Official skills · page 8

Skills published by Anthropic and by the companies behind the tools they cover, such as Vercel, Cloudflare, Stripe, Supabase and Hugging Face.

649 skills · showing 337–384

Agent Performance Triage

110

microsoft/cat-agent-skills

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 and someone asks why resolution or engagement is low, why users escalate or abandon, what the top unanswered questions are, how to improve an agent's containment or CSAT, or wants a post-launch review, health check or optimization sprint for a deployed agent.

AI, LLMs & Agents122

Agent Rai Impact Assessment

110

microsoft/cat-agent-skills

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. Works from the agent's use case, design, tools, data flows, and evaluation evidence to identify affected people, benefits, harm scenarios, authority boundaries, mitigations, residual uncertainty, and the human decisions still required. Not a generic security audit, automatic compliance certification, or authority to approve deployment.

AI, LLMs & Agents122

Agent Red Team

110

microsoft/cat-agent-skills

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 each one to a concrete Copilot Studio control. Use when someone asks to red team, pen test, adversarially test, jailbreak-test or security-review an agent, wants a prompt injection or data leakage assessment before go-live, or needs security sign-off and a risk report for an agent handling sensitive data.

Security122

AI Demo Assistant

110

microsoft/cat-agent-skills

Builds a scenario-driven content pack for a Microsoft 365 Copilot customer demo. From a customer name, line of business, and target personas, it proposes demo scenarios for operator approval, then generates fictional Word/PowerPoint/Excel example files plus an AI Demo Delivery Plan (persona roster with tenant-account mapping, email and Teams chat scripts, calendar meetings with agendas, a meeting transcript, and app-tagged Copilot prompt workflows grounded in the generated content). After approval it can OPTIONALLY seed the Office files into a customer-named OneDrive folder and optionally post

AI, LLMs & Agents122

AI First Process Redesign

110

microsoft/cat-agent-skills

Facilitates a zero-based AI-first process redesign session that helps a team reimagine an existing work process as AI-first. Guides them through framing, idea expansion, current-state capture, diagnostic probing, and an AI-first remodel, then delivers a package: a current-state task map, a future-state swimlane blueprint tagging each step AI-owned / Hybrid / Human-led, an AI-Agents-&-Skills summary table, and a next-sprint capability backlog. Weighs the full range of AI building blocks — process change, knowledge, tools, reusable skills, agents, connected agents — instead of defaulting to an a

AI, LLMs & Agents122

AI Rollout Education

110

microsoft/cat-agent-skills

Coordinates a phased AI rollout across schools, colleges, universities, trusts, districts, or an education ministry: staff cohorts, prerequisites, role-based learning paths mapped to professional development windows, communications, support readiness, and wave gates checked against the academic calendar, with state carried between waves. Use when the user asks to "plan our AI rollout", "set up the training cohorts", "are we ready for the next wave", "what training does this role need", or "how is the rollout tracking". Do NOT use for any learner- or student-facing enablement wave, which is alw

Learning & Education122

AI Usecase Assessment

110

microsoft/cat-agent-skills

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 `*_AI_UseCase_Assessment_Report_*.html` and ask you to assess, strengthen, score, or refresh it. Invoke BEFORE writing any assessment content and BEFORE generating any report.

AI, LLMs & Agents122

Analyze Related Contracts

110

microsoft/cat-agent-skills

Analyzes how a set of contracts relate and produces a Related Contracts Report: which document amends, restates, replaces or terminates which, the effective sequence, and the currently operative version of each key term with its governing clause. Read-only on sources. Use when the user asks "how do these contracts relate", "which amendment is currently operative", "build a related contracts report", "map this contract family", "which version of this term applies now", or supplies amendments, restatements, SOWs, variations or novations and asks what is still in force. Do NOT use for one agreeme

Marketing, Sales & Business122

Anonymised Case Study Writer

110

microsoft/cat-agent-skills

Use this skill when the user asks to create, improve, anonymise, structure, or publish a client case study, success story, engagement summary, or transformation story.

