wrap-up
Skill3 starsChanged 3 months agoMITView on GitHub
Produce a structured closing summary for work-focused sessions — coding tasks, feature builds, bug fixes, design work, content production, or any session with a defined goal or deliverable. Trigger whenever the user types /wrap-up, or says something like "let's wrap up", "we're done with this task", "summarise what we built", or "what did we get done". Also trigger when a task reaches a natural completion point and the user signals they want to review what was accomplished. Do NOT use for informal chats or exploratory discussions — use /wind-down for those instead.
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
MicrosoftSkillsync
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 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
- wind-downSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 56 edited versions we read keep these.
4
Distinctive
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 23
If no formal spec exists, infer the intended goal from the opening of the conversation.
- Distinctive: line 64
Read back through the full conversation before writing.
- Distinctive: line 67
If the session involved multiple distinct workstreams or tasks, structure "What was completed" and "Next steps" accordingly.
- Distinctive: line 68
After completing the wrap-up, consider whether to invoke /suggest-next to surface related tasks, improvements, or follow-on work the user …
“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
/wrap-up
Produces a clear, honest closing summary for work sessions. The goal is to give both the user and any future session a complete picture of what was done, how it compares to what was intended, and what comes next. Think of it as the handover document — precise enough to resume work cold, honest enough to flag what didn't get done.
Tone
Professional but not stiff. Direct and accurate. This isn't a celebration or a post-mortem — it's a clear-eyed account of where things landed. Flag incomplete items plainly without over-explaining.
Before writing
Scan the full conversation for:
- Any spec, PRD, brief, or stated goals at the outset
- Any checkpoints, waypoints, or milestones that were set
- What was actually built, written, fixed, or decided
- Any blockers, diversions, or scope changes that occurred
- Any explicit TODOs, known issues, or deferred items mentioned If no formal spec exists, infer the intended goal from the opening of the conversation.
Output Structure
Produce the following sections. Omit any section that has nothing meaningful to put in it.
✅ Wrap-Up: [Brief descriptive title — what was built or done]
Goal One or two sentences stating what this session set out to accomplish, based on the spec, PRD, or stated intent at the outset. If goals evolved during the session, note that briefly.
What was done A clear account of what was actually accomplished versus what was intended. Be specific — reference file names, features, decisions, outputs where relevant. If explicit checkpoints or acceptance criteria were set at the outset, review each one here: was it met, partially met, or skipped, and why? If no formal checkpoints exist, a single honest account of what was done versus the stated goal is sufficient.
What wasn't completed Anything that was in scope but didn't get done — deferred, blocked, or deprioritised. Be plain about it. Include brief context if it's useful (why it was deferred, what's needed to unblock it).
Omit if everything in scope was completed.
Known issues and open questions Bugs, rough edges, unresolved decisions, or things that need a second look. Distinct from "not completed" — these are things that exist in the current output but may need attention.
Omit if there are none.
Next steps The concrete actions that should follow from this session — ordered by priority where obvious. These should be specific enough to act on: not "improve the UI" but "add loading state to the submit button" or "write tests for the auth module".
References A list of any external resources directly relevant to this session — formatted like references in a formal paper. Include where applicable:
- Tickets and issues (Linear, Jira, GitHub Issues, Trello, etc.) — title and URL
- Pull requests — title, number, and URL
- Repositories — name and URL
- Any other directly relevant links (staging URLs, docs, design files, etc.) Omit if no external references were mentioned or used.
Notes for execution
- Read back through the full conversation before writing. Don't reconstruct from memory of recent messages — the spec or goals are often set early and easy to miss.
- Be honest about what wasn't done. A wrap-up that only lists completions and buries gaps is less useful than one that's accurate.
- "Next steps" should be written as if handed to someone picking this up cold — specific enough to act on without needing to re-read the whole conversation.
- If the session involved multiple distinct workstreams or tasks, structure "What was completed" and "Next steps" accordingly.
- After completing the wrap-up, consider whether to invoke /suggest-next to surface related tasks, improvements, or follow-on work the user might not have considered.
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.

