Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/microsoft/cat-agent-skills.Loading the repository README…
Showing 40 of 202 collected skills.
Use this skill whenever the user asks how to connect, integrate or extend SAP (ECC, S/4HANA, RISE, S/4HANA Cloud, SuccessFactors, BTP) with Microsoft Power Platform or Copilot Studio: which SAP connector, gateway, API layer or single sign-on option to choose;…
Use this skill whenever the user asks for a Responsible AI (RAI) impact assessment, RAI review, harms or impact analysis, or pilot/release-readiness review of an AI agent, or to reassess an agent after material changes to its tools, data, memory, or users.…
Use this skill when the user asks to create, improve, review, package, genericise, or submit an Agent Skill, SKILL.md file, skill metadata, or reusable agent instruction bundle.
Turns Microsoft 365 admin center Cost Management and Cowork usage exports (CSV) into an interactive Cowork & Work IQ consumption report: service breakdown (prepaid vs pay-as-you-go), spending-limit analysis per policy, group and user consumption, credits per…
Discovers the user's authorized Microsoft 365 meetings and transcripts, then builds a reviewable library of verified moments in Microsoft 365 Copilot Cowork. Use whenever the user wants a how-to library, decision log, customer-voice library, demo highlights,…
Use this skill whenever the user wants to evaluate, test, or validate an AI agent, decide whether an agent is ready to ship or go live, choose how to grade an agent's answers (exact match, similarity, meaning, keywords, quality, or custom), design a test set…
Use this skill whenever the user wants to inspect, understand, snapshot, compare, or document the capabilities of the current agent harness — for example "what can this harness do?", "which Python libraries are installed?", "what should I use to create Word…
Diagnose a live Microsoft Copilot Studio agent from its analytics and transcripts, find why it is underperforming, and produce a prioritized improvement backlog tied to specific topics, knowledge sources and tools. Use when an agent is already in production…
Run an adversarial assurance review of a Microsoft Copilot Studio agent you own — generate and execute test cases for indirect prompt injection, oversharing and authorization bypass, data leakage, scope escape and tool misuse — then score the findings and map…
Use this skill whenever the user says "assess this use case", "score my AI use case", "prioritise these agent ideas", "generate a use case assessment report", or "update my AI use case report" — or when they attach a use-case document, SDR, or prior…
Builds the evidence register for the mapped clauses from the uploaded QMS exports and document indexes. Use when the user says "gather the evidence", "what do we have on file", "build the evidence register", or after scope-map in a readiness run.
Validates the evidence register against clause requirements and flags gaps with severity - the explicit Govern step and the core work of this plugin, via the deterministic gap_check engine. Use when the user says "are we ready for the audit", "check for…
Drafts the audit-readiness pack - verdict, gaps with owners and actions, clause map, evidence index - from the contract payload. Use when the user says "draft the readiness pack", "prep the audit binder", or after gap-check in a readiness run.
Maps the audit scope to the standard's clauses and required evidence types with the deterministic clause_map engine. Use when the user says "we have an audit coming", "map the audit scope", "what clauses apply", or when an audit-readiness run begins.
Surfaces contradictory evidence - studies moving the same metric in opposite directions - rather than a smoothed answer. Use on "do the studies agree", "any conflicting evidence", after trend-compare.
Drafts the cited insight brief with the provenance and usage-rights record attached. Use to close every insight run: "draft the brief", "write it up for the category review".
Checks usage rights, geography and expiry for every retrieved study against the declared use - the explicit Govern step - with the deterministic provenance_check engine. Use on "can we use this externally", "is this stat cleared for the board deck", after…
Retrieves and ranks prior research, panel extracts and campaign results relevant to the question. Use when the user says "what do we already know about <topic>", "find prior research on", "have we studied this before", or an insight request begins.
Compares trends across markets and periods like-for-like with the deterministic trend_compare engine. Use on "how has this trended", "compare markets", "what changed since the last study", after research-retrieve.
Recommends which Microsoft 365 / Copilot Studio agent option fits a described scenario — using Microsoft 365 Copilot as-is, building a standard (declarative) agent, or building a custom (custom engine) agent — and which Copilot Studio harness to build on…
Test Microsoft Copilot Studio agents programmatically against a set of question/answer pairs, without driving a browser. Use when the user wants to evaluate, test, validate, benchmark or regression-test a Copilot Studio agent; run an eval set or test set…
Assess business, experience, channel, identity, orchestration, governance, maturity, and cost requirements to recommend the right Microsoft Copilot Studio harness: GitHub Copilot, standard, or Copilot chat. Use when asked which harness to choose, what to…
Use when a Copilot Studio maker provides uploaded files, exported text, or a document set and wants to assess whether that corpus is ready for knowledge grounding. Use this before scoring chunkability, freshness signals, conflicts, or whether content belongs…
Use this skill whenever the user describes a Copilot Studio agent in a sentence or two and wants a build-ready blueprint, or asks how to design, scope, or structure an agent (its type, topics, tools, knowledge, or welcome experience). Trigger on requests like…
Assembles customer, order, loyalty and carrier context, detects record-vs-account contradictions, and selects the resolution path deterministically with the context_assemble engine. Use after inquiry-intake, or on "pull up everything on this order".
Builds the structured escalation packet when the run cannot resolve - intent, context, contradictions, what was checked, recommended next step. Use on any low-confidence, contradicted, or out-of-scope run: "escalate this", "hand off to tier 2".
Takes the customer inquiry from any channel and classifies intent against the taxonomy with the deterministic intent_classify engine. Use when a service inquiry arrives - "where is my order", "it says delivered but I never got it", "can I return this", "is it…
Retrieves the approved knowledge article, policy text or product doc that grounds the answer for the classified intent. Use after context-assemble, or on "what's the approved answer for this".
Drafts the customer-facing resolution in the right channel and tone from the assembled context and approved sources. Use to close resolvable runs - "draft the reply", "answer the customer".
Traces the change across the BOM with where-used and rolls up form/fit/function impact, interface violations, document updates and inventory disposition - deterministically. Use when the user says "what does this change affect", "run where-used", "impact…
Drafts the engineering change notice with the affected-item list, document updates, dispositions and open requirements from the contract payload. Use when the user says "draft the ECN", "write up the change", or after standards-check in a change run.
Reads the engineering change request, spec/drawing delta and BOM export into the mfg.engineering-change-bom.v1 contract. Use when the user says "assess this change request", "work ECR <id>", "what does this change touch", or when an engineering-change run…
Checks the proposed change against drawing standards and internal design rules, citing each rule applied. Use when the user says "does this meet the design rules", "standards check", "is this change allowed", or after bom-impact in a change run.
Use this skill whenever the user asks to review, assess, validate, improve, govern, or prepare a Microsoft Copilot Studio agent, multi-agent solution, or enterprise AI architecture before implementation. Apply an enterprise architecture assessment before…
Use this skill whenever a user asks to audit, curate, clean up, deduplicate, rationalize, or assess files used by an AI knowledge source. Require the user to upload copies of the source files, analyze those complete files locally, and use configured knowledge…
Required whenever a knowledge request names or implies a country, asks what applies "here," or compares countries. Treat Country as document metadata, not as a content-search term. Before any content search, general-knowledge answer, or clarification, use…
Prioritizes the fault by asset criticality and downtime cost into a P1-P4 maintenance priority with a response target and cost estimate, deterministically. Use when the user says "how urgent is this", "what's the priority", "rank by criticality", "what will…
Ranks the likely failure modes for a fault against the failure-mode library, symptoms, alarm codes and repeat-failure history, deterministically. Use when the user says "what's the likely cause", "rank the failure modes", "diagnose this fault", "is this the…
Reads maintenance fault notes, operator reports, alarm/event logs, asset IDs and location into the mfg.maintenance-triage.v1 contract inputs. Use when the user says "triage this fault", "work this breakdown", "read the fault note for <asset>", "what's wrong…
Retrieves the asset's maintenance history — prior work orders, similar failures, PM records — and the relevant OEM manual and troubleshooting sections, and attaches them to the mfg.maintenance-triage.v1 contract. Use when the user says "pull the history for…
Repository README source: README.md
Read the source README