- Code ReviewReview changed code for reuse, quality, and efficiency, then fix any issues found.microsoft/amplifier-bundle-skills12
- CouncilConvene the persona panel — six orthogonal review lenses — on a target. Cold independent fan-out, debate-to-consensus, synthesized verdict with recorded dissent and a roster manifest.microsoft/amplifier-bundle-skills12
- Council HereConvene the persona panel on the CURRENT conversation — the plan, design, or decision built in this session. The INLINE counterpart to /council (which forks isolated and cannot see the chat). Use when you want the council to critique what we're working on right now.microsoft/amplifier-bundle-skills12
- CouncilifyBuild a NEW complete "council" for a domain — a panel of orthogonal review lenses that fan out cold, debate to consensus, and return a synthesized verdict with recorded dissent, exactly like /council and /design-council. Identifies the distinct lenses a domain needs (one load-bearing question each, mined from real archetypes — not invented), reuses existing lenses, and builds only the genuinely-missing ones (persona SKILLs via personafy, or agents when the role is an active builder). Use when crmicrosoft/amplifier-bundle-skills12
- Cranky Old SamSimplicity-obsessed reviewer that interrogates complexity and insists on the minimal viable design. Voice of a senior engineer who treats every unnecessary layer as a personal affront. Use at any checkpoint — brainstorm, design, plan, implement, debug, review — when anything looks more complex than the problem needs: a speculative idea, an abstraction, a layer, an over-built fix. The worry: "do we actually need this, or can it be deleted?"microsoft/amplifier-bundle-skills12
- Create Demo VideoProduce a narrated demo video that shows something the user made or built, cut from recordings they supply or recordings made to their direction. Use when showing a product, feature, tool, or project in action, including explainers built around a live demo. Not for slide-style explainers; for a single trim or audio cleanup, use the relevant tool directly.microsoft/amplifier-bundle-skills12
- Crusty Old EngineerCurmudgeonly engineering advisor: grounded skepticism and evidence-linked judgment on architecture, legacy refactors, and tooling choices. Voice of a senior systems engineer who has reviewed too many designs to be impressed but still cares about correctness. Use at any checkpoint — brainstorm, design, plan, implement, debug, review — when weighing consequences, hidden costs, or failure modes of a choice, or for broad "how should I start?" questions: "what will this cost us later?"microsoft/amplifier-bundle-skills12
- Engineering PatternsUse for tool/service work: CLI packaging, installers, config/state, HTTP, auth/TLS, file IPC, plugins, instance storage, containers, React MFE, Graph, self-update, tool leverage.microsoft/amplifier-bundle-skills12
- Image VisionAnalyze images using LLM vision APIs (Anthropic Claude, OpenAI GPT-4, Google Gemini, Azure OpenAI). Use when a task requires understanding image content, describing visual elements, answering questions about images, comparing images, or extracting text from images (OCR). Provides ready-to-use scripts.microsoft/amplifier-bundle-skills12
- Intent KeeperGoal-clarity reviewer that refuses to judge a solution until the intent behind it is pinned. A patient interrogator of "why are we doing this?", hunting goal drift — the deliverable quietly replacing the goal. Use at any checkpoint — brainstorm, design, plan, implement, debug, review — when the build has wandered from the brief or nobody can say in one sentence what success looks like: "is this still the real goal?"microsoft/amplifier-bundle-skills12
- Mass ChangeResearch and plan a large-scale change, then execute it in parallel across isolated agents that each open a PR.microsoft/amplifier-bundle-skills12
- MonitorRun a bounded, self-checking polling loop (sleep -> check -> decide, repeat) WITHOUT ENDING THE TURN. The turn ends only when the watched thing is done, has failed, or genuinely needs the user's attention — which is what makes Amplifier's end-of-turn notification fire correctly and honestly. Primarily invoked explicitly via `/monitor <thing to watch>`, e.g. `/monitor the CI run for PR 412, check every 2m, stop after 1h`. May also be self-invoked in the rare case you are about to tell the user "Imicrosoft/amplifier-bundle-skills12
- Outcome CartographerOutcome-validity reviewer that refuses to count shipped work as progress until it maps to a measurable change in behavior. Hunts the gap between "we shipped it" and "we moved the number" — the output mistaken for an outcome. Use at any product checkpoint — plan, roadmap, PRD, ship review — when deliverables carry no metric, "done" is confused with "worked," or nobody can say how success will be measured: "what measurable outcome defines success, and how will we know we moved it?"microsoft/amplifier-bundle-skills12
