github/awesome-copilot / skills/workiq-copilot
workiq-copilot
VerifiedGuides the Copilot CLI on how to use the WorkIQ CLI/MCP server to query Microsoft 365 Copilot data (emails, meetings, docs, Teams, people) for live context, summaries, and recommendations.
WorkIQ Copilot Skill
Overview
WorkIQ (Public Preview) lets Copilot query Microsoft 365 data with natural language. It supports schedules, documents, Teams messages, email threads, follow-up tracking, stakeholder summaries, and more. Use this skill whenever a task needs live organizational intelligence beyond the local repository.
Supported Data & Sample Prompts
- Emails – “Summarize emails from Sarah about the budget.”
- Meetings – “What are my upcoming meetings this week?”
- Documents – “Find recent documents about Q4 planning.”
- Teams – “Summarize messages in the Engineering channel today.”
- People/Projects – “Who is working on Project Alpha?”
Getting Access
- Copilot CLI plugin (preferred)
copilot/plugin marketplace add github/copilot-plugins/plugin install workiq@copilot-plugins- Restart Copilot CLI.
- Standalone CLI / MCP server
npm install -g @microsoft/workiq(ornpx -y @microsoft/workiq mcp).- Run
workiq mcpto expose MCP tools if needed.
- Tenant consent
- First use prompts for Microsoft 365 admin consent (EULA + permissions). Non-admins must contact tenant admin to approve per the Tenant Administrator Enablement Guide.
Pre-flight Checklist
- Run
Get-Command workiqto ensure the binary is available. - Accept the EULA once via
workiq accept-eula. - Confirm the correct tenant (
-t <tenant-id>if different from defaultcommon). - Be ready to complete device login in the browser when prompted.
Core Workflow
- Clarify intent – agenda, action items, document lookup, people search, risk summary, etc.
- Craft precise prompt – include timeframe, source, or topic (e.g., “Summarize Teams posts in #eng for today”).
- Run command –
workiq ask --question "<prompt>"(use-qfor shorthand if desired). - Monitor execution – long answers may stream; wait for the response to finish before issuing additional requests.
- Summarize & redact – highlight insights, note conflicts/tasks, avoid pasting raw links unless required.
- Offer follow-ups – blocking time, drafting notes, deeper queries, etc.
Command Reference
| Command | Purpose |
|---|---|
workiq --help | Show global options. |
workiq version | Display installed version. |
workiq accept-eula | Accept license (first use). |
workiq ask | Interactive mode. |
workiq ask --question "..." | Ask a specific question (use -q shorthand if preferred). |
workiq ask -t <tenant> -q "..." | Target a specific tenant. |
workiq mcp | Start MCP stdio server (expose WorkIQ tools to other agents). |
Prompt Patterns
- Agenda: “What’s on my calendar tomorrow?”
- Action items: “Summarize follow-ups from today’s customer sync.”
- Documents: “List PowerPoints about Contoso FY26 roadmap.”
- Communications: “What did my manager say about the deadline?”
- Insights: “What blockers came up in the last three meetings?”
- Planning: “Suggest focus blocks for Tuesday afternoon.”
Response Guidelines
- Keep summaries concise (2–3 sentences) calling out load, priorities, blockers, and optional next steps.
- Refer to meetings/documents generically unless the user specifically needs links.
- Mention if WorkIQ can continue (e.g., “WorkIQ can show Thu–Sun if needed”).
- Map WorkIQ’s suggested actions to clear offers (block time, send follow-up, request recording, run deeper query).
Best Practices
- Prefer narrow prompts to reduce noise; run multiple queries if needed.
- Combine outputs logically (agenda + conflicts + action items) before responding.
- Respect privacy: do not expose attendee lists or confidential snippets unless explicitly requested.
- Log which commands were run so future steps can reference them (“Asked WorkIQ for agenda + conflicts”).
- Use MCP mode (
workiq mcp) when another agent/workflow needs direct tool access.
Troubleshooting
- Missing CLI – install via npm or ensure PATH is set; notify user if unavailable.
- Consent/auth errors – re-run command after admin grants permissions or after completing device login.
- Long/incomplete output – rerun with refined scope or ask for specific data slices (per day/project/person).
- Command hanging – cancel the running command in your terminal (for example, with Ctrl+C) or restart the Copilot CLI session, then retry; ensure browser login completed.
Follow-up Actions to Offer
- Block focus/overflow holds at suggested times.
- Draft reschedule/decline messages referencing WorkIQ guidance.
- Request recordings or summaries for overlapping sessions.
- Capture action items into task trackers.
- Run additional WorkIQ queries (by project, stakeholder, time range) for deeper analysis.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 466k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 196k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |