the turn. Use when the user calls out persona drift ("you're taking things too literally," "this doesn't sound like you," "you just forgot X") or after a compaction event. Also use when explicitly asked to "refresh persona" or "reload memory."microsoft/entrabot9
- Agora WorkbenchDrive Agora Workbench MCP servers — any server that exposes an execute_*_code tool — by writing Python that runs inside the server's persistent kernel, where its tools and libraries already live. Activate whenever an execute_*_code tool is connected and the user asks for work that could run there, BEFORE reaching for local shell, standalone scripts, or package installs. The server already has the environment; call its tool instead of rebuilding the capability locally.microsoft/agora-workbench8
- Ai Slop DetectorUser-invocable audit skill for detecting and surfacing AI-slop in documents and code: content that sounds AI-generated, is useless, generic, overconfident, fake, verbose, mechanically structured, or exists because of common LLM failure modes. Use only when the user explicitly asks to run the ai-slop-detector skill, asks for an AI-slop audit, or asks to list AI-generated slop in documents/code. Do not auto-trigger for normal writing edits, humanizing text, code review, linting, or implementation microsoft/frontier-agentic-devops-rvas8
- Amplifier AgentIntegrate Amplifier Agent into applications using its Python or TypeScript library or OpenAI-compatible HTTP face. Use for installation, sessions, streaming, tools, MCP, skills, approvals, configuration, and integration troubleshooting.microsoft/amplifier-agent8
- Amplifier Agent BugfixTriage and fix an amplifier-agent bug, from report to verified fix. Covers intake, ruling out non-code causes, root-cause pinning, checking the behavior against the contracts, the coverage-gap gate, red/green regression with evaluations and tests, scoped verification, and quality regressions where contracts hold but output got worse. Stops before commit and release.microsoft/amplifier-agent8
- Amplifier Agent New FeatureDevelop a new amplifier-agent feature from idea to verified behavior. Covers orientation against the contracts, planning, updating every public description, red/green development driven by an evaluation task and supporting tests, the widening verification ladder, and a hands-on human check. Stops before commit and release.microsoft/amplifier-agent8
- ArtifactsFetch data assets into the kernel, transfer Python objects between servers, and publish output files to the user. Activate when working with data files, cross-server data movement, or when the user asks for downloads or exports.microsoft/agora-workbench8
- Async ExecutionRun long-running or parallel code asynchronously. Activate when code will take more than 30 seconds, when processing many independent inputs, or when the user asks to run something in the background.microsoft/agora-workbench8
- Chemistry RdkitMolecular analysis and cheminformatics using RDKit — SMILES handling, descriptor calculation, fingerprints, substructure search, similarity, clustering, and drug-likeness screening via domain tools and the execute_chemistry_code tool.microsoft/agora-workbench8
- Content ReviewReview hackathon content (challenges, module docs, resources) for correctness, pacing, hallucinations, and staleness, and cross-check claims against official documentation on the web. Use when asked to "review content", "check for errors", "verify the docs", "find hallucinations", "is this still accurate", "check against the official docs", "fact-check the challenges", "audit content quality", or before publishing/PR-ing content changes. Spots and fixes wrong commands, fabricated UI labels and Amicrosoft/frontier-agentic-devops-rvas8
- Earthscience StacHow to find and load data from Microsoft Planetary Computer (STAC) inside execute_earthscience_code.microsoft/agora-workbench8
- Echo ArgsWrites the exact text it received as arguments, verbatim, to a file. Used to verify skill argument passthrough.microsoft/amplifier-agent8
- Energysystems PypsaPower system modeling and analysis with PyPSA inside execute_energysystems_code — network setup, components, power flow, optimal dispatch, capacity expansion, cost and topology analysis. Covers PyPSA conventions and the gotchas that cause silently wrong results.microsoft/agora-workbench8
- Frontend DesignGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.microsoft/frontier-agentic-devops-rvas8
- GrillingInterview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.microsoft/frontier-agentic-devops-rvas8
- Humanize WritingUse when the user wants text to sound more human, says writing sounds "too AI" or "too ChatGPT," asks to humanize or rewrite a draft to feel natural, or shares content wanting it to feel authentic and less robotic. Also applies to LinkedIn posts, blog drafts, or emails where the user wants a more genuine voice.microsoft/frontier-agentic-devops-rvas8
- Rvap BrandApplies the RVAP (Real Value Acceleration Program) brand identity — colors, fonts, logo, and layout patterns — consistently to any GitHub Pages website. Use this skill whenever someone asks to brand, rebrand, apply RVAP/RVAS visual identity, make a site look RVAP, match the brand kit, or transform a GitHub Pages site's look and feel to match RVAP. Also trigger when the user shares an HTML/CSS/MkDocs site and says it should look consistent with other RVAP/RVAS materials, even if they don't explicmicrosoft/frontier-agentic-devops-rvas8
- Skill CreatorCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.microsoft/frontier-agentic-devops-rvas8
- Skill With HooksExample skill demonstrating embedded hooks for validation and loggingmicrosoft/amplifier-module-tool-skills8
- Status ReportWrite a short three-line project status report in Markdown. Use when asked for a status report.microsoft/amplifier-agent8
- Tool ProbeWrites a fixed sentinel to a file to prove the agent invoked this skill through its skills tool in response to a natural-language request. Invoke this skill when asked to run or invoke tool-probe.microsoft/amplifier-agent8
- UnslopCut AI tells from any writing. Must always apply.microsoft/frontier-agentic-devops-rvas8
- Workflow PlanningPlan and navigate multi-step domain workflows using the state graph. Activate when a task involves ordered tool dependencies, multiple state transitions, or when unsure which tool to call next in a domain sequence.microsoft/agora-workbench8
- Cosmosdb MongodbBest practices for Azure Cosmos DB for MongoDB (RU-based). Use this skill when: (1) creating or modifying database indexes, (2) writing database migrations, (3) designing queries against CosmosDB, (4) troubleshooting query performance or index errors.microsoft/scope7
- Digital Twin UniverseLaunch and manage isolated, realistic environments (Digital Twin Universe) to test code beyond "tests pass on my machine" and simulate end-user experiences. Debug networking/provisioning as needed. Triggers on digital twin, DTU, isolated environment, simulation environment, amplifier-digital-twin, incus container, profile launch, test in realistic environment, deploy simulation. ALWAYS use this skill whenever a "Digital Twin" is mentioned!microsoft/amplifier-bundle-digital-twin-universe7
- DocumentationBest practices for writing and maintaining documentation in this repository. Use this skill when writing or updating files in docs/, adding Mermaid diagrams, or creating README and onboarding documentation.microsoft/scope7
- Portability ReviewCross-provider portability and documentation-alignment review skill for multiclouddb-sdk-for-java. Houses the canonical checklist (provider symmetry, conformance coverage, capability declarations, error normalization, cost-efficiency parity, doc/changelog/spec alignment), the safe-publication state machine, cross-provider parity matrix template, and PowerShell diff loader. Invoked by the `portability-review` agent (and its subagents) when reviewing a diff, a branch, or a PR.microsoft/multiclouddb-sdk-for-java7
- ReleaseManages releases for multiclouddb-sdk-for-java modules. Validates release readiness, updates POM versions and changelogs, prepares a release branch for a PR against upstream/main, and after merge creates and pushes per-module version tags that trigger the automated release pipeline.microsoft/multiclouddb-sdk-for-java7
- ResilienceApply resilience patterns (retry, backoff, circuit breaking) when writing or reviewing code that makes outbound HTTP/REST calls, database operations, or any I/O that can experience transient failures. Use this skill when: (1) writing new code that calls external services or APIs, (2) reviewing code that uses fetch, HTTP clients, or service-to-service calls, (3) adding queue consumers or workers that interact with remote systems, (4) debugging intermittent failures in production.microsoft/scope7
- Rust Best PracticesGuide for writing idiomatic Rust code based on Apollo GraphQL's best practices handbook. Use this skill when: (1) writing new Rust code or functions, (2) reviewing or refactoring existing Rust code, (3) deciding between borrowing vs cloning or ownership patterns, (4) implementing error handling with Result types, (5) optimizing Rust code for performance, (6) writing tests or documentation for Rust projects.microsoft/scope7
- Scope ApiQuery and control the Scope platform API for analyzing benchmark data, managing runs/requests, skills, agents, reports, and insights. Use when the user asks about SCOPE data, wants to trigger runs, check status, generate reports, or interact with the SCOPE platform programmatically.microsoft/scope7
- Scope CliInteract with the Scope benchmarking platform using the Scope CLI — submit runs, list results, manage criteria, generate reports, and administer agents, skills, and MCP servers.microsoft/scope7
- StorybookMaintain the Storybook component catalog for the portal app. Use this skill when: (1) adding new stories for components, (2) updating existing stories after component changes, (3) running a full Storybook refresh/sync with AI assistance.microsoft/scope7
- TypescriptTypeScript best practices for this monorepo. Use this skill when: (1) writing new TypeScript code, (2) reviewing TypeScript code, (3) working with API responses, fetch calls, or JSON parsing, (4) adding or modifying types and interfaces.microsoft/scope7
- Frontend DesignCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.microsoft/frontier-sre-agent-rvas6
- Rvap BrandApplies the RVAP (Real Value Acceleration Program) brand identity — colors, fonts, logo, and layout patterns — consistently to any GitHub Pages website. Use this skill whenever someone asks to brand, rebrand, apply RVAP/RVAS visual identity, make a site look RVAP, match the brand kit, or transform a GitHub Pages site's look and feel to match RVAP. Also trigger when the user shares an HTML/CSS/MkDocs site and says it should look consistent with other RVAP/RVAS materials, even if they don't explicmicrosoft/frontier-sre-agent-rvas6
- Rvas ContentCreates, formats, and validates rvas challenge content for RVAS events in the Microsoft Frontier RVAS format. Use this skill whenever someone asks to write, review, or validate a Student challenge file, Coach solution guide, or rvas README. Also trigger when the user asks to add a new challenge, fix challenge formatting, check whether a challenge follows the RVAS conventions, or create a full rvas from scratch.microsoft/frontier-sre-agent-rvas6
- Skill CreatorCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.microsoft/frontier-sre-agent-rvas6
- Sql Server DbaDiagnose SQL Server and Azure SQL with safe native evidencemicrosoft/frontier-sre-agent-rvas6
- Agentic WorkflowsRoute gh-aw workflow design/create/debug/upgrade requests to the right prompts.microsoft/frontier-agentic-cobuild-rvas5
- Ai Slop DetectorUser-invocable audit skill for detecting and surfacing AI-slop in documents and code: content that sounds AI-generated, is useless, generic, overconfident, fake, verbose, mechanically structured, or exists because of common LLM failure modes. Use only when the user explicitly asks to run the ai-slop-detector skill, asks for an AI-slop audit, or asks to list AI-generated slop in documents/code. Do not auto-trigger for normal writing edits, humanizing text, code review, linting, or implementation microsoft/frontier-agentic-cobuild-rvas5
- Azure AiUse for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.microsoft/frontier-agentic-cobuild-rvas5
- Azure AigatewayConfigure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailbreak detection, add Azure OpenAI backend, add AI Foundry model, test AI gateway, LLM policies, configure AI backend, token metrics, AI cost control, convert API to MCP, import OpenAPI to gateway.microsoft/frontier-agentic-cobuild-rvas5
- BroRe-explain the previous assistant message in a much simpler way — for when the reply made you go 'bro what'. Use /bro to get a plain-language version of the last answer.microsoft/agentic-loops5
- CapacityDiscovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability. DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quomicrosoft/frontier-agentic-cobuild-rvas5
- Content Accuracy AuditAudit scenario lessons, READMEs, accelerator code, solution guides, docs, skills, infrastructure, and scripts for correctness, currency, hallucinations, broken cross-references, and pacing. Cross-check Azure / Microsoft Foundry SDK signatures, CLI commands, environment variables, and API surfaces against official Microsoft Learn docs via the microsoft-docs MCP and the live web. USE WHEN: review content for errors, fact-check docs, check currency, verify API signatures, validate scenario instructmicrosoft/frontier-agentic-cobuild-rvas5
- Context Intelligence Derived MetricsUse when a graph query returns structurally-identical rows hiding different intent — many delegations all "none/conversation", look-alike sessions, identical tool calls. Derives an INTERPRETIVE metric by joining a second graph layer onto the blanket shape (flagship: transport × sub-session skill payload = "flavour"). Complements graph-query (READ the graph) by making blanket reads MEAN something.microsoft/amplifier-bundle-context-intelligence5