- OutcomistOutcome-clarity reviewer that asks whether you have defined what you're trying to achieve and validated that the problem is real. Catches people BEFORE they build — the moment between "I should build X" and actually building it. Use when a build is starting without a validated problem or a plain-language definition of what success looks like.microsoft/amplifier-bundle-skills12
- PersonafyBuild a new opinionated advisor-persona skill — a reviewer "lens" like crusty-old-engineer, modeled on a real person or archetype. Mines the subject's authentic voice, defines its one load-bearing question, drafts it to the family template, and proves it steers a live session before publishing to a skills bundle. Use when creating or authoring a persona/advisor skill, adding a sibling to the crusty-old-engineer family, or turning a person's real direction style into a reusable reviewer skill. Almicrosoft/amplifier-bundle-skills12
- Positioning CriticCompetitive-differentiation reviewer that refuses to accept "the user wants this" as sufficient. Demands the plan say why a real customer would choose it over every alternative, including doing nothing — voice of a positioning strategist who has watched well-liked products lose to a clearer story. Use at any product checkpoint — plan, roadmap, go-to-market framing — when nobody can say why users would switch or pay, the competitive landscape is unaddressed, or "no one else does this" is assertedmicrosoft/amplifier-bundle-skills12
- Product CouncilConvene the Product Development Council — six orthogonal product-delivery lenses anchored by a mandatory problem-validation gate. Cold independent fan-out, debate-to-consensus, synthesized verdict with recorded dissent and a roster manifest.microsoft/amplifier-bundle-skills12
- Product Council HereConvene the Product Development Council on the CURRENT conversation — the plan, roadmap, or scope decision built in this session. The INLINE counterpart to /product-council (which forks isolated and cannot see the chat). Use when you want the council to critique what we're working on right now.microsoft/amplifier-bundle-skills12
- Restless Old BrianMomentum-driven engineering reviewer holding one uncompromising gate: is it REAL, proven end-to-end as a user would? Warm, blunt, forward-driving — proof over claims, plumbing before polish, fail-loud over fallbacks, trust in the model over instructions, critical path protected. Use at any checkpoint — brainstorm, design, plan, implement, debug, ship — when testing whether work is provable, built in the right order, or actually done rather than band-aided: "are we fooling ourselves about what's microsoft/amplifier-bundle-skills12
- RetrospectiveReview how work went and improve the next round. USE WHEN asked for a retro, delays, or process lessons. DO NOT USE for code review or transcript replay.microsoft/amplifier-bundle-skills12
- Second OpinionIndependent review of current work or a past session. USE WHEN a user wants a second opinion. DO NOT USE WHEN ordinary code review is wanted — use code-review.microsoft/amplifier-bundle-skills12
- Session DebugDiagnose issues in the current Amplifier session — misconfigured tools, failing operations, unexpected behavior. Use when something isn't working right.microsoft/amplifier-bundle-skills12
- SkillifyCapture a repeatable process from the current session into a reusable Amplifier SKILL.md skill file. Use when the user wants to create a skill, save a workflow as a skill, turn a process into a reusable skill, or mentions "skillify", "create skill", "make a skill", "save as skill", "capture workflow", "turn this into a skill", "new skill", or wants to automate a repeatable process they just performed.microsoft/amplifier-bundle-skills12
- Skills AssistAuthoritative consultant for all skills-related questions. Use when creating or modifying skills, understanding the Agent Skills spec, troubleshooting skill loading or invocation issues, leveraging enhanced format features (context fork, model_role, user-invocable), writing cross-harness portable skills, ensuring Claude Code Skills 2.0 compatibility, or deciding between skills vs agents.microsoft/amplifier-bundle-skills12
- Tester BreakerAdversarial breaker that reviews code by trying to make it fail, not by confirming it works. Hunts the unhappy paths — malformed input, the empty string, the reversed range, the race condition — as a gleeful adversary who assumes everything is broken until a concrete attempt to break it comes up empty. Use at any checkpoint — brainstorm, design, plan, implement, debug, review — when the happy path is celebrated while the edges sit unexamined, "looks fine" stands in for "I tried to break it and cmicrosoft/amplifier-bundle-skills12