Writing & Content122

Answer Draft

110

microsoft/cat-agent-skills

Drafts the cited floor answer for the associate - or the shift-lead escalation when the payload is out of scope or below confidence - from the completed rtl.store-associate-assist.v1 payload, using the answer template. Use to close every assist run: "draft the floor answer", "write up the answer for the associate", "close out the assist run", "draft the escalation to the shift lead", "what can I tell the customer". Do NOT use for a new question with no resolved payload - use question-intake instead; not to compute eligibility - use policy-retrieve or promo-check; never send, post or execute an

Marketing, Sales & Business122

Answer Research

110

microsoft/cat-agent-skills

Researches a bounded, source-backed answer to a support, policy, eligibility, or troubleshooting question, with citations and explicit evidence gaps. Use when a support, policy, eligibility, informational, or troubleshooting question needs a bounded, source-backed investigation that reconciles authority, applicability, currency, contradictions, and source coverage. Triggers include "research this answer," "what does the guidance support," "reconcile these sources," and "does this customer appear eligible." Do not use merely to compose a reply after the answer is established.

Research & Science122

Appeal Draft

110

microsoft/cat-agent-skills

Drafts the level-appropriate appeal letter from the cited policy clause and chart evidence already on the contract, with the deadline status in the header. Use when asked to "draft the appeal letter", "write the appeal for this denial", "put together our response to Contoso", "redraft this appeal on the original code". Use after evidence-assemble and deadline-track. Do NOT use to classify a new denial or "start an appeal" from a remittance - use denial-classify instead; do NOT use to gather evidence - use evidence-assemble instead; do NOT use to find policy - use policy-retrieve instead; do NO

Data & Analytics122

Artifact Assemble

110

microsoft/cat-agent-skills

Retrieves and normalizes raw closeout sources (deliverable register, decision log, retrospective notes, confidentiality terms) into a cited engagement.json draft in the shared closeout contract. Use at the start of a closeout harvest when the user says "close out the engagement", "assemble the final deliverables", "load the decision log", "bring in the retrospective", "pull the confidentiality terms" or "gather the closeout artifacts". Do NOT use for scoring assets (use asset-identify), clustering lessons (use lesson-cluster), confidentiality or clearance (use sanitize-check), drafting the rec

Marketing, Sales & Business122

Assertion Map

110

microsoft/cat-agent-skills

Maps each deliverable assertion to the support pack with the deterministic assertion_map engine and reports its support status. Use after intake and criteria, or when the user asks "what is not substantiated?", "check the claims", "trace this saving", "which assertions lack evidence?" or "map assertions to evidence". Do NOT use for ingesting documents (use deliverable-ingest), choosing criteria (use criteria-retrieve), gate findings or review status (use gate-check), drafting the partner packet (use review-packet), time or expense narratives (use time-expense-narrative-compliance), closeout ha

Other122

Asset Identify

110

microsoft/cat-agent-skills

Scores candidate reusable assets and checks final-deliverable completeness with the deterministic asset_identify engine, after artifact-assemble has produced engagement.json. Use when the user asks "what can we reuse from this?", "find reusable assets", "shortlist closeout assets", "is the final deliverable package complete?", "score the reuse value" or "build the final deliverable index". Do NOT use for loading sources (use artifact-assemble), clustering lessons (use lesson-cluster), deciding if an asset is safe to share (use sanitize-check; a score is never clearance), drafting the record (u

Other122

Attribute Normalize

110

microsoft/cat-agent-skills

Maps supplier product fields to the retailer taxonomy through the mapping table only, converts units with the calculation shown, and validates every GTIN check digit (GS1). Use after source-ingest, or when the user says "map these to our taxonomy", "are these GTINs valid", "validate these GTINs", "check the GS1 check digit", "normalise the supplier attributes" or "which supplier columns are unmapped". Do NOT use for ad-hoc unit conversions or non-product data - answer in chat instead; do NOT use for completeness or missing fields - use completeness-score instead; do NOT use for claim wording -

