claude

microsoft-365-copilot

Name: microsoft-365-copilot
Author: Matt Corbett

Microsoft 365 Copilot extensibility & administration team — agents (copilot-extensibility-architect, declarative-agent-engineer, graph-connector-engineer, api-plugin-engineer, agents-sdk-engineer, copilot-admin-governance) covering declarative agents (pinned manifest schema + the 50/25/4096/45s hard-limit wall), custom-engine agents on the M365 Agents SDK/Toolkit, Copilot (Graph) connectors (synced vs federated/MCP, semantic labels, ACL trimming), API plugins (OpenAPI + Entra/OAuth2), the app-package publish lifecycle, and M365 Agent Registry + Purview DLP-for-Copilot governance. citation-grounded knowledge bank (two Mermaid decision trees), skills, templates, an advisory hook (house opinions). Disjoint from power-platform's Copilot Studio low-code coverage (cross-linked). Seams: Copilot Studio → power-platform; CEA engine → claude-app-engineering; Entra/hosting → azure-cloud; security → ravenclaude-core. Requires ravenclaude-core@>=0.7.0.

9 on GitHubby Matt Corbettv0.5.10MITupdated today

Plugin microsoft-365-copilot from marketplace ravenclaude in mcorbett51090/RavenClaude. Commands read from the repo's manifest — today.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (5)

api-plugin-openapi-hygiene
Make a REST API safe and correct to expose as a Microsoft 365 Copilot API plugin — lay out the four files (app manifest + plugin manifest + OpenAPI + adaptive cards), verify the plugin-manifest↔OpenAPI `operationId` mapping both ways, respect the OpenAPI-for-Copilot subset, write model-readable oper
copilot-agent-eval-harness
Build the golden-prompt regression set + pre-publish evaluation gate for a Microsoft 365 Copilot agent — author representative + adversarial prompts, check grounding accuracy and citation correctness, stress the declarative-agent hard limits (50/25/4096/45s, no-loop), and gate publish on the results
copilot-connector-schema-design
Design a Microsoft 365 Copilot (Graph) connector schema — choose synced vs federated (MCP), declare property attributes (searchable/queryable/retrievable), apply the mandatory semantic-label map (title/url/createdBy/...), ingest ACLs for per-user trimming, and plan crawl/refresh + semantic-index lat
declarative-agent-manifest-authoring
Author and review a Microsoft 365 Copilot declarative-agent manifest — pin the schema version (v1.8), keep instructions within the ~8,000-char budget, declare only the needed capabilities, write scope-demonstrating conversation starters, wire API actions, and pass manifest + Responsible-AI validatio
oversharing-remediation-playbook
Remediate Microsoft 365 oversharing BEFORE enabling Copilot — assess the blast radius, then run the sequence (RCD/RSS reach-reduction → Purview sensitivity labels + DLP-for-Copilot → site/permission cleanup → enable), framing RSS/RCD as reach-reduction and NOT a security boundary, with owners, verif

Slash commands (5)

/microsoft-365-copilot:build-declarative-agent
Build a Microsoft 365 declarative agent — pinned manifest schema, instructions kept in-manifest under the 8K budget, minimal scoped capabilities, designed to ~66% of every hard limit, and gated on RAI + a golden-prompt regression set.
/microsoft-365-copilot:build-graph-connector
Build a Microsoft 365 Copilot (Graph) connector — choose synced vs federated for the right reason, semantic-label every schema property, ingest real per-item ACLs (never "everyone"), and set crawl/refresh to the source's change rate.
/microsoft-365-copilot:design-copilot-extensibility
Decide how to extend Microsoft 365 Copilot — traverse the declarative vs custom-engine vs Copilot-Studio decision, pick the grounding source (synced/federated connector vs SharePoint knowledge vs API plugin), and name the host/engine seams.
/microsoft-365-copilot:remediate-copilot-oversharing
Plan the pre-Copilot oversharing remediation — run the RCD/RSS to Purview to permission-cleanup to enable sequence in order, treat RSS/RCD as blast-radius reduction (not a security boundary), and route the verdict to the security reviewer.
/microsoft-365-copilot:scaffold-api-plugin
Scaffold a Microsoft 365 Copilot API plugin from an OpenAPI spec — choose the auth scheme from the identity model (never embed a secret), map operationId both ways, and mark every state-changing action consequential with security_info attestation.

Subagents (6)

agents-sdk-engineer
Use this agent to build a Microsoft 365 CUSTOM-ENGINE AGENT on the M365 Agents SDK (the Bot Framework SDK successor) and the Agents Toolkit (`atk`, the Teams Toolkit successor, with the Playground) — channel/turn/state management, streaming + citations, proactive/autonomous behavior.
api-plugin-engineer
Use this agent to turn a REST API into a Microsoft 365 Copilot API PLUGIN / action — the four-file architecture (app + plugin manifest + OpenAPI + adaptive cards), the `operationId` mapping, and Entra OAuth2 / API-key auth.
copilot-admin-governance
Use for Microsoft 365 Copilot ADMINISTRATION & GOVERNANCE — Agent Registry lifecycle, MCP-tool approval, app-package publish, Copilot/PAYG licensing, Purview DLP, oversharing remediation, and data residency. NOT for the agent build (the engineers) or the ACL/DLP verdict (security-reviewer).
copilot-extensibility-architect
Use this agent to choose HOW to extend Microsoft 365 Copilot — declarative vs custom-engine agent vs (the seam) Copilot Studio; which grounding source (synced/federated connector vs SharePoint knowledge vs API plugin); NOT for authoring the manifest (declarative-agent-engineer).
declarative-agent-engineer
Use this agent to author or review a Microsoft 365 Copilot DECLARATIVE AGENT — the pinned-schema manifest (currently v1.8), ~8,000-char instructions, capabilities, conversation starters, and API actions, plus manifest + Responsible-AI validation and the Agent Builder vs Agents Toolkit choice.
graph-connector-engineer
Use this agent to design and build a Microsoft 365 Copilot (Graph) CONNECTOR — synced (indexed, semantic-ranked, ACL-trimmed) vs federated (real-time over MCP, no index); NOT for choosing grounding source vs an API plugin (copilot-extensibility-architect / api-plugin-engineer).

MCP servers (1)

microsoft-learn
connects to: https://learn.microsoft.com/api/mcp

Hooks (1)

PostToolUse
/usr/bin/env -u BASH_ENV -u ENV -u SHELLOPTS -u BASHOPTS -u LD_PRELOAD -u LD_LIBRARY_PATH -u LD_AUDIT -u DYLD_INSERT_LIBRARIES -u DYLD_LIBRARY_PATH -u PYTHONPATH -u PYTHONSTARTUP PATH=/usr/local/bin:/

View source on GitHub mcorbett51090.github.io

More from mcorbett51090/RavenClaude

All 184 plugins →

RavenClaude Core

claude

Domain-neutral Claude Code foundation: specialist agents, skills, gates, hooks, rules, templates. Capability Grounding Protocol, Structured Output Protocol, Researcher meta-skill, comfort-posture dashboard, opt-in command-review tribunal (the Thing), WebFetch sanitizer, branch-archive escape hatch, brand-extraction (homepage → brand kit), /wireframe (describe anything → validated model + high-fi Artifact + Mermaid), Problems & Resolutions view, declarative-visualization (Vega-Lite/Deneb/SVG, Gate 101 + Gate 103 svg-report-lint, viz-spec-reviewer), and Claude orchestrator escape hatch (/claude-orchestrate). Slash commands: /init-agent-ready, /wrap, /set-posture, /dashboard, /forge, /wireframe, /reset-plugin-cache, /handoff.

70 skills · 14 commands · 18 agents · hooks

power-platform

claude

Power Platform specialist team — agents (incl. power-platform-tester, power-bi-engineer) and skills, with strong ALM/git coverage for solutions, flows, and PBIP. A house-opinions hook flags 8 §3/§4 violations; the knowledge bank carries production decision trees (PA-flow recovery, Dataverse token-acquisition, PCF React surface, PBI deploy/refresh, custom-connector build-path, PBIR Enhanced infinite-spinner debug + full build reference, DAX silent-zero scoring via the `Domain` pattern, sempy.fabric notebook reference, Power BI Copilot report-readiness, Code Apps connector gotchas, PBIP deployment variables + #839, PBIR reference enrichment, PBIP report fast-solve triage router [MCP-optional], main-forms-are-Web-API-authorable grounding) plus a real-engagement scenarios bank. Bundles the community pbix-mcp server (d0nk3yhm/pbix-mcp, MIT) for .pbix/.pbit read/write/DAX-eval (`pip install pbix-mcp`); documents (not bundles) the official Microsoft Dataverse MCP (CLAUDE.md §9a). Extends ravenclaude-core.

