Delegate Check logo

Delegate Check

Community
davekilleen
delegate-check

Review open delegations — what you handed off, to whom, its status, and the next useful nudge. Use when the user says 'what did I delegate', 'who owes me', 'check my handoffs', 'follow up with someone'. Not for prepping a meeting; use meeting-prep.

Overview

Publisherdavekilleen
RepositoryDex
Skill namedelegate-check
Stars
481
Forks
130
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 davekilleen on GitHub. Read the source before you install it.

Installation

Install the Delegate Check 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.
  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/davekilleen/Dex.git /tmp/Dex
mkdir -p .claude/skills
cp -r /tmp/Dex/packages/dex-agent-plugin/skills/delegate-check .claude/skills/delegate-check
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Delegate Check 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 Delegate Check 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 Delegate Check 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.

Execution mode

Run inline in the current conversation by default, so this work can see what the user has already discussed, decided, or settled this session. Do not fork merely because this skill was selected. Only run in the background when the user explicitly asks for a background run or the host has already obtained a specific background-work approval for this run.

Purpose

Give the user a clear view of work they have handed to other people without turning delegation into hovering. Find what is moving, what is waiting, and where a short follow-up would help.

When to Use

  • The user asks what they are waiting on
  • The user wants to review delegated work or team commitments
  • A weekly planning or review conversation reveals unclear ownership
  • A promised follow-up is approaching or overdue

Step 1: Gather Open Delegations

Read 03-Tasks/Tasks.md and recent notes in 00-Inbox/Meetings/.

Look for plain-language patterns such as:

  • An owner or assignee who is not the user
  • "Delegated to", "waiting on", "with", or "owned by"
  • A person promising to send, review, decide, introduce, or deliver something
  • A user task whose next step is to follow up with someone
  • An open action item in a meeting note assigned to another person

Check related person and project pages when they add useful context. If semantic search is available, use it to catch commitments expressed without the exact words above.

Do not count a general hope, discussion point, or completed promise as an open delegation.

Step 2: Reconcile Duplicates

The same handoff may appear in both Tasks.md and a meeting note. Treat matching owner, outcome, and timing as one delegation, and keep links to both sources.

When two records disagree, show the disagreement plainly and ask which status is current. Do not silently choose one.

Step 3: Build the Review

For each open delegation, capture:

  • What: the result the user handed off
  • Who: the person responsible
  • Handed off: the date or source meeting, when known
  • Expected: the promised or useful check-in date, when known
  • Status: moving, waiting, due soon, overdue, or unclear
  • Last touch: the latest relevant update
  • Next nudge: one specific, proportionate follow-up

Present the items in this order:

  1. Overdue or blocked
  2. Due soon
  3. Waiting normally
  4. Status unclear

Keep healthy items brief. Spend attention where the user may need to act.

Step 4: Recommend the Next Nudge

A good nudge is short and easy to answer. Draft it in the user's normal tone and include the outcome or date that matters.

Examples:

  • "How is the pricing review looking? I need the final call by Thursday to keep the launch on track."
  • "Quick check: are you still able to send the notes this week, or should we reset the date?"

Do not send a message or create a task without the user's approval.

Step 5: Update the Record

After the user confirms what changed:

  • Update a Dex task through the normal task tools, not by hand-editing its checkbox
  • Add a short status line to the relevant meeting or project note when that is the clearest source of truth
  • Mark a delegation complete only when the promised result is actually delivered or the user explicitly closes it
  • If the owner or date changed, preserve the earlier context in the note

Output

Use a compact review:

markdown
## Delegations needing attention

- **Pricing review — Morgan**
  - Expected: 2026-07-23 · Status: due soon
  - Last touch: Agreed in the 2026-07-16 launch meeting
  - Next nudge: Confirm whether Thursday still holds

## Waiting normally

- **Customer notes — Riley** · Expected next week · No action today

If nothing is open, say so plainly: "I found no open delegations in Tasks.md or recent meeting notes."

Rules

  • Never guess that silence means progress or failure
  • Keep the focus on outcomes, not activity
  • Distinguish work delegated by the user from work the user personally owes
  • Name missing owners, dates, or status as unclear
  • Use absolute dates
  • Do not nag when the agreed date has not arrived and there is no sign of risk

Frequently asked questions

What does the Delegate Check AI skill do?

Review open delegations — what you handed off, to whom, its status, and the next useful nudge. Use when the user says 'what did I delegate', 'who owes me', 'check my handoffs', 'follow up with someone'. Not for prepping a meeting; use meeting-prep.

Why use Delegate Check on TypingMind?

Because you install it once and use it with any model. Delegate Check 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 Delegate Check in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/davekilleen/Dex/tree/main/packages/dex-agent-plugin/skills/delegate-check. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Delegate Check?

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 Delegate Check?

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

Is the Delegate Check AI skill free?

It is published on GitHub by davekilleen. 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 👇