workiq-copilot
Guides 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.
What this skill does
# 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 1. **Copilot CLI plugin (preferred)** - `copilot` - `/plugin marketplace add github/copilot-plugins` - `/plugin install workiq@copilot-plugins` - Restart Copilot CLI. 2. **Standalone CLI / MCP server** - `npm install -g @microsoft/workiq` (or `npx -y @microsoft/workiq mcp`). - Run `workiq mcp` to expose MCP tools if needed. 3. **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 workiq` to ensure the binary is available. - Accept the EULA once via `workiq accept-eula`. - Confirm the correct tenant (`-t <tenant-id>` if different from default `common`). - Be ready to complete device login in the browser when prompted. ## Core Workflow 1. **Clarify intent** – agenda, action items, document lookup, people search, risk summary, etc. 2. **Craft precise prompt** – include timeframe, source, or topic (e.g., “Summarize Teams posts in #eng for today”). 3. **Run command** – `workiq ask --question "<prompt>"` (use `-q` for shorthand if desired). 4. **Monitor execution** – long answers may stream; wait for the response to finish before issuing additional requests. 5. **Summarize & redact** – highlight insights, note conflicts/tasks, avoid pasting raw links unless required. 6. **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 in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.