Writing & Content122

Audit Evidence Package

110

microsoft/cat-agent-skills

Maps auditor or reviewer requests to supporting evidence, summarizes what each document proves, and makes missing support visible before review rather than during it. Produces a request-by-request package with an evidence index and a gap list. Use when the user asks to "build the audit evidence package", "map these PBC requests to support", "what support are we missing for the auditors", "prepare for the audit walkthrough", or "pull evidence for this request list". Do NOT use for performing the audit or issuing an opinion, ledger or subledger reconciliation, or interpreting accounting standard

Finance & Crypto122

B2b Outreach Suite

110

microsoft/cat-agent-skills

A complete B2B sales outreach toolkit for agentic sales solutions. Use this skill whenever the user wants to research a prospect or build an account briefing, create cold emails or first-contact emails, LinkedIn/social DMs and connection messages, plan a follow-up sequence or outreach cadence, write B2B ad copy (social posts, ads, flyers, headlines, out-of-home), or needs to answer a prospect's objection (e.g. "no budget", "we already have a vendor", "too expensive", "send me some material"). Also use it when the user is building or configuring an agentic B2B sales/outreach workflow and mentio

Marketing, Sales & Business122

Bench Query

110

microsoft/cat-agent-skills

Normalizes bench, availability, rate and conflicts-register data into bench_candidates[] and constraints[] after role-intake, keeping every record and its citation without deciding fit or eligibility. Use when the user says "check the bench", "who is available?", "pull the roster", "include rates" or "load the conflicts extract". Do NOT use for job postings or recruiting copy, extracting roles from a SOW (use role-intake), fit scores (use fit-score), eligibility or conflict verdicts (use constraint-check), drafting the slate (use slate-draft), or for sales segmentation, general rate analysis o

Marketing, Sales & Business122

Blog Content Auditor

110

microsoft/cat-agent-skills

Use this skill when the user asks to audit, review, score, rationalise, prioritise, refresh, or improve blog posts, article libraries, newsletters, or thought-leadership content.

Writing & Content122

Blog Post Structure Pass

110

microsoft/cat-agent-skills

Use this skill when the user asks to restructure, reorganise, improve, rewrite, tighten, or strengthen a blog post, article, newsletter, essay, or thought-leadership draft.

Writing & Content122

Booth Loop Video

110

microsoft/cat-agent-skills

Use this skill whenever the user asks for a looping booth, kiosk, trade-show, lobby-screen, or silent background video — including requests phrased as "a video loop for our stand", "an animated explainer with no voiceover", "a motion graphic for the monitor", or "turn this pitch into a looping MP4". Generate and run a self-contained Python render script (Pillow + ffmpeg) that outputs a 1920x1080 30fps MP4. Do NOT use this skill for videos that need narration, live footage, or editing of an existing video file.

Images, Video & Audio122

Borrower Prospect Research

110

microsoft/cat-agent-skills

Build a sourced public-record background brief on a commercial borrower or prospect, with entity identity, jurisdiction, retrieval date, and search limits. Use when the user says "what do we know about this company", "run background on this borrower", "pull public records on Acme", "who owns this business", or "any liens or litigation on this prospect". Do NOT use for financial spreads — use financial-statement-spread instead. Do NOT use for relationship-history call prep — use rm-call-prep-followup instead. Do NOT use for standalone covenant tests — use covenant-compliance-check instead. Do N

Research & Science122

Brand Template Enforcer

110

microsoft/cat-agent-skills

Applies bundled or SharePoint-hosted organization-approved PowerPoint and Word templates whenever the agent is about to create, generate, export, or substantially rebuild a presentation, slide deck, report, proposal, brief, memo, letter, or other .pptx, .docx, or .dotx deliverable. Use before any file-generation tool or document-creation skill so the output starts from the appropriate brand template instead of a blank file. Do not use for read-only analysis or minor edits that do not create a new Office file.

Frontend & Design122

Brand Voice Pass

110

microsoft/cat-agent-skills

Use this skill when the user asks to rewrite, humanise, de-AI, polish, localise, or align draft text to a brand voice, house style, named audience, or writing profile.

Frontend & Design122

Breathing Room

110

microsoft/cat-agent-skills

Show the user where their own week has room to breathe and where it does not, from their calendar, their sent mail and their sent Teams messages. Use this skill when the user asks how their day or week looks, whether they are overloaded, where their free blocks are, whether they still have deep-work time, how much they are working outside hours or at weekends, what the coming week already looks like, or - when they ask - which meetings are the most movable. It recognises time off and does not flag or count leave. Runs in three scopes - today, week, ahead. This skill only ever looks at the user

Productivity & Notes122

Brief Draft

110

microsoft/cat-agent-skills

Drafts the store readiness checklist, the shift brief in store language, and the exception escalation for a promotion launch from the ranked contract payload — draft-first, nothing sent. Use to close every execution run — "draft the shift brief", "write up the readiness pack", "build the launch checklist for store <id>", "what does the team do each shift", "write the escalation for the district manager". Do NOT use for field-sales store visit reports or action registers — use visit-report instead; not for the readiness test or ranking — use readiness-check instead for the test, use exception-r

Productivity & Notes122

Browser Uat Analyst

110

microsoft/cat-agent-skills

Use this skill whenever the user asks to test, validate, UAT, regression-check, or investigate the behaviour of a browser-based application — including Copilot Studio agents, Power Platform apps and flows, Dataverse, Dynamics 365, Microsoft 365 admin centres, Teams web, and custom web apps. Covers test charter design, Playwright-driven execution, screenshot evidence capture, expected-vs-observed analysis, and stakeholder reporting. Use it BEFORE claiming any UI behaviour works or is broken. Do NOT use this skill for unit tests, API-only contract tests, or load testing.

Testing & QA122

Budget Consolidation

110

microsoft/cat-agent-skills

Runs a budget or planning cycle: tracks which cost centers have submitted, drafts chase messages for the ones outstanding, consolidates returned templates into one view, flags variance against target or prior year, and assembles a decision packet. Use when the user asks "who hasn't submitted their budget", "chase the outstanding cost centers", "consolidate the budget submissions", "roll up the plan templates", or "build the budget decision packet". Do NOT use for building one cost center's budget model (use xlsx), explaining actuals against plan (use variance-commentary), or valuation modeling

AI, LLMs & Agents122

Build Case Chronology

110

microsoft/cat-agent-skills

Builds a dated, source-cited chronology of factual and procedural events from supplied case papers, with date flags, evidence pinpoints and mandatory Assumptions & Discrepancies and Coverage sections. Read-only on sources; it never assesses merits, liability or limitation. Use when the user asks to "build a case chronology", "create a litigation timeline", "prepare a chronology for this dispute", "list the procedural deadlines in this matter", or "work out who did what and when across these papers". Do NOT use for contractual obligations and deadlines taken from an agreement — use extract-obli

Research & Science122

Business Case Composer

110

microsoft/cat-agent-skills

Builds a customer-specific business-case draft connecting the problem, cost of inaction, proposed solution, investment, and supported value. Use when a customer-specific deal or initiative needs a decision-ready qualitative or quantitative business case, such as "draft a business case", "build the value case", or "justify this initiative". DO NOT use for generic product pitches or price and discount quotes.

Marketing, Sales & Business122

Business Os

110

microsoft/cat-agent-skills

Turns vague or complex business requests (decisions, problems, projects, incidents, processes, ideas, documents, communications) into a clear outcome, an appropriately sized plan, and a verified result. Also assesses whether repeated work should become a reusable Skill and can draft that Skill package. Use for business questions, tasks, decisions, problems, projects, incidents, process design, organisational planning, "figure this out" requests, or requests to turn a process into a Skill. Do not use for casual conversation, trivial rewrites, or work already covered by a more specific installed

Marketing, Sales & Business122

Call for Speakers Digest

110

microsoft/cat-agent-skills

Weekly digest of open conference Call for Speakers (CFP) opportunities matching the person's topics of interest, delivered as an HTML email. Use this skill when someone asks to be notified about speaking opportunities, wants a recurring CFP digest, asks "what conferences are taking submissions right now", or wants to set up a weekly speaker opportunity search. Also use on the skill's own recurring weekly run to refresh the digest, and when the person wants to update their topics, location or format preferences, or exclude a conference they're already committed elsewhere for.