- User AdvocateUser-need reviewer that speaks for the person who isn't in the room — the one who will actually live with what gets built. Hunts the gap between "we can build this" and "they actually want this," in the patient, impatient voice of the absent user. Use at any checkpoint — brainstorm, design, plan, implement, debug, review — when a feature is being built because it's buildable rather than wanted, the recovery path is missing, or nobody can name the person this serves: "do they actually want this, microsoft/amplifier-bundle-skills12
- Verification DisciplineUse when verifying that completed work actually works. Auto-surface during /verify mode, post-implementation review, or before claiming a task is done. Teaches testing outcomes vs implementation, the unit/integration/smoke gradient, and what "done" actually means.microsoft/amplifier-bundle-skills12
- Content Track ScaffolderScaffold a complete new content track (like Foundation, Advanced, or Terminal) with all required files — data parser, page components, routes, markdown content, and navigation. Use when adding a new learning path, creating a new track, or expanding the tutorial with a new module series. Use for questions like "add a new track", "create learning path for X", "scaffold track pages".microsoft/learn-ai-native-dev11
- Cowork Dashboard MemberMember step of the Cowork Team Report: gathers the user's own Cowork sessions, supports exclusions, computes impact metrics, and emails aggregate tables to a configured Teams channel email address. Excludes person names and prompts and replaces raw file names with de-identified descriptive labels; retains customer/account names. Supports one-time or biweekly runs with review before sending. Use for "send my Cowork Team Report stats", "email my Cowork stats to the team channel", "run the Cowork Tmicrosoft/CoworkDashboard11
- Cowork Dashboard MemberMember step of the Cowork Team Report: gathers the user's own Cowork sessions, supports exclusions, computes impact metrics, and emails aggregate tables to a configured Teams channel email address. Excludes person names and prompts and replaces raw file names with de-identified descriptive labels; retains customer/account names. Supports one-time or biweekly runs with review before sending. Use for "send my Cowork Team Report stats", "email my Cowork stats to the team channel", "run the Cowork Tmicrosoft/CoworkDashboard11
- Cowork Dashboard Team DashboardManager-side team rollup for Copilot Cowork ROI. Aggregates the de-identified stats teammates post (via the Cowork Dashboard Member skill) to a shared Teams channel into ONE anonymized HTML dashboard (five tabs), then emails the channel members a summary with the dashboard and a one-page PDF guide attached. First run asks for the Teams channel link and remembers it; each run reads the latest 15 days and keeps the latest post per person. Numbers only — no names or files; a Role breaks out only whmicrosoft/CoworkDashboard11
- Cowork Dashboard Team DashboardManager-side team rollup for Copilot Cowork ROI. Aggregates the de-identified stats teammates email (via the Cowork Team Report Member skill) to a shared Teams channel into ONE anonymized HTML dashboard (four tabs, with the how-to-read guide built in), then emails the channel members a summary with the dashboard attached. First run asks for the Teams channel link and remembers it; each run reads the latest 15 days and keeps the latest report per person. Numbers only — no names or files; a Role bmicrosoft/CoworkDashboard11
- Cowork Dashboard Team DashboardManager-side team rollup for Copilot Cowork ROI. Aggregates the de-identified stats teammates email (via the Cowork Team Report Member skill) to a shared Teams channel into ONE anonymized HTML dashboard (four tabs, with the how-to-read guide built in), then emails the channel members a summary with the dashboard attached. First run asks for the Teams channel link and remembers it; each run reads the latest 15 days and keeps the latest report per person. Numbers only — no names or files; a Role bmicrosoft/CoworkDashboard11
- Deploy Agent Aca AwsAI-led deployment of the AWS Bedrock sample agent with the Microsoft Entra Agent ID sidecar to Azure Container Apps. Use when the user wants to deploy the AWS sample to ACA, provision the AWS-federation intermediary Entra app, wire the token refresher, create the AWS OIDC provider and IAM role for Bedrock, build and push the four container images to ACR, or debug InvalidIdentityToken / AADSTS65001 / Directory.AccessAsUser.All / AcrPull errors in this specific deployment. NOT for local docker-commicrosoft/entra-agentid-samples11
- Deploy Agent Aca DevAI-led deployment of the local-LLM sample agent (Ollama + Microsoft Entra Agent ID sidecar) to Azure Container Apps. Use when the user wants to deploy sidecar/dev to ACA, run the agent on Azure without AWS/GCP, host Ollama on Container Apps, promote the docker-compose local-dev stack from ClientSecret to SignedAssertionFromManagedIdentity (secretless), or debug AADSTS65001/AADSTS50011/ImagePullBackOff/Ollama OOM errors in this specific deployment. NOT for AWS Bedrock (use deploy-agent-aca-aws) amicrosoft/entra-agentid-samples11
- Diagram ScaffolderGenerate new interactive diagram components for tutorial content. Use when adding a visual diagram, creating architectural illustrations, or building interactive flow visualizations. Use for questions like "add a diagram", "create diagram component", "new visual for module X". Produces a React component, registers it in the barrel export and StepCard parser, and provides the markdown reference syntax.microsoft/learn-ai-native-dev11
- Docs SyncDiff src/ and .github/ against docs/ to detect drift between code and design spec. Use when auditing the docs folder, after merging structural changes (adding paths/modules/diagrams/syntax/agents/skills/hooks), or before a release. Use for questions like "is docs in sync?", "what changed since the last docs update?", "find docs drift". Produces a structured report with proposed edits — does not modify docs/ directly.microsoft/learn-ai-native-dev11
- Entra Agent Id SetupAI-guided setup for Microsoft Entra Agent ID. Use when the user wants to provision an Agent Identity Blueprint, Agent Identity, and OBO client app in an Entra tenant; when configuring the dev/AWS/GCP sidecar stack; when debugging 403 Authorization_RequestDenied on blueprint creation; when checking which Entra role is required (Global Admin / Agent ID Administrator / Agent ID Developer); when running Start-EntraAgentIDWorkflow / setup-obo-client-app / setup-obo-blueprint.microsoft/entra-agentid-samples11
- Eval AnalysisComprehensive guide for analyzing SABER evaluation results — model comparison, agent architecture comparison, domain-specific analysis, and cross-domain aggregate analysis. Use this when asked to analyze eval results, compare models, generate visualizations, interpret scores, investigate cost-efficiency trade-offs, or extend analysis to new domains.microsoft/ACESEvals11
- Eval MonitoringGuide for monitoring running SABER evaluations, checking progress, and managing eval batches. Use this when asked to monitor evals, check progress, produce a status report, or manage concurrent eval runs. Also covers Docker health and resource management.microsoft/ACESEvals11
- Exercise ScaffolderGenerate consistent, high-quality coding exercises for AI-Native development tutorials. Use when creating hands-on exercises, coding challenges, practice problems, quizzes, labs, or skill-building activities. Use for questions like "create an exercise", "add practice activity", "build a challenge for Part X". Includes starter templates, solution patterns, hint progressions, and verification criteria.microsoft/learn-ai-native-dev11
- Inspect Eval DebuggingGuide for debugging inspect_ai evaluation failures, score issues, and model behavior. Use this when eval results are unexpected, scores are wrong, scoring fails, or model output appears corrupted.microsoft/ACESEvals11
- Inspect Eval ExecutionGuide for running SABER inspect_ai evaluations locally. Use this when asked to run, re-run, or configure an inspect eval for any SABER domain.microsoft/ACESEvals11
- Inspect Eval Log AnalysisGuide for parsing and analyzing inspect_ai .eval log files. Use this when asked to interpret eval results, extract tool calls, find scores, or investigate agent behavior from .eval logs.microsoft/ACESEvals11
- Teardown Agent Aca AwsAI-led teardown of the AWS Bedrock sample agent deployment on Azure Container Apps created by deploy-agent-aca-aws. Use when the user wants to delete the AWS sample ACA deployment, clean up the resource group, remove the AWS IAM role + OIDC provider, delete the intermediary Entra app, or optionally delete the Blueprint / Agent Identity / Client SPA. Defaults to DRY-RUN and keeps Entra/AWS objects unless the user explicitly opts in. NOT for local docker-compose (no cloud resources to delete) and microsoft/entra-agentid-samples11
- Teardown Agent Aca DevAI-led teardown of the local-LLM (Ollama) sample agent deployment on Azure Container Apps created by deploy-agent-aca-dev. Use when the user wants to delete the dev sample ACA deployment, clean up the resource group, or optionally delete the Blueprint / Agent Identity / Client SPA. Defaults to DRY-RUN and keeps Entra objects unless the user explicitly opts in. NOT for local docker-compose (use `docker compose down -v`) and NOT for the AWS Bedrock variant (use teardown-agent-aca-aws).microsoft/entra-agentid-samples11