24 skills · 8 commands · 11 agents · 1 MCP server · hooks

finance

claude

Corporate finance & FP&A specialist team — FP&A analyst (budgets, forecasts, variance commentary), financial modeler (3-statement, DCF, scenarios), controller (close, JEs, reconciliations), treasury analyst (cash, covenants, FX), valuation analyst (DCF + comps + precedent), audit-prep specialist (PBC, walkthroughs, SOC1/2 narratives), and board-pack composer. skills incl. a gold-standard NetSuite close (OAuth2 M2M + SuiteQL BS/IS trial balance, layperson runbook), templates, a knowledge bank (ASC 805 / 718 / 740, accrual-cutoff, WACC, cost accounting, FP&A operating model + decision support, NetSuite integration landscape), advisory hooks (hardcoded rates / plaintext PII / missing Sources / Assumptions; secrets-PII scan). Inherits ravenclaude-core protocols.

23 skills · 7 commands · 7 agents · hooks

web-design

claude

Web design & build specialist team — web architect (IA, stack, hosting), UX designer (wireframes, flows, conversion), visual designer (brand, typography, tokens), frontend implementer (HTML/CSS/JS, React, Astro, Next), content strategist (copy, microcopy, SEO content), accessibility auditor (WCAG 2.2 AA/AAA), and performance engineer (Core Web Vitals, image/font optimization). skills (the gold-standard-website-pipeline gated build pipeline, static-site build, design-system audit, card/tile UI, accessibility review, Core Web Vitals tuning, technical SEO audit, information architecture, conversion design, content audit, design-tokens scaffolding, third-party hygiene, Fluent UI v9 + React implementation), templates, an advisory hook, and a knowledge bank seeded with a curated 2026 reference set of "cutting edge yet simple" marketing-site donors — the design agents carry compact inline priors plus a pointer to the full brief. Inherits ravenclaude-core protocols.

19 skills · 7 commands · 7 agents · hooks · LSP

edtech-partner-success

claude

EdTech-flavored Partner Success Manager team — specialist agents anchored on the PSM lane, with skills, templates, an advisory hook, a knowledge bank with Mermaid decision trees, a engagement bank, and a stdlib psm_calc.py calculator (seat-utilization / renewal-NRR-forecast / time-to-value). Covers QBRs, success plans, health scores, a self-contained Power-BI-style partner-health report, onboarding, touchpoint logs, adoption sequencing, 90-day implementation arcs, train-the-trainer curricula, advocacy/reference pipelines, renewal decision memos, and the integration contract for a centralized CS dashboard (Planhat + Salesforce + Snowflake + Zapier + Granola). Team growth ships as skills + knowledge + templates, not parallel agents. Primary-source citations with retrieval dates. Vertical-explicit but segment-agnostic — fits K-12, higher-ed, corporate L&D, or mixed EdTech books. Inherits ravenclaude-core protocols including the alternate-methods Capability Grounding Protocol.

17 skills · 5 commands · 6 agents · hooks

regulatory-compliance

claude

Financial-regulatory & compliance specialist team — function agents (AML/KYC, regulatory-reporting, risk-and-controls, policy & procedure, examination-prep, Bermuda-insurance) PLUS jurisdiction/regulator specialists: BMA financial-institutions (banking, trust, corporate-services, fund-admin, investment-business, money-service, digital-assets — the primary build-out, with deep AML/ATF + supervision/fees + licensing-classification trees), CIMA (Cayman), Bahamas, Channel Islands (Jersey JFSC + Guernsey GFSC), UK PRA, and US federal+state. primary-source-cited regulator knowledge files, best-practice rules, skills, templates, a defensive PreToolUse hook (PII scrub — SSN/IBAN/credit-card/Bermuda TIN/wire instructions). Positioning reflects field experience inside a Tier-1 financial regulator (BMA). Inherits ravenclaude-core protocols.

11 skills · 5 commands · 12 agents · hooks

Maintain microsoft-365-copilot?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins184 plugins