Productivity & Notes122

Campaign Deck Builder

110

microsoft/cat-agent-skills

Use this skill whenever the user wants to create a marketing-campaign presentation, pitch deck, or launch deck for a brand. Ask the campaign questions, then run the bundled script to fill the template into a finished .pptx.

Marketing, Sales & Business122

Case Packet

110

microsoft/cat-agent-skills

Drafts the return case packet - determination, recommendation, evidence list, fraud signals, customer response draft, manager exception request - from the governed contract payload using the packet template. Use to close every return case: "build the case packet", "write up the return", "draft the customer response", "draft the manager exception request", "close the return case". Do NOT use to start a case - use return-intake instead; not for eligibility or red flags - use eligibility-check; not for incident or safety write-ups.

Marketing, Sales & Business122

Case Preparation Brief

110

microsoft/cat-agent-skills

Builds a decision-ready brief on one support issue, covering status, material history, open commitments, and the recommended next step. Use before the next interaction or action on one case, incident, ticket, customer issue, request, or complaint — reconciling what's happened, what's still open, and what to do next, even from a single description or one substantive interaction with no full record yet. Examples include "brief me on this case", "prepare this case handoff", and "what is still open on this complaint". Do not use to rank several issues, compose the outbound customer reply, or close

Marketing, Sales & Business122

Case Triage

110

microsoft/cat-agent-skills

Ranks support issues into an explainable work order based on impact, deadlines, commitments, and evidenced urgency. Use when two or more tickets, incidents, issues, requests, or complaints need an explainable relative work order based on impact, deadlines, commitments, staleness, unanswered contact, documented urgency, and any available priority or response-time evidence. Also supports a bounded urgency assessment for one issue without inventing a queue rank. Examples include "rank these cases", "which complaint should be first", and "how urgent is this issue". Do not use for a deep brief on o

Other122

Chart Builder

110

microsoft/cat-agent-skills

Use this skill whenever the user asks to visualize, chart, plot, or graph data (bar, line, scatter, histogram, pie) from a CSV, table, or DataFrame. It gives the agent prebuilt, parameterized matplotlib functions so charts are produced faster and more reliably — with consistent styling and sane defaults — instead of hand-writing matplotlib each time.

Data & Analytics122

Check Cross References

110

microsoft/cat-agent-skills

Checks every internal cross-reference in a supplied legal document against an index of its actual clause, schedule, annex and exhibit numbering, and reports each outdated, missing, mislabelled, ambiguous or unverifiable reference with a quoted citation plus suggested wording for the mechanical fixes. Use when the user asks to "check the cross-references in this agreement", "are the clause references in this contract still correct?", "find broken or outdated internal references in this document", or "which references can't be verified without the other agreements?". Do NOT use for undefined, du

Marketing, Sales & Business122

Check Defined Terms

110

microsoft/cat-agent-skills

Audits the defined term machinery of a supplied legal document — terms used but not defined, defined but not used, defined twice, used inconsistently, or resting on an undefined term — reporting each defect with a quoted citation to its clause, then suggested wording the user applies. Read-only. Use when the user asks to "check the defined terms in this NDA", "any duplicate definitions?", "is Confidential Information used consistently?", "find any terms used but not defined in this agreement", or "is anything defined but never used?". Do NOT use for broken clause, schedule or annex references