- Track GeneratorGenerate new example tracks for the AI-Native tutorial. Use when creating new industry examples, adding a new track, building project templates, or expanding learning paths. Use for questions like "add a track for healthcare", "create new example", "new industry template". Produces consistent ExampleTrack data with all required fields including projectName, requirements, colorCoding, taskExamples, and verification examples matching the TypeScript interface in exampleTracks.ts.microsoft/learn-ai-native-dev11
- Tutorial Content QaComprehensive quality assurance for AI-Native development tutorials across all tracks (Foundation, Advanced, Terminal). Use when reviewing content for accuracy, clarity, consistency, and completeness. Use for proofreading, checking errors, auditing content, or running QA checks before publishing.microsoft/learn-ai-native-dev11
- Version CheckerValidate that tutorial content references current tool versions, APIs, CLI commands, and features. Use when reviewing content for outdated information, checking deprecations, verifying feature availability, auditing tool references, or updating stale version numbers. Covers GitHub Copilot (VS Code + CLI), Claude Code, VS Code settings, MCP, and Agent Skills standard.microsoft/learn-ai-native-dev11
- Agent DeveloperMicrosoft Agent Framework + Foundry Toolbox MCP integration specialistmicrosoft/Build26-BRK242-turn-your-agents-into-action-connect-tools-apis-and-documents10
- Azure Search OpsOperate the Azure AI Search index and knowledge base behind FoundryIQ for Fibey field ops.microsoft/Build26-BRK242-turn-your-agents-into-action-connect-tools-apis-and-documents10
- FeedbackFile a bug report or feature suggestion on GitHub via gh CLI. Gathers details conversationally, previews, and creates an issue. Use when the user wants to report a bug or suggest a feature.microsoft/MCS-Agent-Builder10
- Field BriefingProvide a comprehensive field briefing for a work order — combining work order details, parts availability, and relevant technical procedures or safety protocols from the knowledge base. Use when the technician wants a full briefing, walkthrough, or complete preparation guide for a job.microsoft/Build26-BRK242-turn-your-agents-into-action-connect-tools-apis-and-documents10
- Foundry Toolbox OpsOperate the Foundry Toolbox and Foundry-hosted agents for the Fibey project: inspect, version, recreate, and smoke-test.microsoft/Build26-BRK242-turn-your-agents-into-action-connect-tools-apis-and-documents10
- Inventory LookupHandle inventory and parts queries — stock checks, part lookups, availability, category browsing, and equipment searches. Use when the technician asks about parts, stock levels, SKUs, availability, supplies, or equipment.microsoft/Build26-BRK242-turn-your-agents-into-action-connect-tools-apis-and-documents10
- IterateUse this skill when the user asks Claude to autonomously test, fix, review, and merge a change end-to-end. Detects which lane(s) changed (frontend / backend / framework / agentspec), spawns relevant verifiers (agentic-test-loop with --require-oracle for false-green prevention; backend-verify for contracts/types/unit/server), runs a facilitator review loop using qa-challenger via Agent tool with worktree isolation until score>=9 and zero critical findings, calls multi-model-review.js review-mergemicrosoft/MCS-Agent-Builder10
- Knowledge RetrievalHandle technical knowledge questions — procedures, safety protocols, troubleshooting, specifications, installation standards, and testing guidance. Use when the technician asks how-to questions, about procedures, safety, cable specs, OTDR testing, splicing techniques, or troubleshooting steps.microsoft/Build26-BRK242-turn-your-agents-into-action-connect-tools-apis-and-documents10
- Mcs BuildUse this skill to build an agent in Copilot Studio from a researched agentspec.json. Runs pre-build validation (auth, env, connections, tools, model), then creates the agent, configures instructions, knowledge, tools, model, topics, and publishes. Supports single-agent, multi-agent, and connected-agent architectures. Use after /mcs-research when agentspec.json is ready, or to resume a partially completed build.microsoft/MCS-Agent-Builder10
- Mcs ContextUse this skill to pull M365 history about a customer or company before research. Searches emails, meetings, documents, Teams, and people via WorkIQ MCP to compile a customer context file. Use when starting a new project, when the user mentions a customer name, or when you need business context for architecture decisions.microsoft/MCS-Agent-Builder10
- Mcs EvalUse this skill to test an agent's quality after building or fixing it. Runs eval test sets against a published agent via Direct Line API (default, auto), CopilotStudio SDK, Power CAT Kit, or MCS Native Eval (for MCP agents). Results are written per-test to evalSets[].tests[].lastResult in agentspec.json. Use after /mcs-build or /mcs-fix, or when the user wants to re-test.microsoft/MCS-Agent-Builder10