- Context Intelligence Eval DesignUse when designing evaluation scenarios for a context-intelligence tool signal. Derives success criteria from domain-concepts.md and produces evaluation-scenarios.md entries plus DTU profile templates.microsoft/amplifier-bundle-context-intelligence5
- Context Intelligence Evaluation MethodologyUse when deciding how to measure a context-intelligence tool signal. Covers metric design across quality/efficiency/efficacy axes, artifact-metric avoidance via precursor measurement, A/B and statistical-N discipline, and test-data fidelity.microsoft/amplifier-bundle-context-intelligence5
- Context Intelligence GdsUse when about to write naive Cypher for a graph-topology question — pathfinding, reachability, centrality/influence, community/clustering, structural similarity, or similar event paths/trajectories (with/without time) — reach for Neo4j GDS or APOC instead of hand-rolling traversals one hop at a time. WHEN/WHY layer; graph-query's "Push Work to the Database" section is the HOW.microsoft/amplifier-bundle-context-intelligence5
- Context Intelligence Graph QueryUse when querying the context-intelligence property graph for session history, tool call traces, LLM iteration analysis, execution scale metrics, agent delegation trees, skill loading, and recipe orchestration. Covers all graph layers, cross-layer SOURCED_FROM joins, SST navigation, blob handling, and verified Cypher patterns.microsoft/amplifier-bundle-context-intelligence5
- Context Intelligence Hill ClimbingUse when an investigation needs more than one step — track it in todo as a hill climb so progress and dead leads leave an audit trail. Governs HOW you track the climb, not how you query or extract — that stays in graph-query / session-navigation.microsoft/amplifier-bundle-context-intelligence5
- Context Intelligence Server Data OpsExact step order, wording, and the "session details" block format for the delete flows the server-data-ops agent drives — delete the current session, clean up every session from the current working directory, find-then-delete a session by description, and delete a session someone else created.microsoft/amplifier-bundle-context-intelligence5
- Context Intelligence Session NavigationUse when extracting session data directly from JSONL files — the fallback when the graph server is unavailable or outside graph-analyst.microsoft/amplifier-bundle-context-intelligence5
- Context Intelligence Session ReconstructionUse when local Amplifier session files are missing, broken, or incomplete — rebuilds events.jsonl, transcript.jsonl, and metadata.json from the context-intelligence graph server.microsoft/amplifier-bundle-context-intelligence5
- Context Intelligence Tool DesignUse when selecting a detection strategy and implementation primitive for a context-intelligence signal. Classifies signals as deterministic, probabilistic, llm-evaluated, or hybrid, and applies the cheapest-sufficient-capability principle.microsoft/amplifier-bundle-context-intelligence5
- Customer Activity ForgeFind a bounded AI opportunity when a customer or industry is known but no use case is defined. Research public sources, rank ideas against scenario playbooks, and expose gaps.microsoft/frontier-agentic-cobuild-rvas5
- CustomizeInteractive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deploymicrosoft/frontier-agentic-cobuild-rvas5
- Deploy ModelUnified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deploymmicrosoft/frontier-agentic-cobuild-rvas5
- Excalidraw DiagramCreate Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.microsoft/frontier-agentic-cobuild-rvas5
- FinetuningFine-tune models on Azure AI Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), microsoft/frontier-agentic-cobuild-rvas5
- Foundry Hosted AgentsBuild, deploy, and manage Microsoft Foundry hosted (containerized) agents — Responses + Invocations protocols, agent.yaml, azd ai agent, per-agent Entra identity, dedicated endpoints, ACR. Use for optional hosted-agent paths in scenario deployment lessons.microsoft/frontier-agentic-cobuild-rvas5
- Foundry Iq Knowledge BasesBuild Microsoft Foundry IQ knowledge bases (preview) — multi-source, permission-aware grounding with agentic retrieval (query decomposition + parallel search + reranking); expose to agents via MCP. Use for AI Grounding knowledge-base lessons.microsoft/frontier-agentic-cobuild-rvas5