Finance & Crypto122

Check Execution Readiness

110

microsoft/cat-agent-skills

Read-only check of whether a legal document is complete enough to sign: party names and roles, execution and effective dates, signature blocks, and unresolved drafting such as blanks, placeholders, TBD markers and open tracked changes. Gives one position plus a Finding / Location / What is needed table, and never proposes wording. Use when the user asks "is this ready to sign", "run an execution readiness check", "check the signature blocks", "are there any blanks left in this agreement", or "can we execute this today". Do NOT use for a defined term or cross-reference audit — use check-defined

Finance & Crypto122

Cim Teardown

110

microsoft/cat-agent-skills

Tears down a confidential information memorandum or management presentation: extracts the financials into a usable model input, separates disclosed fact from seller framing, identifies adjustments and add-backs that need challenge, and produces a diligence question list. Use when the user asks to "tear down this CIM", "extract the financials from this deck", "what should we challenge in this memorandum", "review the management presentation", or "build diligence questions from the CIM". Do NOT use for the investment recommendation — use ic-memo instead; a multi-document data room review — use d

Finance & Crypto122

Claim Check

110

microsoft/cat-agent-skills

Validates product marketing claims and regulated terms in supplier copy against the approved claim library for that GTIN and market - the explicit Govern step. Use after completeness-score, or when the user says "is this copy safe", "can we say antibacterial", "check the claims", "validate the marketing claims", "is this regulated wording allowed in <market>" or "do we have substantiation for <claim>". Do NOT use for trade-deduction, invoice or insurance claims - use claim-ingest / claim-match instead; do NOT use to approve or add a claim to the library - that is the claim owner's decision; do

Writing & Content122

Classic Text Adventure

110

microsoft/cat-agent-skills

Play and operate a deterministic, resumable Colossal Cave text adventure with verbatim game output and an OOC escape. Use when a user asks to start, continue, inspect, reset, or smoke-test the Classic Text Adventure; treat unprefixed messages as game commands while a session is active.

Testing & QA122

Clipchamp Video

110

microsoft/cat-agent-skills

Create narrated demo/explainer videos of a live web app or agent, with real screen-flow footage under an AI (Ava neural) voiceover. Use whenever the user wants to "make a video", "record a demo", "create a walkthrough", "screen record an agent/app and narrate it", "build a Clipchamp video", "produce a product demo", or turn a Copilot Studio / web-app flow into a narrated MP4. FIRST ask the user which assembly method to use: (A) headless ffmpeg + edge-tts Ava — fast, scripted, produces a finished MP4 directly — or (B) the Clipchamp web UI — slower, but leaves an editable Clipchamp project for h

Images, Video & Audio122

Close Status Digest

110

microsoft/cat-agent-skills

Builds a situational-awareness digest for a financial close cycle by aggregating email and chat signal into what has landed, what is in flight, what is blocked, and what is at risk, then calling a top-line status of on-track, at-risk, or slipping with owners and unblock paths. Use when the user asks "where are we on close", "what's blocking month-end", "give me the close status", "are we on track for close", or "what's at risk this close". Do NOT use for preparing journal entries, accruals or reconciliations, post-close variance narrative (use variance-commentary), or ordinary non-close daily

Productivity & Notes122

Clt Hr Assistant

110

microsoft/cat-agent-skills

Responde dúvidas de legislação trabalhista brasileira (CLT) para equipes de RH/DP e calcula verbas rescisórias com memória de cálculo completa, usando as tabelas oficiais vigentes (salário mínimo, INSS e IRRF, incluindo a Lei 15.270/2025).

Marketing, Sales & Business122

Code Map

110

microsoft/cat-agent-skills

Maps drafted time entries to the client phase and task codes with the deterministic code_map engine and flags submitted-code mismatches with citations; it recommends codes only. Use it after narrative-draft and before guideline-check when the user asks "what code should this entry use?", "map my time to billing codes", "is this task code wrong?", "check my phase and task codes" or "recommend phase codes for my entries". Do NOT use for gathering activity (use activity-pull), narrative wording (use narrative-draft), overall compliance or rejection risk (use guideline-check), recoding entries in

Software Development122