wrap-up
Skill0 starsChanged 13 days agoMITView on GitHub
Close a working session so the next one starts cheaply. Rewrites STATE.md as a snapshot of now with the next step, adds the non-obvious reasons for decisions to DECISIONS.md, updates CLAUDE.md if the essence or the rules changed, and leaves a first message for the next session. Use when the user says "that's it for today", "let's wrap up", "let's stop here", or when a meaningful piece of work is finished and checked.
61 other projects use a version of this.
Adopted by
Most recently taken up by
- codewithmukesh/dotnet-claude-kittheir own version, first seen Nov 8, 2026
- PaulRBerg/dot-agentstheir own version, first seen Nov 6, 2026
- adeonir/agent-skillstheir own version, first seen Nov 6, 2026
- Memolok/Claude-plugintheir own version, first seen Nov 6, 2026
- bas1l/claude-skillstheir own version, first seen Nov 3, 2026
- kiloloop/oacp-skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use refine, doctor and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AlexPEClubSkillrefine
Always use when the user wants to discuss an exsiting feature or specification. Open an existing feature spec to improve, extend, or fundamentally challenge it. Pass the feature ID as argument (e.g. /refine PROJ-2).
Also in 3 projects that use this
MicrosoftSkilldoctor
Diagnose an Amplifier CLI environment through the CLI doctor agent. USE WHEN a user requests CLI runtime, settings or missing-capability inspection. DO NOT USE for project bugs or other hosts.
Also in 4 projects that use this
- MicrosoftSkill
sync
Sync the current session branch with its upstream branch, or publish the current session branch to a remote. Use when the user asks to sync a branch, pull latest changes, rebase onto upstream, push current branch, publish branch, or set upstream.
Also in 3 projects that use this
austintgriffithSkillorchestration
Use when a Scaffold-ETH 2 build leaves localhost: planning the launch order, deploying and verifying contracts on a live network, standing up a fork of a real chain to rehearse a deploy, or fixing a contract bug that is already onchain. Not for running the app or a demo against that fork (`/frontend-playbook`).
Also in 3 projects that use this
SentrySkillspec
Produce a verified spec — problem, desired outcome, and acceptance criteria — before building. Use when given a GitHub/Linear issue link, when starting from a fuzzy in-conversation idea, or asked to "figure out what to do" / "scope this" / "what should I build" — whenever the *what* isn't yet pinned down. Grills the ambiguities, checks the premise against the code, and produces acceptance criteria you sign off on — then hands to design-first.
Also in 5 projects that use this
nicolasestremSkillbrainstorm
Structured idea generation and solution exploration with systematic analysis.
Also in 5 projects that use this
Other versions61 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 61
- rohitg00/pro-workflow★ 2.9ksame name
- anthropics/launch-your-agent★ 1ksame name
- codewithmukesh/dotnet-claude-kit★ 808same name
- ianlkl11234s/mini-taiwan-pulse★ 546same name
- aspi6246/Claude-Code-Skills-for-Academics★ 153same name
- PaulRBerg/agent-skills★ 104same name
- KerberosClaw/kc_ai_skills★ 79same name
- jonathanmalkin/jules★ 65same name
- simoncorry/foundry★ 39same name
- alxyrgin/health-os★ 38same name
51 more not listed
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 repository3 other files it gives its agents.
- catch-upSkill
- new-projectSkill
- parkSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 56 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 17
No STATE.md in the project → it hasn't been started with these files: offer new-project instead of inventing them.
- Distinctive: line 28
Only the non-obvious *why*: what can't be read from the result itself.
“Common” is measured: kept by at least 6 in 10 of the 56 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
You are closing the session: stop, look at what was done, and move what matters from this conversation into the files, so that the next session goes on without losses.
It fits when a meaningful piece is finished and works, before a break or the end of the day, or when the session has grown long. Not in the middle of unfinished work: finish it first, or mark it "in progress" in STATE.md.
0. Name the project
Say in one line which project you are wrapping up, and let the user correct you before you write
anything. If the session touched several projects, list them all and wrap up each in turn.
No STATE.md in the project → it hasn't been started with these files: offer new-project instead
of inventing them.
1. Rewrite STATE.md
Where we are now, and the next steps. STATE.md is a snapshot of the present, not a diary: remove what is no longer true. End it with Next step: — concrete enough to start from tomorrow without this conversation.
2. Add to DECISIONS.md — if decisions were made
Only the non-obvious why: what can't be read from the result itself. Take the reasons from the
conversation — the user's words, or what you worked out together — and don't add new ones of your
own. Add new entries at the bottom as ## YYYY-MM-DD · <the decision> and a few lines. Never rewrite
old entries.
3. Update CLAUDE.md — only if it changed
The essence, the rules or the map of files changed → reflect it. Otherwise leave the file alone.
4. Look at the extra files
Suggest a new one if some knowledge keeps repeating and doesn't fit; suggest merging duplicates and removing files nobody uses. Act on the user's yes.
5. Summarize
Briefly, in plain words: what was done in this session.
6. Hand over
Give a ready "first message for the next session": what to read and what the next step is. Its
source is the Next step in STATE.md — the chat is temporary, the file stays, and catch-up will
find it on its own. Suggest starting the next session fresh: the context comes back from the files,
not from the chat history.
7. Don't commit
Saving to version control is a separate step. If the project is a git repository, say in one line that the files changed and can be committed — and commit only if the user asks.
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.