team-shutdown
Skill4 starsChanged 3 months agoMITView on GitHub
Use when all team tasks are complete or abandoned and team infrastructure, worktrees, and AGENTS.md need cleanup
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
When to use: All worker tasks are complete (PRs merged) or explicitly abandoned, and the team infrastructure, worktrees, and AGENTS.md need …
- Distinctive: line 19
If open or unmerged work remains, list it and confirm with the user before tearing down.
- Very specific: line 24
Run this BEFORE TeamDelete — a torn-down agent cannot help iterate on a PR.
- Distinctive: line 28
Do NOT skip this — leaving team infrastructure running wastes resources and pollutes context.
- Very specific: line 32
Commit to agents-workbench (local only — never push).
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Team Shutdown Phase
You are the Team Lead, tearing down a finished (or abandoned) team. This skill owns team-level teardown only. Per-branch finishing — verifying tests, choosing merge / PR / keep / discard, and provenance-safe worktree removal — is delegated to superpowers:finishing-a-development-branch. Do not hand-roll merges or git worktree remove here.
When to use: All worker tasks are complete (PRs merged) or explicitly abandoned, and the team infrastructure, worktrees, and AGENTS.md need cleanup.
Shutdown Workflow
- Verify completion status.
gh pr list --state openandgit branch --no-merged "$(git symbolic-ref refs/remotes/origin/HEAD | sed 's@^refs/remotes/origin/@@')"to find any unmerged worker branches.- If open or unmerged work remains, list it and confirm with the user before tearing down.
- Finish each remaining worker branch (delegate).
- For every worker worktree still under
.worktrees/,cdinto it and invokesuperpowers:finishing-a-development-branch. That skill verifies tests, presents merge / PR / keep / discard, and cleans up the worktree provenance-safely. - Branches already merged and cleaned during execution need no action.
- Run this BEFORE
TeamDelete— a torn-down agent cannot help iterate on a PR.
- For every worker worktree still under
- Shut down team agents.
TeamDeleteto remove team infrastructure (Principal Engineer, QA, all Workers).- Do NOT skip this — leaving team infrastructure running wastes resources and pollutes context.
- Update
AGENTS.md.- Mark every task complete (or abandoned with reason); record final status.
- Commit to
agents-workbench(local only — never push).
- Context hygiene.
- Team context is large. If you're moving on to new work, start a fresh session or use
/handoffto carry forward only what's needed. (Context is auto-summarized as it grows; no manual/compactstep is required.)
- Team context is large. If you're moving on to new work, start a fresh session or use
Common Shutdown Mistakes
| Mistake | Fix |
Hand-rolling git worktree remove or merges | Delegate per-branch finishing to superpowers:finishing-a-development-branch |
TeamDelete before finishing branches | Finish branches first; a torn-down agent can't iterate on a PR |
Skipping the AGENTS.md final status | Record it for future reference |
Pushing the AGENTS.md commit | agents-workbench is local-only; never push it |
Arguments
User arguments: $ARGUMENTS
In this repository48 other files it gives its agents.
- .claude/templates/AGENTS.mdAGENTS.md
- docs/agents.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- .cursor/rules/core.mdcCursor rule
- .cursor/rules/go.mdcCursor rule
- .cursor/rules/k8s.mdcCursor rule
- .cursor/rules/node.mdcCursor rule
- .cursor/rules/python.mdcCursor rule
- .cursor/rules/rust.mdcCursor rule
- .cursor/rules/tdd.mdcCursor rule
- .cursor/rules/workbench.mdcCursor rule
- llms-full.txtllms.txt
- llms.txtllms.txt
- cmux-sprint-orchestratorSkill
- config-auditSkill
- doneSkill
- eurekaSkill
- goalSkill
- go-reviewSkill
- handoffSkill
- js-reviewSkill
- k8s-debugSkill
- k8s-reviewSkill
- kickoffSkill
- pr-review-ingestSkill
- pr-reviewSkill
- python-reviewSkill
- reflectionSkill
- skill-evalSkill
- tdd-protocolSkill
- team-executeSkill
- team-planSkill
- test-reviewSkill
- validate-recommendationSkill
- worktree-guideSkill
- babysitSkill
- canvasSkill
- create-hookSkill
- create-ruleSkill
- create-skillSkill
- create-subagentSkill
- migrate-to-skillsSkill
- sdkSkill
- shellSkill
- split-to-prsSkill
- statuslineSkill
- update-cli-configSkill
- update-cursor-settingsSkill
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.