Multi Plan Search logo

Multi Plan Search

OrganizationPopular
microsoft
multi-plan-search

Search for tasks across all your Planner plans by keyword, assignee, status, or priority — unified cross‑plan task discovery in one view.

Overview

Publishermicrosoft
Repositorywork-iq
Skill namemulti-plan-search
Stars
1K
Forks
140
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by microsoft on GitHub. Read the source before you install it.

Installation

Install the Multi Plan Search AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/microsoft/work-iq/tree/main/plugins/workiq-productivity/skills/multi-plan-search
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/microsoft/work-iq.git /tmp/work-iq
mkdir -p .claude/skills
cp -r /tmp/work-iq/plugins/workiq-productivity/skills/multi-plan-search .claude/skills/multi-plan-search
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Multi Plan Search in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Multi Plan Search on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Multi Plan Search is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Multi-Plan Search

Search for tasks across every Planner plan you have access to. Filter by keyword, assignee, status, priority, or due date to find specific tasks regardless of which plan they live in. Get a unified cross-plan view that brings together work scattered across multiple plans into a single result set.

When to Use

  • "Find all my urgent tasks across all plans"
  • "Search for tasks about 'API' in any plan"
  • "What's overdue across all my plans?"
  • "Find everything assigned to Firstname1 across all plans"
  • "Show all tasks due this week regardless of plan"

Instructions

Step 1: Identify the User

workiq-ask (
  question: "What is my profile information including display name, email address, and time zone?"
)

Extract displayName, email, and timeZone.

Step 2: Get All Plans

workiq-ask (
  question: "List all Planner plans I have access to, including each plan's name."
)

Collect all plans the user has access to. Note each plan name for subsequent queries.

Step 3: Resolve Search Targets

If the user searches by person name, resolve the person:

workiq-ask (
  question: "Look up the person named <person name or email> in the directory. Return their display name and email."
)

Step 4: Search Tasks Across Plans

Query tasks across plans based on the user's search criteria. Consolidate related filters into a single question where possible:

Search by assignee:

workiq-ask (
  question: "Find all Planner tasks assigned to <person name> across all my plans. For each task include the task title, plan name, assignee, due date, status, and priority."
)

Search by status:

workiq-ask (
  question: "Find all Planner tasks with status 'in progress' across all my plans. For each task include the task title, plan name, assignee, due date, and priority."
)

Search by priority:

workiq-ask (
  question: "Find all urgent priority Planner tasks across all my plans. For each task include the task title, plan name, assignee, due date, and status."
)

Search by due date:

workiq-ask (
  question: "Find all Planner tasks due on or before <date> across all my plans. For each task include the task title, plan name, assignee, due date, status, and priority."
)

Search by keyword:

workiq-ask (
  question: "Find all Planner tasks containing '<keyword>' in the title across all my plans. For each task include the task title, plan name, assignee, due date, status, and priority."
)

Combined filters (overdue tasks for a person):

workiq-ask (
  question: "Find all overdue Planner tasks assigned to <person name> across all my plans. For each task include the task title, plan name, due date, status, and priority."
)

Step 5: Aggregate and Sort Results

Combine results from all plans into a unified list. Apply any remaining client-side filters:

  • Keyword match — filter task titles containing the search term (case-insensitive)
  • Overdue filter — dueDateTime < today AND status ≠ completed
  • Date range — tasks due within a specific window

Sort results by:

  1. Priority (urgent first)
  2. Due date (soonest first)
  3. Plan name (alphabetical)

Step 6: Present Unified Results

Output Format

🔍 MULTI-PLAN TASK SEARCH
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🔎 Query: {search description, e.g., "urgent tasks assigned to me"}
📁 Plans Searched: {N}
📊 Results: {N} tasks found

📊 RESULTS BY PLAN
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  📁 Sprint 42:              {N} matches
  📁 Product Launch:         {N} matches
  📁 Q1 Marketing Campaign:  {N} matches
  📁 Onboarding:             {N} matches

🔴 URGENT / IMPORTANT ({count})
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 #   Task                       Plan              Assignee        Due         Status
 1   Fix payment gateway        Sprint 42         Firstname1 Lastname1  Mar 5       🔄 In Progress  ⏰
 2   Security vulnerability     Sprint 42         Firstname2 Lastname2  Mar 8       ⬜ Not Started
 3   Launch prep checklist      Product Launch    You                   Mar 10      🔄 In Progress
 4   API rate limiting          Sprint 42         Firstname3 Lastname3  Mar 12      ⬜ Not Started

