microsoft/cat-agent-skills

Skills for modern agents in Copilot Studio

About the project

microsoft/cat-agent-skills is a static website that catalogs reusable instruction sets and related packages for AI agents. People use it to search, filter, rate, and download skills for Cowork, Copilot Studio, and Scout, along with Copilot plugins and Scout automations. The catalogue entries are the skills, instructions, plugins, and settings displayed by the site.

This repository also configures its own agents. See what cat-agent-skills tells them →

93Stars on the repository
194Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

Use this skill when someone wants to connect a Model Context Protocol (MCP) server to a Microsoft Copilot Studio agent, is reviewing an MCP server before a rollout, or is debugging why a tool never appears in the agent, why the input schema came back truncated, or why a connection fails. Trigger on requests like "can…

not rated 93 +4 changed 20d ago A 145 tokens original MIT

study-flashcards

98

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

Use this skill whenever the user provides source material (notes, slides, a document, a PDF, pasted text, or a web page) and asks to "create a guide based on this", make a study guide, make flashcards, turn it into a quiz, "quiz me on this", or otherwise study from that material. Produces source-grounded flashcards…

not rated 93 +4 today A 136 tokens original MIT

qr-code-builder

99

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

Use this skill whenever the user asks to "make a QR code", "create a QR code", "QR code for this link/website", "QR code with my logo", "branded QR code" or "Wi-Fi QR code". Guided walkthrough that builds a scannable QR code (PNG, SVG, PDF, JPG, WEBP) with a bundled Python script. Only the web address is required…

not rated 93 +4 today A 176 tokens original MIT

inbox-triage

100

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

Use this skill whenever the user asks to clean up, triage, declutter, or archive low-value Outlook inbox mail - "clean up my inbox", "triage my mail", "declutter my inbox", "sort out newsletters", "archive old resolved threads", "/inbox-triage" - to group only newsletters, auto-notifications, past-event meeting…

not rated 93 +4 today A 160 tokens original MIT

kql-grounded-queries

101

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

Use whenever the user asks for a KQL query for Microsoft Sentinel, Log Analytics or Defender XDR Advanced Hunting — writing one, fixing one, modifying one, or explaining one — including requests that never say "KQL" (for example "query SigninLogs", "hunt for phishing URLs in Defender", "write a Sentinel detection").…

not rated 93 +4 today A 108 tokens original MIT

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

Fill a Word (.docx) template from structured data and return the finished document with its branding intact. Placeholders, blanks and content controls are replaced with values, optional sections are removed, and table rows repeat per input item. Use when the user supplies a .docx template plus data and asks to fill…

not rated 93 +4 today A 78 tokens original MIT

evidence-gather

103

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

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.

not rated 93 +4 today A 58 tokens original MIT

gap-check

104

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

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 gapcheck engine. Use when the user says "are we ready for the audit", "check for gaps", "will we pass", or after evidence-gather in a readiness run.

not rated 93 +4 today A 69 tokens original MIT

readiness-pack

105

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

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.

not rated 93 +4 today A 57 tokens original MIT

scope-map

106

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

Maps the audit scope to the standard's clauses and required evidence types with the deterministic clausemap 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.

not rated 93 +4 today A 55 tokens original MIT

contradiction-flag

107

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

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.

not rated 93 +4 today A 45 tokens original MIT

insight-brief

108

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

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".

not rated 93 +4 today A 42 tokens original MIT

provenance-check

109

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

Checks usage rights, geography and expiry for every retrieved study against the declared use - the explicit Govern step - with the deterministic provenancecheck engine. Use on "can we use this externally", "is this stat cleared for the board deck", after trend-compare.

not rated 93 +4 today A 57 tokens original MIT

research-retrieve

110

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

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 ", "find prior research on", "have we studied this before", or an insight request begins.

not rated 93 +4 today A 55 tokens original MIT

trend-compare

111

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

Compares trends across markets and periods like-for-like with the deterministic trendcompare engine. Use on "how has this trended", "compare markets", "what changed since the last study", after research-retrieve.

not rated 93 +4 today A 47 tokens original MIT

context-assemble

112

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

Assembles customer, order, loyalty and carrier context, detects record-vs-account contradictions, and selects the resolution path deterministically with the contextassemble engine. Use after inquiry-intake, or on "pull up everything on this order".

not rated 93 +4 today A 53 tokens original MIT

handoff-packet

113

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

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".

not rated 93 +4 today A 61 tokens original MIT

inquiry-intake

114

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

Takes the customer inquiry from any channel and classifies intent against the taxonomy with the deterministic intentclassify 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 in stock", "how do I set this up".

not rated 93 +4 today A 71 tokens original MIT

knowledge-retrieve

115

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

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".

not rated 93 +4 today A 42 tokens original MIT

resolution-draft

116

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

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".

not rated 93 +4 today A 42 tokens original MIT

bom-impact

117

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

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 analysis", or after ecr-ingest in a change run.

not rated 93 +4 today A 66 tokens original MIT

ecn-draft

118

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

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.

not rated 93 +4 today A 54 tokens original MIT

ecr-ingest

119

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

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 ", "what does this change touch", or when an engineering-change run begins.

not rated 93 +4 today A 65 tokens original MIT

standards-check

120

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

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.

not rated 93 +4 today A 54 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: