creating-amplifier-modulesUse when creating a new Amplifier module (tool, hook, orchestrator, context, or provider). Covers the mount() contract, protocol compliance validation, placeholder patterns, and the module directory structure. Prevents the common mistake of creating no-op…fixture-skillA comprehensive and extensive skill package covering the complete theory and practice of fixture artifact handling, including the creation, validation, inspection, review, refresh, alignment, migration, archival and eventual deletion of fixture artifacts of…per-repo-conventionsUse when starting work in any repository, and again at each work-phase transition (design, coding, debugging, verification, opening a PR). Loads the canonical per-repo-conventions guidance from foundation:docs/PER_REPO_CONVENTIONS.md — the discovery pattern…bundle-to-dotConvention for the v3 bundle documentation system: a single bundle.dot + bundle.png per repo, generated by bundle_repo_dot(). Use when generating, validating, or interpreting bundle documentation files. Covers 7-cluster DOT structure, token cost model, color…
repository explorer
microsoft · Repositories and representative skills - Page 16
Repository-level view of 4,208 collected skills across 434 GitHub repositories.
viva-insights-causal-analysisAssess and analyse exposure-outcome relationships in Viva Insights Person Query exports using design-first panel diagnostics. Use when an analyst asks whether a workplace behaviour, Copilot metric or intervention affects another metric or a supplied…viva-insights-analysisAnalyze Microsoft Viva Insights data with the open-source vivainsights R and Python packages. Use this skill whenever working with Viva Insights query exports (Person Query, Meeting Query, Consumption query, GitHub query, person-to-person or group-to-group…viva-insights-process-analysisAnalyse collaboration around a named business process, such as an annual audit, financial close, planning cycle or review programme, using Viva Insights Meeting Query and optional purpose-specific Person Query exports. Use when defining which process meetings…viva-insights-copilot-dashboardsReproduce and customise the Viva Insights Consumption and Ways of Working or Developer Experience and Copilot reference dashboards with reusable R code. Use for building either demo, adapting Consumption or GitHub query exports into these dashboards, or…
build-tool-graphRun VULCAN's graph-construction phase correctly — build_graph and plan_sequences — with a cost estimate before you start and a check afterwards that the graph is actually usable. Use when building the tool dependency graph for a category, or when…generate-training-dataRun VULCAN's task-generation and trajectory phases — initial states, argument samples, chain execution, user queries, trajectories, judging, and dataset export — and verify every stage wrote to its documented path with the documented record shape. Use after…run-vulcanDrive a complete VULCAN run from a conversation — take tool schemas or an existing catalog, build the simulated environment, review it, construct the tool dependency graph, generate and judge trajectories, and export the training set. Use when someone wants…simulate-environmentBuild a VULCAN input catalog from tool schemas a user shares, run the environment-simulation phase, and review the generated environment class for state/behaviour mismatches, unusable initial states, arguments with no effect, non-determinism, and missing tool…
appearance-authoringCreate, revise or package Amplifier Unified Reference appearance deltas with light/dark support, scoped profiles and safe preview/cancel. Load for authoring, not merely choosing a look. Component/layout authoring belongs to amplifier-shell.amplifier-shellCustomize Amplifier Unified presentation or build shell extensions. USE WHEN changing layouts, themes, sidebar modules, or artifact viewers, interactive conversation surfaces, and validating hot-loaded components. DO NOT USE WHEN changing AmplifierSession…unified-appOperate Amplifier Unified through app_control: settings, tasks, collaboration, testing, outputs, Canvas, computer access and Smart Tools. Load only the reference needed for the user's task; ordinary conversation and actions whose schema is already known do…coordinate-workCommission independent goal-driven workers, review their results, and resolve real blockers through Unified's authenticated coordination controls.
test-ahp-conformanceCreate or review black-box Agent Host Protocol conformance tests, including deterministic model fixtures, lifecycle and error cases, multi-client and restart coverage, bounded timeouts, and CLI/HTML reports with optional JSON results. Use for observable…build-ahp-clientImplement or review an SDK-backed Agent Host Protocol client application, including initialization, subscriptions, immutable reducer state, reconnect cleanup, multi-host behavior, and UI-friendly projections. Use for browser, TypeScript, desktop, or other…build-ahp-hostImplement or review an Agent Host Protocol host or server, including JSON-RPC transport routing, subscriptions, serverSeq and reconnect, durable state, cancellation, concurrency, model adapters, and explicit unsupported behavior. Use for host architecture and…design-ahp-protocolDesign or review Agent Host Protocol commands, actions, state, errors, reducers, schemas, code generation, versioning, compatibility, and multi-client invariants. Use when changing the AHP contract or assessing a protocol-level design, not when implementing…
zava-act1-migrateAct 1 of the Zava Lending Hyperscale workshop — Migrate & Modernize — and the standalone, approve-each-step runbook to migrate ANY on-prem / IaaS SQL Server database to Azure SQL Database Hyperscale using the local `az datamigration` CLI. USE WHEN the user…zava-act2-scaleAct 2 of the Zava Lending Hyperscale workshop — Scale on Hyperscale. USE WHEN the user wants to run "Act 2", "the scale act", or to learn how Hyperscale scales: changing vCores as a minimal-downtime control-plane operation, serverless for variable load, and…zava-act3-aiAct 3 of the Zava Lending Hyperscale workshop — The Engine Knows: native vector search + in-database AI loan scoring. USE WHEN the user wants to run "Act 3", "the AI act", build embeddings / DiskANN vector index / hybrid Narrative Search / Phi-4 AI Loan…zava-hyperscale-workshopOrchestrator for the Azure SQL Foundations Hyperscale workshop (fictional customer ZavaFin / Zava Lending, one database ZavaLendingDB) — a three-act "Migrate → Scale → AI" story. USE WHEN the user says "let's go through the workshop examples", "run the Azure…
approval-routingUse when submitting a decision to the Caldova Deal System, when it returns REQUIRES_HUMAN_APPROVAL, while waiting for a human approval, and after approval (term sheet, CRM, reply to seller).counterproposalUse when a deal ask is outside the rate card or below the margin floor and you must recommend a decision-ready counter (terms, GM bridge, customer value, approver).deal-intakeUse first on any new deal-desk request (a seller email or redline pasted into the chat, or a deal id). Gathers the request, the deal record and precedents, and treats customer documents as untrusted.pricing-policyUse whenever you need deal economics, the margin floor, the rate card or the authority matrix. Calls the Deal Economics agent for all math and explains results against Caldova policy.
junco-graph-createGenerate runnable Junco workflows as paired `name.yml` topology and `name.ts` configuration/code using `JuncoGraph.fromYaml` from `junco`. Use for any dataflow graph, agent coordination, fan-out/fan-in, joined review, feedback or Ralph loops, nested agencies,…junco-graph-optimizerOptimize an existing Junco workflow's graph topology through measured restructuring, decomposition, tournaments or pruning, not new-workflow creation or model, scheduler or limit tuning.junco-profile-optimizerProfile and tune an existing Junco workflow pair (`workflow.yml` + `workflow.ts`) until a measured objective converges: scheduler, model-ladder and limit experiments that minimize or maximize recorded USD, tokens, memory, an existing numeric edge probe or a…update-dependenciesUpdate Junco's vendored, imported, and pinned dependencies to the latest allowed stable versions, including major upgrades, and repair resulting API incompatibilities. Use for dependency refreshes, marsh patch rebases, TypeScript/Rust/Verus pin updates,…
ksr-gap-repairRecover historical Kusto Slice Runner Failed/DeadLettered gaps after a job is healthy again. Use for cleanup, failed-slice backfill, or dependency-aware recovery of selected jobs or groups. Requires three recent successful logical slices for windows up to one…ksr-job-managerUse when the user wants an agent to read Kusto Slice Runner jobs, inspect read-only operational diagnostics, create/update/pause/resume/soft-delete/restore jobs, or repair Failed/DeadLettered work in a running local Kusto Slice Runner app. Drives the…ksr-release-highlightsUse when the user wants AI-written highlights for an existing Kusto Slice Runner GitHub Release draft. Auto-selects one workflow-owned draft or asks the user to choose among multiple drafts, previews the exact highlights for approval, and can replace only the…ksr-schedule-jsonUse when the user wants to create, edit, or validate a Kusto Slice Runner job-schedule JSON file (single object or an array of objects). Produces JSON-only output and validates it locally against the strict Kusto Slice Runner schedule contract. Does NOT…
generate-revision-uxBuild a browsable web UI showing where a vision stands in the ReVisioner process: which risky assumptions need the user's attention right now (amend the vision, or unblock a spike), and a drill-down into the evidence behind every verdict. Reads…derisk-assumptionsDe-risk the risky assumptions in a vision by running spikes. Given the revisioner risky-assumptions.yaml, this designs a spike for each open assumption (literature/evidence search, hands-on trial, or a fresh empirical investigation), runs the spikes in…find-risky-assumptionsSurface the risky, unvalidated assumptions hidden inside a vision, product plan, proposal, solution write-up, spec, or design doc, and record any NEW ones in the project's risky-assumptions file. Use this whenever the user has a vision/plan/ proposal artifact…vision-check-inCheck in on where a vision stands once its risky assumptions have been found and are being de-risked. Reads the revisioner risky-assumptions.yaml plus the live per-spike status.json files, classifies every assumption (holds / fails / blocked / in-flight /…
pyright-pr-typespec-reviewInvestigate whether Pyright changes typing behavior safely by tracing the diff, designing adversarial cases, comparing exact revisions, and checking relevant CPython behavior. Use for author preflights, regression investigations, merge safety, or testing…pyright-issue-analysisInvestigate Pyright issues using minimal repros, CPython semantics, the typing specification, and mypy comparisons. Use for issue triage, maintainer response drafts, or evidence-backed issue fixes and PRs.evaluation-tracingInvestigate Pyright type-inference or cache regressions, unexpected or lost diagnostics, speculative or reentrant evaluation, evaluator state changes, and repeated evaluator work using local evaluation traces.
playwright-patch-releasePrepare a patch release of Playwright Python (v1.xx.1 and later) from a release branch. Picks the next version, writes the release notes as the list of fixes in microsoft/playwright between the driver of the previous release of the branch and the driver of…playwright-releasePrepare a new Playwright Python release, v1.xx.0, with the full release notes. For a patch release of a release branch, use playwright-patch-release. Checks open bugs, adds Python-specific changes to the Python release notes in microsoft/playwright, opens the…playwright-rollRoll Playwright Python to a new microsoft/playwright commit. Pins the commit, generates the API and builds the driver from it, and ports the upstream diff of the client and the tests.