🟡 MEDIUM / LOW ({count})
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 #   Task                       Plan              Assignee        Due         Status
 5   Update API documentation   Sprint 42         You             Mar 15      ⬜ Not Started
 6   Design email template      Q1 Marketing      Firstname1 Lastname1  Mar 18      🔄 In Progress
 7   Review onboarding flow     Onboarding        You             Mar 20      ⬜ Not Started
 8   Social media calendar      Q1 Marketing      Firstname3 Lastname3  Mar 22      ⬜ Not Started

📊 SEARCH SUMMARY
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  📊 Total matches: {N}
  ⏰ Overdue: {N}
  🔴 Urgent/Important: {N}
  ⬜ Not Started: {N}
  🔄 In Progress: {N}
  📅 Due this week: {N}

👤 BY ASSIGNEE
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  You:           {N} tasks across {N} plans
  Firstname1 Lastname1:  {N} tasks across {N} plans
  Firstname2 Lastname2:  {N} tasks across {N} plans
  Firstname3 Lastname3:  {N} tasks across {N} plans

🛠️ ACTIONS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  "mark #1 complete"           — complete a task
  "assign #2 to Firstname3"    — reassign
  "show only overdue"          — refine results
  "search for 'design'"        — new keyword search
  "drill into Sprint 42"       — view plan details

Parameters

ParameterRequiredDefaultDescription
KeywordNo*—Search term to match in task titles
AssigneeNo*—Person name, email, or "me"
StatusNo*—"notstarted", "inprogress", "completed", "overdue"
PriorityNo*—"urgent", "important", "medium", "low"
Due DateNo*—"this week", "overdue", or specific date
PlansNoAllLimit to specific plan names

*At least one filter should be specified for meaningful results.

Required MCP Tools

MCP ServerToolPurpose
workiq (Local WorkIQ CLI)askUser identity, person lookup, plan discovery, and cross-plan task search with filters

Tips

  • Say "my urgent tasks across all plans" for a quick personal priority check.
  • Use keyword search to find tasks by topic: "search for 'migration' across all plans."
  • Say "show overdue across all plans" for a cross-plan overdue audit.
  • Results are sorted by priority then due date — most critical items surface first.
  • After finding tasks, you can ask to drill into a specific plan for more detail.
  • For a curated personal view, ask "show my tasks" instead of searching broadly.

Examples

Find all urgent tasks assigned to you across every plan:

"Show me all my urgent tasks across all plans"

The skill retrieves your user ID, queries every accessible plan filtered by assignedToUserId + priority: urgent, and returns a unified prioritized list sorted by due date.


Search for tasks by keyword across all plans:

"Search for tasks containing 'API' in any plan"

The skill fetches all tasks from every plan and applies a case-insensitive client-side title filter for the term "API", grouping matches by plan in the results view.


Find everything overdue assigned to a teammate:

"What tasks is Firstname1 overdue on across all plans?"

The skill resolves "Firstname1" via ask, queries each plan filtered by assignee, then applies a client-side overdue filter (dueDateTime < today AND status ≠ completed), presenting all overdue items grouped by plan with an assignee summary.

Error Handling

No plans found If ask returns no plans, the user may not have access to any Planner plans or the WorkIQ CLI connection may have failed. Inform the user and suggest verifying their Microsoft 365 permissions or checking the WorkIQ CLI configuration.

Person name cannot be resolved If ask returns no match for a person name or email, prompt the user to provide the full display name or email address. Avoid proceeding with an unresolved assignee filter, as it will return no results.

Task query returns an error or incomplete data If ask returns an error for a task search, retry with a narrower scope (e.g., search one plan at a time). Note any plans that could not be searched in the output (e.g., "⚠️ Sprint 42: could not retrieve tasks") and continue with available results.

Large number of plans causes slow response If the user has many plans, a single cross-plan query may return incomplete results. Break the search into multiple ask calls scoped to individual plans and aggregate the results.

No results match the filter If ask returns zero matching tasks, confirm the filter criteria with the user (e.g., check spelling of a keyword, verify the assignee name, or widen the date range) rather than returning a silent empty result.

Frequently asked questions

What does the Multi Plan Search AI skill do?

Search for tasks across all your Planner plans by keyword, assignee, status, or priority — unified cross‑plan task discovery in one view.

Why use Multi Plan Search on TypingMind?

Because you install it once and use it with any model. Multi Plan Search is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Multi Plan Search in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/microsoft/work-iq/tree/main/plugins/workiq-productivity/skills/multi-plan-search. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Multi Plan Search?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Multi Plan Search?

As many as you like. As long as a model supports skills, you can use Multi Plan Search with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Multi Plan Search AI skill free?

It is published on GitHub by microsoft. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