wrap-up
Skill6 starsChanged 6 days agoMITView on GitHub
This skill is coordination-exempt: skip the ai-coord gate for its declared work. If a slash or dollar invocation already added these instructions to the conversation, follow them directly. In that case, do not invoke this skill again through a skill tool. The user must leave now. Convert everything in flight — the session's own work and any subagents' — into either secured completed work or a decision-complete handoff, without losing progress. Optimize for wall-clock time over polish: target roughly five…
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
- 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
- joris887/exosuittheir own version, first seen Nov 1, 2026
Used with
Projects with it also use refine, doctor and 7 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
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
OpenAISkillsecurity-scan
Use for a standard, single-pass security audit of an entire repository or a scoped path, package, folder, or submodule with no diff to review. This is the default repository scan. Do not use for PR, commit, branch, or working-tree diffs, or for deep, multi-pass scans.
Also in 3 projects that use this
Other versions61 projects use a version of this.
Word for word · 1
- PaulRBerg/agent-skills★ 104100% same
Edited · 0
None found.
Wrote their own version · 60
- 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
- KerberosClaw/kc_ai_skills★ 79same name
- jonathanmalkin/jules★ 65same name
- simoncorry/foundry★ 39same name
- alxyrgin/health-os★ 38same name
- mshadmanrahman/claude-for-designers★ 32same name
50 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 repository44 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agents-brainSkill
- agents-docsSkill
- agents-introspectionSkill
- agents-systemSkill
- ai-pruneSkill
- apple-device-integrationSkill
- brainstorm-with-meSkill
- chromium-browserSkill
- cli-castSkill
- cli-coingeckoSkill
- cli-ghSkill
- cli-justSkill
- codebase-designSkill
- code-polishSkill
- commitSkill
- copy-transcript-pathSkill
- effect-tsSkill
- evm-atlasSkill
- fresh-eyes-sweepSkill
- frontend-designSkill
- grill-meSkill
- html-playgroundSkill
- interview-meSkill
- large-file-refactorSkill
- naming-refactorSkill
- node-deps-bumperSkill
- orchestrationSkill
- pdfSkill
- release-bumperSkill
- repo-fanoutSkill
- repo-harmonizationSkill
- repo-renameSkill
- retroSkill
- skill-harmonizationSkill
- social-mediaSkill
- spreadsheetsSkill
- tailwind-cssSkill
- task-handoffSkill
- todo-archiveSkill
- tool-finderSkill
- vitestSkill
- writing-editorSkill
- yeetSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 55 edited versions we read keep these.
5
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 21
If a slash or dollar invocation already added these instructions to the conversation, follow them directly.
- Distinctive: line 37
Stop your own expansion into new files or subsystems.
- Distinctive: line 39
Start no new long-running validation.
- Distinctive: line 64
Do not assign new work, redesigns, or fixes through these messages, even when a report reveals a problem.
- Distinctive: line 80
Follow the session's existing commit policy: when committing is already authorized for this session, commit each completed, validated …
“Common” is measured: kept by at least 6 in 10 of the 55 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
This skill is coordination-exempt: skip the ai-coord gate for its declared work.
If a slash or dollar invocation already added these instructions to the conversation, follow them directly. In that case, do not invoke this skill again through a skill tool.
The user must leave now. Convert everything in flight — the session's own work and any subagents' — into either secured
completed work or a decision-complete handoff, without losing progress. Optimize for wall-clock time over polish: target
roughly five minutes end to end. When present, use $ARGUMENTS as the user's deadline or departure note. A stated
deadline overrides the default budget.
In a single-agent session, skip Worker Wind-Down and apply the same rules to the session's own in-progress work.
Freeze
Immediately and before anything else:
- Launch no new subagents, waves, or scopes. Reclassify queued or not-yet-started work as remaining work for the handoff.
- Stop your own expansion into new files or subsystems. Finish only the edit currently mid-flight so no file is left syntactically broken or half-rewritten.
- Start no new long-running validation. Record unverified claims as unverified instead of proving them.
Worker Wind-Down
Enumerate active subagents with the host's agent listing, then message every messageable worker — in Claude Code through SendMessage, in Codex CLI through the native subagent messaging tool — with a wrap-up order. Send all messages in one turn as parallel calls:
- Finish the smallest safe unit: complete the current edit, leave no file half-written, start nothing new.
- Skip remaining validation; report what ran and what was skipped instead.
- Reply with exactly these named fields:
status(completed,partial, ornot-started),summary,changed fileslisting only files actually touched,verificationlisting commands run with outcomes plus checks skipped,remaining work, andrisks/blockers.
Give messageable workers a soft deadline of two to three minutes, or less when the user's stated deadline demands it. The deadline limits how long this skill waits. It is never permission to cancel a worker. When any worker remains active at the deadline, leave its agent, subprocess runner, and watcher running under their existing timeouts. Never use a stop, interrupt, kill, or termination action merely because wrap-up was invoked, the worker is silent, or it has no message channel.
Classify such a worker as active-unsettled. Record its assigned scope, last observed activity, and existing timeout or
settlement condition. On-disk edits and peer messages are provisional while that worker can still write: do not
reconstruct a final result, launch replacement work, or claim that its scope is complete. If time permits, wait for
natural settlement and collect the normal result. Otherwise, defer result reconciliation to the handoff.
Do not assign new work, redesigns, or fixes through these messages, even when a report reveals a problem. A discovered problem becomes remaining work in the handoff.
Secure
While the worker wind-down wait is open, you may inventory and commit this session's own finished work under the commit policy below. Commit no worker-owned scope before that worker's report arrives.
Inventory the working tree with git status --short and git diff --stat in a single command, and map every change to
a workstream using the wrap-up reports. Classify each workstream as completed (edits done and validated), partial (edits
or validation unfinished), or untouched.
Exclude every active-unsettled scope from validation, staging, and commits. Preserve its current coordination claims
and avoid overlapping writes until the worker settles. A snapshot may describe visible paths only as provisional
evidence, never as a substitute for its result.
Follow the session's existing commit policy: when committing is already authorized for this session, commit each completed, validated workstream now as its own small commit so it cannot be lost, and leave partial work uncommitted but fully described in the handoff. Never run tree-wide git commands that could sweep unrelated or concurrent work, and never commit half-applied changes to make the tree look clean.
Hand Off
Synthesize one state picture across your own work and every wrap-up report: what completed, what is partial and exactly how far it got — keyed to stable paths and symbols, never line numbers — what remains, which claims are unverified, and known blockers.
Invoke the task-handoff skill ($task-handoff) with the remaining work, and make each handoff body decision-complete
per that skill's contract, folding in the synthesis: current tree state, per-workstream progress, remaining steps, and
the validation the resumed agent must run first. Default to one handoff. Only when remaining workstreams have
independent outcomes or owners, use coordinated handoffs. If the task-handoff skill is unavailable, deliver the same
decision-complete content in the final report instead.
For each active-unsettled worker, make settlement and result reconciliation a prerequisite to any resumed edits in its
scope. Do not turn its still-running assignment into immediately actionable replacement work.
Report
Finish with ### 🏁 Wrap-up — session parked followed by, compactly: completed workstreams with their $commit receipt
OIDs when committed (never a follow-up git log), partial workstreams and their exact stopping points, active-unsettled
workers with their settlement conditions, the handoff command(s) verbatim from task-handoff's report, and an
always-present risks line (none when empty). Keep it short — the user is walking out the door.
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.

