Wrap Up logo

Wrap Up

Community
mshadmanrahman
wrap-up

Saves today's work session as a four-line entry (did, decided, open, next) at the top of the project's log.md, after the student confirms it, so a fresh chat can continue tomorrow with /pick-up. Writes to projects/<client>/log.md or career-vault/log.md, one entry per project touched, never to _new-client. Use when the student says wrap up, done for the day, save my progress, end session, or is about to close the chat.

Overview

Publishermshadmanrahman
Repositoryclaude-for-designers
Skill namewrap-up
Stars
40
Forks
10
Bundled files
Instructions only
LicenseMIT
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 mshadmanrahman on GitHub. Read the source before you install it.

Installation

Install the Wrap Up 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/mshadmanrahman/claude-for-designers/tree/main/.claude/skills/wrap-up
  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/mshadmanrahman/claude-for-designers.git /tmp/claude-for-designers
mkdir -p .claude/skills
cp -r /tmp/claude-for-designers/.claude/skills/wrap-up .claude/skills/wrap-up
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wrap Up 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 Wrap Up 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 Wrap Up 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.

The student typed /wrap-up. They are done for the day and about to close this chat. Your job is to save what happened in this session so that tomorrow, in a fresh chat, /pick-up can carry on from exactly here.

A new chat remembers nothing from this one. The log is the only thing that carries over, so the four lines you write are all tomorrow's Claude will know.

Step 1. Work out where the entry goes

The log lives beside the work it describes. Never in one shared file at root.

  • Client work goes to projects/<client>/log.md. The client is the folder the session worked in: edubridge, or their own client folder.
  • Career work (Classes 7 and 8, anything in career-vault/) goes to career-vault/log.md.
  • Work on principles/claude-contract.md (Class 2) goes to the log of their project, because Class 2 also writes the project contract and that is where they will look for it.
  • Never write to projects/_new-client/log.md. That folder is an empty template.

If the session touched two projects, write one entry into each project's log, each holding only what happened in that project. One client's notes never land in another client's file.

If log.md does not exist yet, create it with the header shown in Step 3.

Step 2. Propose, then let them correct

Do not write straight away. Draft the entry from the session and show it:

Before I save, check this:

  Did:     ran /grill-me on the brief, finished brief-v3-interrogated.md
  Decided: bKash is its own flow, because the parent leaves the site
  Open:    the client has not said who handles refunds
  Next:    write scope-email.md

Anything wrong or missing?

The Decided line matters most. Write the decision and the reason, in their words where you can. If you are not sure something was a decision, ask rather than guess: the decisions are theirs, and a wrong one saved here gets repeated tomorrow as if it were settled.

If nothing was decided, write "nothing decided". Never invent one.

When they answer, apply their corrections. If they say it is fine, save it.

Step 3. Write the entry

Newest entry at the top, directly under the header, so /pick-up reads the first entry and stops. Never rewrite or delete older entries.

New file header:

markdown
# Log

One entry per work session, newest first. `/wrap-up` writes it, `/pick-up` reads it. You never edit this by hand.

Entry format, exactly four lines under a dated heading:

markdown
## 2026-10-02, Class 3

- **Did:** ...
- **Decided:** ... because ...
- **Open:** ...
- **Next:** ...

Get today's date from the system, never guess it. Take the class number from the class table in CLAUDE.md; if the work was outside any class, leave the class off the heading.

Keep each line to one or two sentences. This is a note to themselves, not a report. Name real files by path.

Step 4. Close

One line: which file you saved to, and that they can close the chat. Then stop.

Saved to projects/edubridge/log.md. Close this chat whenever you like. Tomorrow, open a new one and type /pick-up.

Do not summarise the session a second time. Do not suggest more work.

Frequently asked questions

What does the Wrap Up AI skill do?

Saves today's work session as a four-line entry (did, decided, open, next) at the top of the project's log.md, after the student confirms it, so a fresh chat can continue tomorrow with /pick-up. Writes to projects/<client>/log.md or career-vault/log.md, one entry per project touched, never to _new-client. Use when the student says wrap up, done for the day, save my progress, end session, or is about to close the chat.

Why use Wrap Up on TypingMind?

Because you install it once and use it with any model. Wrap Up 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 Wrap Up in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mshadmanrahman/claude-for-designers/tree/main/.claude/skills/wrap-up. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Wrap Up?

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 Wrap Up?

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

Is the Wrap Up AI skill free?

Yes. It is published on GitHub by mshadmanrahman under the MIT license. 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 👇