Microsoft Teams SDK dev plugin for Agents Store. TypeScript guidance for building Teams bots, message extensions, tabs, dialogs and AI agents on Teams SDK 2.1 and Teams Developer CLI 3. Vendors the official microsoft/teams-sdk skill (scaffold, bot registration, SSO setup) and adds skills for the App framework and turn state, Adaptive Cards, openai/MCP/A2A agents, Microsoft Graph, SSO with addOAuthFlow, deployment, sovereign clouds and the Agents Playground.
Plugin teams-dev from marketplace agents-store-claude-plugins in Agents-Store/claude-plugins. Commands read from the repo's manifest — today.
adaptive-cardsUse this skill when the user is building or sending Adaptive Cards from a Microsoft Teams bot on `@microsoft/teams.cards` 2.1 — `AdaptiveCard`, `TextBlock`, inputs with `.withId()`, `ExecuteAction` with `SubmitData`, routing `card.action.<action>`, input validation, pasting Designer JSON, search-as-
agents-playgroundUse this skill when the user wants to test or debug a Microsoft Teams bot locally on Teams SDK 2.1 — Microsoft 365 Agents Playground (`agentsplayground`), accepting unauthenticated local requests (`dangerouslyAllowUnauthenticatedRequests`), the "No credentials configured … all incoming requests will
ai-agentsUse this skill when the user is adding LLM behaviour to a Microsoft Teams bot on Teams SDK 2.1 — calling OpenAI or Azure OpenAI directly with the `openai` SDK and `runTools()`, streaming into Teams, tools as `RunnableToolFunction`, conversation history in turn state, clarification cards, AI labels,
api-referenceUse this skill on explicit request when the user asks for the Teams SDK 2.1 API reference — the `@microsoft/teams.*` packages and what each exports, `App` options, the handler context, activity routes, the `app.api` clients. Reference-only — does not auto-load.
authenticationUse this skill when the user is wiring authentication into a Microsoft Teams app on Teams SDK 2.1 — app credentials (`CLIENT_ID`/`CLIENT_SECRET`/`TENANT_ID`, managed identity), user sign-in with `app.addOAuthFlow()` (SSO or third-party OAuth), several connections, sign-in callbacks, Nested App Authe
cli-recipesUse this skill when the user is driving the Microsoft Teams Developer CLI 3.x (`teams`) from a script, a CI job or an agent — `teams login`, `teams project new typescript`, `teams app create|get|update|doctor`, manifest and RSC edits, `--json` output with jq, non-interactive flags. Triggers on "team
deploymentUse this skill when the user is deploying a Microsoft Teams bot built on Teams SDK 2.1 — runtime environment variables (`CLIENT_ID`, `CLIENT_SECRET`, `TENANT_ID`, `MANAGED_IDENTITY_CLIENT_ID`), managed identity and federated credentials, the messaging endpoint, install and sideloading, organisation
dialogsUse this skill when the user is building dialogs (task modules) in a Microsoft Teams bot on Teams SDK 2.1 — opening a dialog from a card with `OpenDialogData`, handling `dialog.open.<id>` and `dialog.submit.<action>`, returning an Adaptive Card or a web page, multi-step flows, dialogs opened from me
graph-integrationUse this skill when the user is calling Microsoft Graph from a Microsoft Teams app on Teams SDK 2.1 — `app.graph.call(endpoints…)` as the app, a `GraphClient` built from a user's OAuth token, `@microsoft/teams.graph-endpoints` parameters, beta endpoints, paging, permissions. Triggers on "Microsoft G
mcp-a2aUse this skill when the user is combining the Model Context Protocol or Agent2Agent with a Microsoft Teams bot on Teams SDK 2.1 — using a remote MCP server's tools in the agent, exposing the Teams bot as an MCP server (`find_user`, `notify`, `ask`, `request_approval`) with `@modelcontextprotocol/sdk
message-extensionsUse this skill when the user is building Microsoft Teams message extensions on Teams SDK 2.1 — search commands (`message.ext.query`), action commands (`message.ext.submit`, `message.ext.open`), link unfurling (`message.ext.query-link`), item selection, settings pages. Triggers on "Teams message exte
messagingUse this skill when the user is sending or receiving messages in a Microsoft Teams bot on Teams SDK 2.1 — handling incoming messages, `send`/`reply`/`quote`, `MessageActivityInput`, typing indicators, mentions, targeted (private) messages, quoted replies, streaming and its limits, proactive notifica
sdk-patternsUse this skill when the user is writing the core wiring of a Microsoft Teams app on Teams SDK 2.1 — booting `App`, credentials from the environment, per-turn state (`state`), activity routing (`app.on`, `app.message`, `app.event`), middleware (`app.use`, `next`), plugins, logging, or running the app
tabsUse this skill when the user is building a tab inside a Microsoft Teams app on Teams SDK 2.1 — serving a static page with `app.tab()`, calling the agent from the page with `@microsoft/teams.client` and `app.function()`, using TeamsJS (`@microsoft/teams-js`) for context and dialogs, acquiring tokens
teams-sdk-teams-devUse this skill whenever the user mentions Microsoft Teams in a development context — whether they're building, integrating, configuring, debugging, or just asking questions. Covers bots, message extensions, embedded web apps, Adaptive Cards, dialogs, SSO, infrastructure, the Teams Developer CLI/SDK,
troubleshootUse this skill when the user is debugging a Microsoft Teams bot built on Teams SDK 2.1 — "bot did not reply", "All incoming requests will be rejected", 401/403 from or to Teams, sideload and install errors, SSO sign-in failures, Adaptive Card or dialog problems, streaming and AI issues, manifest che
/teams-dev:add-featureAdd a feature (message handler, Adaptive Card, dialog, message extension, tab, AI agent, MCP server or client, A2A, SSO, Graph call, turn state) to an existing Microsoft Teams app on Teams SDK 2.1
/teams-dev:scaffoldScaffold a new Microsoft Teams bot, Graph bot or tab on Teams SDK 2.1 with the Teams Developer CLI 3
teams-developerUse this agent when the user needs help building a Microsoft Teams application in TypeScript or JavaScript with the Teams SDK 2.1 (`@microsoft/teams.*`) and the Teams Developer CLI 3 — bots, message extensions, tabs, dialogs, Adaptive Cards, AI agents on the `openai` SDK, MCP and A2A, Microsoft Grap
Google Workspace plugin powered by the official googleworkspace/cli (gws) Agent Skills. ~95 skills for Gmail, Drive, Calendar, Sheets, Docs, Chat, Meet, Tasks, Slides, Forms, Classroom and Admin — plus role personas and ready-made recipes — all driving the gws CLI. Vendored from upstream and auto-synced weekly. Requires the gws CLI (npm i -g @googleworkspace/cli) and a one-time OAuth setup.
96 skills
Plane Agile Ops knowledge plugin. Sprint planning, task decomposition, estimation, backlog management, velocity tracking, retrospectives, standups, intake triage, modules, epics, milestones, roadmaps, dependencies, burndown, and page publishing. Written for Plane MCP 0.3.0+ (resource tools with an action parameter, PQL filters, releases); a bootstrap skill discovers the tools across naming conventions and translates for older per-operation connectors.
16 skills · 44 commands · 2 agents · hooks
Vercel ecosystem dev plugin. Deployment, AI SDK, Edge Functions, storage, routing, performance optimization. CLI deploy troubleshooting for non-Git projects, Hobby plan fixes, standalone output handling, CMS deploy hooks. Based on official vercel-plugin v0.53.0 by Vercel Labs; telemetry is opt-in (VERCEL_PLUGIN_TELEMETRY=on).
40 skills · 4 commands · 3 agents · 1 MCP server · hooks
Day-two operations for a fleet of self-hosted OpenClaw gateway instances on one Docker host. Discovers every instance from the live Docker state instead of hard-coded paths, classifies it ok / degraded / down / alien, and drives the repair work: health and liveness reporting, provider-auth triage (expired, emptied and shadowed OAuth profiles, shared-credential token sink), config surgery with a snapshot and an executable rollback, memory and embedding repair, shared skills and plugins consolidation, secret-delivery audit by key name only, security audit, version-drift and channel-aware upgrades, and reference-instance cloning. Mutations are dry-run behind an eight-block plan, need --yes, and need a typed confirmation when irreversible. Secrets are reported as fingerprint, presence and expiry — never as values. No MCP server and no required environment variables: the one optional variable, OPENCLAW_OPS_CONFIG, is an escape hatch for the fleet-config path, and deployment specifics live in that operator-owned config outside the repository. Also carries the workspace persona guides (AGENTS.md, SOUL.md, USER.md, IDENTITY.md, standing orders, bootstrap, memory, session analysis) taken over from the retired openclaw-configurator.
22 skills · 11 commands · 2 agents · hooks
Sendpulse multi-channel marketing plugin. Manage chatbots (Telegram, WhatsApp, Instagram, Messenger, Viber, TikTok), CRM (contacts, deals, pipelines, boards, tasks), Courses (LMS) academies, courses and students, email campaigns, templates, addressbooks, and SMTP transactional email via 147 MCP tools.
11 skills · 15 commands · 2 agents · 1 MCP server
Turns what a client says into documents they can correct, a machine spec an agent can build from, and a work list somebody can pick up. Keeps the macstack/ folder of a project: macstack.json — the standardized business + technical stack specification, always English — and the six client documents it is written from. OVERVIEW says what the product is and who it is for; USER-CASES carries each case with its UX bar and an addressable acceptance list; UX-UI states what each screen shows and what must never appear on it; AUTOMATION is the trigger -> task -> workflow -> role model; HANDBOOK is how a person actually uses the thing; OPEN-QUESTIONS splits what the client owes from what the team deferred. v3 makes those six pure markdown — headings and bullet lists, nothing else. No YAML blocks, no tables, no change-log sections: the only machine markup is an HTML comment the reader never sees, pointing each entity at its place in the spec. A client can edit the document in any editor and hand it back. Around them: an immutable inbox for anything a client sends, a gated delta/rulings loop that merges it, generated requirements, architecture, test cases and index that carry every id the client documents carry, an append-only ledger with one row per edit and per client comment, tasks reconciled with the team's own tracker, and a review package that shows each statement with its own history and reads the client's answers back into the ledger. Eight commands, one job each — including one that reconciles the whole folder against the source tree in a direction you have to declare: the code is master and every document is corrected through a gate that never silently overrules an answer the client gave, or the documents are master and the gaps become tasks. Every edit is journalled, every finished task sweeps the client documents and not only the generated ones, task statuses move to what the audit actually found — closing what is built and reopening what is not — and every document
18 skills · 8 commands · 1 agent · hooks
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Use Alibaba Open Code Review from local Codex.
2 skills
Claude Code skill for creating and presenting Slidev slidedecks
1 skill
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.