- Foundry ModelsDiscover, deploy, and manage Microsoft Foundry models; preset vs customized deployments; capacity discovery across regions; quota; PTU vs PAYG; RAI policy. Use for scenario model selection.microsoft/frontier-agentic-cobuild-rvas5
- Foundry ObservabilityTrace, monitor, and evaluate Microsoft Foundry agents — OpenTelemetry GenAI traces in Application Insights (KQL), eval↔trace correlation, azd ai agent monitor, dataset curation from prod traces, built-in quality + safety/RAI evaluators, batch evals, regression detection. Use for scenario evaluation and tracing.microsoft/frontier-agentic-cobuild-rvas5
- Foundry Projects ResourcesProvision Microsoft Foundry resources and projects; wire connections (key / OAuth / managed identity / agent identity); standard vs private-network infra. Use for scenario setup and provisioning.microsoft/frontier-agentic-cobuild-rvas5
- Foundry ToolboxesCurate intent-based Microsoft Foundry Toolboxes (preview) — one MCP-compatible endpoint bundling MCP, Web Search, Azure AI Search, Code Interpreter, File Search, OpenAPI, A2A, Browser Automation, and Computer Use tools. Use when a scenario needs a toolbox integration.microsoft/frontier-agentic-cobuild-rvas5
- Foundry WorkflowsMulti-agent orchestration in Microsoft Foundry — declarative workflow vs A2A tool call vs Connected Agents pattern; Microsoft Agent Framework (MAF) patterns including Magentic manager/planner. Use when adapting a scenario to multi-agent orchestration.microsoft/frontier-agentic-cobuild-rvas5
- 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-agentic-cobuild-rvas5
- 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-cobuild-rvas5
- 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-cobuild-rvas5
- ImpeccableUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, lamicrosoft/frontier-agentic-cobuild-rvas5
- ImpeccableUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, lamicrosoft/frontier-agentic-cobuild-rvas5
- Lookup Patient HistoryLoad a synthetic patient EHR record (demographics, HPI, problems, meds, devices, prior imaging studies and reports) for a given chest X-ray. Invoke as the first step of any context-aware reporting flow that needs patient history. No model calls.microsoft/siim-workshop-20265
- Membership Card PngGenerate a digital BlastPass membership card as a PNG image by running the bundled card_png.py script. Use when a member self-serves a lost/stolen/damaged card replacement, or any time a card needs to be shown on screen (vs. printed). The skill takes the member details returned by the Membership MCP (get_membership) plus the new_card_serial returned by reissue_card and passes them as command-line flags to a bundled Python (matplotlib) script that renders a CR80-sized membership card to a real PNmicrosoft/copilot-studio-gallery5
- Membership Card PngGenerate a digital BlastPass membership card as a PNG image by running the bundled card_png.py script. Use when a member self-serves a lost/stolen/damaged card replacement, or any time a card needs to be shown on screen (vs. printed). The skill takes the member details returned by the Membership MCP (get_membership) plus the new_card_serial returned by reissue_card and passes them as command-line flags to a bundled Python (matplotlib) script that renders a CR80-sized membership card to a real PNmicrosoft/copilot-studio-gallery5
- Microsoft FoundryDeploy, evaluate, fine-tune, and manage Foundry agents end-to-end: Docker build, ACR push, hosted/prompt agent create, container start, batch eval, continuous eval, prompt optimizer, Agent Optimizer scaffold, agent.yaml, dataset curation from traces, model fine-tuning (SFT/DPO/RFT). USE FOR: deploy agent, hosted agent, create agent, add tool to agent, invoke agent, evaluate agent, continuous eval, continuous monitoring, optimize prompt, improve prompt, optimize agent instructions, deploy model, microsoft/frontier-agentic-cobuild-rvas5
- Points ReconciliationReconcile a customer's BlastPoints loyalty balance after a complex visit (purchases, returns, promo multipliers, expiry) and convert the net balance to store credit. Use when an associate asks about a member's points, or after a return that should claw back previously earned points. The skill runs a bundled Python script that applies the base earn rate, promo multipliers, tier bonus, clawbacks, and expiry, then prints a points ledger and the redeemable store-credit value.microsoft/copilot-studio-gallery5
- Points ReconciliationReconcile a customer's BlastPoints loyalty balance after a complex visit (purchases, returns, promo multipliers, expiry) and convert the net balance to store credit. Use when an associate asks about a member's points, or after a return that should claw back previously earned points. The skill runs a bundled Python script that applies the base earn rate, promo multipliers, tier bonus, clawbacks, and expiry, then prints a points ledger and the redeemable store-credit value.microsoft/copilot-studio-gallery5
- PresetIntelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions. Automatically checks current region first and shows alternatives if needed. USE FOR: quick deployment, optimal region, best region, automatic region selection, fast setup, multi-region capacity check, high availability deployment, deploy to best location. DO NOT USE FOR: custom SKU selection (use customize), specific version selection (use customize), custom capacity configuration (usmicrosoft/frontier-agentic-cobuild-rvas5
- Prorated Refund CalculatorCalculate the exact prorated refund when a customer cancels a BlastPass membership, and the net settlement when a defective unit is traded up to a pricier model. Use after the Store Policy Agent confirms the refund rule and the Membership MCP has returned the membership details. The skill runs a bundled Python script so the arithmetic is exact.microsoft/copilot-studio-gallery5
- Prorated Refund CalculatorCalculate the exact prorated refund when a customer cancels a BlastPass membership, and the net settlement when a defective unit is traded up to a pricier model. Use after the Store Policy Agent confirms the refund rule and the Membership MCP has returned the membership details. The skill runs a bundled Python script so the arithmetic is exact.microsoft/copilot-studio-gallery5
- 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-cobuild-rvas5
- Slip Pdf GeneratorGenerate a printable BlastBox return / RMA / exchange slip as a PDF for the associate to hand to the customer. Use at the end of a return, warranty swap, membership cancellation, or upgrade once all amounts are final. The skill runs a bundled Python script that renders the confirmed slip values into a real PDF file.microsoft/copilot-studio-gallery5
- Slip Pdf GeneratorGenerate a printable BlastBox return / RMA / exchange slip as a PDF for the associate to hand to the customer. Use at the end of a return, warranty swap, membership cancellation, or upgrade once all amounts are final. The skill runs a bundled Python script that renders the confirmed slip values into a real PDF file.microsoft/copilot-studio-gallery5
- Summarize EvalSummarize a CXR eval result directory (or compare two) as a Markdown table with metrics as columns and confidence bins as rows. Invoke when the user points at one or two result-dirs and asks for a summary, calibration analysis, or comparison.microsoft/siim-workshop-20265
- TranscriptRetrieve the prior user and assistant conversation verbatim from the current Context Intelligence capture, or named sessions. Use when a user asks to replay, quote, review, or act on a transcript.microsoft/amplifier-bundle-context-intelligence5
- Use Case MapperBreak a customer's business use case into parts, map each part to scenario modules across tracks, and make adaptation and uncovered work explicit. Use when a team already has a use case and needs to know what the kit covers.microsoft/frontier-agentic-cobuild-rvas5
- Workflow Pattern AnalysisUse when asked how a workflow is failing, what separates a successful run from a failing one, which steps are the most common failure points, or what patterns recur across sessions — analyses failure/success patterns and signals across many runs using context-intelligence session data.microsoft/amplifier-bundle-context-intelligence5
- Write Report AdapterWrite a chest X-ray report grounded in the trained MedImageInsight (MI2) adapter. Invoke whenever drafting a CXR report when the adapter is available — get vision-grounded per-finding positive/possible/negative calls, then delegate the prose to `write-report-simple`.microsoft/siim-workshop-20265
- Write Report AdapterWrite a chest X-ray report grounded in the trained MedImageInsight (MI2) adapter. Invoke whenever drafting a CXR report when the adapter is available — get vision-grounded per-finding positive/possible/negative calls, then delegate the prose to `write-report-simple`.microsoft/siim-workshop-20265
- Write Report SimpleWrite a structured chest X-ray report (Indication, Technique, Findings, Impression) using canonical radiologist phrasings. Invoke whenever drafting or revising a CXR report.microsoft/siim-workshop-20265
- Write Report With EhrWrite a context-aware chest X-ray report grounded in the trained MedImageInsight (MI2) adapter AND the patient's EHR record. Adds a COMPARISON section and uses the most recent prior report to call out interval change.microsoft/siim-workshop-20265
- Write Report ZeroshotWrite a chest X-ray report grounded in MedImageInsight (MI2) zero-shot classifier scores. Invoke whenever drafting a CXR report when MI2 is available — get vision-grounded per-finding probabilities, then delegate the prose to `write-report-simple`.microsoft/siim-workshop-20265
- Write Report ZeroshotWrite a chest X-ray report grounded in MedImageInsight (MI2) zero-shot classifier scores. Invoke whenever drafting a CXR report when MI2 is available — get vision-grounded per-finding probabilities, then delegate the prose to `write-report-simple`.microsoft/siim-workshop-20265
- Writing For AgentsWriting documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.microsoft/frontier-agentic-cobuild-rvas5
- YagniKeep design and code simple, and communicate clearly in documents, comments, messages and diagrams.microsoft/agentic-loops5
- Add ActivityAdd a new duroxide activity to the runtime. Activities are the durable boundary between the orchestration and session management — they dispatch to ManagedSession or SessionManager methods.microsoft/PilotSwarm4
- Add Amplifier AgentUse amplifier-agent (Microsoft's modular agent runtime — bundled providers, swappable orchestrators, MCP tools) as the full agent provider in place of the Claude Agent SDK. Routes through OneCLI's Authorization-header rewrite path so the host never holds raw API keys. Per-group via agent_provider.microsoft/amplifier-app-nanoclaw4
- Add Atomic Chat ToolAdd Atomic Chat MCP server so the container agent can call local models served by the Atomic Chat desktop app via its OpenAI-compatible API.microsoft/amplifier-app-nanoclaw4
- Add CodexUse Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, session resume — in place of the Claude Agent SDK. ChatGPT subscription or OPENAI_API_KEY. Per-group via agent_provider. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).microsoft/amplifier-app-nanoclaw4
- Add DashboardAdd a monitoring dashboard to NanoClaw. Installs @nanoco/nanoclaw-dashboard and a pusher that sends periodic JSON snapshots.microsoft/amplifier-app-nanoclaw4
- Add DeltachatAdd DeltaChat channel integration via @deltachat/stdio-rpc-server. Native adapter — no Chat SDK bridge. Email-based messaging with end-to-end encryption.microsoft/amplifier-app-nanoclaw4
- Add DiscordAdd Discord bot channel integration via Chat SDK.microsoft/amplifier-app-nanoclaw4
- Add EmacsAdd Emacs as a channel. Opens an interactive chat buffer and org-mode integration so you can talk to NanoClaw from within Emacs (Doom, Spacemacs, or vanilla). Local HTTP bridge — no bot token or external service needed.microsoft/amplifier-app-nanoclaw4
- Add EventAdd a new event type that flows from the LLM session through to client subscribers. Covers firing the event from ManagedSession, persisting to CMS, and filtering in PilotSwarmSession.on().microsoft/PilotSwarm4
- Add Gcal ToolAdd Google Calendar as an MCP tool (list calendars, list/search/create events, free/busy queries) using OneCLI-managed OAuth. Multi-calendar and multi-account supported. Mirrors /add-gmail-tool's stub pattern — no raw credentials ever reach the container; OneCLI injects real tokens at request time.microsoft/amplifier-app-nanoclaw4