wind-down
Skill3 starsChanged 3 months agoMITView on GitHub
Produce a structured closing summary for informal or exploratory conversations — discussions, brainstorms, research dives, or any chat that isn't primarily a work task. Trigger whenever the user types /wind-down, or says something like "let's wind down", "wrap this up", "summarise what we discussed", or "close out this conversation". Also trigger at the natural end of a long informal chat when the user signals they're done. Do NOT use for task/work completion — use /wrap-up for that instead.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- creationisttest-git/startup_studiotheir own version, first seen Sep 12, 2026
- median-labs/close-the-bookstheir own version, first seen Sep 10, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- median-labs/close-the-books★ 1same name
- creationisttest-git/startup_studio★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-docsSkill
- be-conciseSkill
- build-contextSkill
- commit-and-pushSkill
- deploy-prototypeSkill
- response-analysisSkill
- suggest-nextSkill
- wrap-upSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 42
Read back through the full conversation before writing.
- Distinctive: line 45
If the conversation touched on personal context (the user's work, projects, interests), reflect that back specifically rather than speaking …
- Distinctive: line 46
After completing the wind-down, consider whether to invoke /suggest-next to surface related ideas, tasks, or reading for the user to …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/wind-down
Produces a warm, well-structured closing summary for informal and exploratory conversations. Think of it as the consolidation layer — the equivalent of writing up notes before sleep, so ideas can be mulled over and returned to later.
Tone
Conversational but considered. This isn't a corporate debrief — it's more like a thoughtful friend summarising a good conversation. Avoid bullet-point overload; use prose where it flows better, lists where structure genuinely helps.
Output Structure
Produce the following sections. Omit any section that has nothing meaningful to put in it — don't force content.
🌙 Wind-Down: [Short evocative title capturing the conversation's essence]
What we explored 2–4 sentences summarising the arc of the conversation. What was the central question or theme? Where did it go? What shifted or developed as the discussion progressed?
Key ideas and insights The most interesting, useful, or novel points that emerged. These should be the things worth remembering — not a transcript, but the signal. Use a short list or prose depending on what suits the content. Aim for 3–6 items.
Things to sit with Open questions, unresolved tensions, or ideas that deserve more thought. The "sleep on it" section. Framed as prompts for reflection rather than problems to solve. 2–4 items.
References and rabbit holes Any books, articles, tools, concepts, people, or links that came up or were implied. Include brief context for each — why it's relevant to what was discussed. Omit if nothing specific came up.
Possible next steps or follow-ons Concrete things that could come next, if any emerged naturally — further conversations, things to try, things to read or watch. Keep this light; this is not a task list. If nothing obvious emerged, omit this section.
Notes for execution
- Read back through the full conversation before writing. Don't rely on recency bias — earlier parts of long conversations often contain the most interesting material.
- The title should feel earned, not generic. "Wind-Down: AI and Cognition" is lazy. "Wind-Down: Sleep Hygiene for Machines" is better.
- "Things to sit with" is the most valuable section for many conversations — don't skip it or phone it in.
- If the conversation touched on personal context (the user's work, projects, interests), reflect that back specifically rather than speaking generically.
- After completing the wind-down, consider whether to invoke /suggest-next to surface related ideas, tasks, or reading for the user to consider.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.