agentleFS
Simple-With-UsSimple-With-Us/BotFleet/.claude/skills/closeout/SKILL.md

closeout

Skill4 starsChanged 10 days agoApache-2.0View on GitHub

Finish a Monet work unit — THE BOARD, effort log, GitHub issue, Slack, Apple Notes, PR merge state, and Mac-process inventory. Use when a lane is merged, deployed, parked, or handed off. Never silently walk away from In Progress.

11 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use prototype, research 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.
  • GoogleSkill

    prototype

    Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

    Also in 4 projects that use this

  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 4 projects that use this

  • GoogleSkill

    teach

    Teach the user a new skill or concept, within this workspace.

    Also in 3 projects that use this

  • MicrosoftSkill

    grill-with-docs

    Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

    Also in 3 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 3 projects that use this

  • +4 more from google

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start-of-work is a Linear claim plus Zulip post.

    line 15
  2. Distinctive:

    If you executed a numbered GitHub issue, comment or close it so it is not abandoned.

    line 36
  3. Very specific:

    If this unit created, loaded, bootout, or retired a LaunchAgent, cron, login item, pm2 KeepAlive job, or a helper other agents run: …

    line 59
  4. Very specific:

    Do not SIGKILL com.jay.claude-remote-control.

    line 61
  5. Very specific:

    If you shipped a flag that is off, reserve a Planned enablement row (ST: also docs/FEATURE-ENABLEMENT-BACKLOG.md).

    line 65
  6. Very specific:

    If you stop without merge: board stays accurate (open or a comment "parked because …"), Slack says BLOCKED/parked, worktree is not dirty …

    line 69
  7. Very specific:

    If closing out work adopted from a peer, posting a direct [<SUB_TAG>-><ORIGINAL_TAG>] notification to #Work-In-Progress.

    line 82

“Common” is measured: kept by at least 6 in 10 of the 10 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Closeout (MONET)

Shared ~/.claude/skills. Monet, Claude/Fable, and (when active) Renoir all load this directory. Do not treat the word Monet in examples as proof of your seat. Pin AGENT_SEAT / AGENT_TAG from the logged-in account before Slack or board --by:

  • Monet → MONET, Notes Monet, monet/, ~/apps/<app>-monet
  • Claude / Fable → CLAUDE, Notes Claude, claude/, ~/apps/<app>-claude
  • Renoir → RENOIR, Notes Renoir, renoir/, ~/apps/<app>-renoir Cursor, Grok, Grok Bot, Codex, AG, DeepSeek, Kimi, and Fx have their own skill dirs and must not take identity from here.

Start-of-work is a Linear claim plus Zulip post. End-of-work closes Linear and Zulip plus Notes when the owner might ask "what happened?"

1. Truth check

  • Merged to main? (gh pr view / git merge-base --is-ancestor)
  • Production verified? (deploy-verify) Completed ≠ Deployed.
  • Uncommitted files? Commit or explicitly report why not (failing tests, secrets, owner hold).

2. Linear

board status <id> completed --resolution "Landed in #<PR>.  <one line>."
# or: deployed — only after health verify

Effort logs are archived — do not edit live ~/apps/*-EFFORT-LOG.md or repo docs/EFFORT-LOG.md. A Linear comment is useful context for peers.

3. Linear + GitHub

  • Completed = merged to main and reflected on the Linear issue.
  • Deployed = released and verified (say how).
  • If you executed a numbered GitHub issue, comment or close it so it is not abandoned.
  • Cross-app work gets a Linear issue (or explicit comment) on each affected app team.

4. Zulip (#Work-In-Progress)

printf '%s\n' "[$AGENT_SEAT] sync-N
repo: <project>
state: DONE
pr: #<n>
board: <id>
work: <what landed>" > /tmp/sync-note.md && chmod 600 /tmp/sync-note.md
AGENT_SEAT="${AGENT_SEAT:?set MONET, CLAUDE, or RENOIR}" simple-chat post --topic "<project> sync" --body-file /tmp/sync-note.md

Not FLEET for a normal closeout.

5. Apple Notes

Substantial work: living Completion note, --update in place. Title [APP, Monet] short topic. See apple-notes. Cloud sessions: skip Notes, say so, leave the handoff in the PR.

6. Mac local processes

If this unit created, loaded, bootout, or retired a LaunchAgent, cron, login item, pm2 KeepAlive job, or a helper other agents run: add/update a row on /Users/jay/apps/MAC-LOCAL-PROCESSES.md and --update "⭐️ Background Jobs Master List" in the same change. Say always-on vs on-demand. Retire in place; never delete historical rows.

Do not SIGKILL com.jay.claude-remote-control.

7. Default-off features

If you shipped a flag that is off, reserve a Planned enablement row (ST: also docs/FEATURE-ENABLEMENT-BACKLOG.md).

Parked, not done

If you stop without merge: board stays accurate (open or a comment "parked because …"), Slack says BLOCKED/parked, worktree is not dirty with uncommitted finished code. In Progress after you left is how three agents redo the same slice.

Canon

  • /Users/jay/apps/FLEET-PROTOCOL.md — triple closeout; Apple Notes; Mac local processes; always-commit
  • /Users/jay/apps/EFFORT-LOG-PROTOCOL.md
  • Skills: board-ops, apple-notes, deploy-verify, land-lane

Living Handoff Morphing to Closeout

Throughout execution, maintain a brief big-picture outline of task state. When the task is complete, this outline naturally becomes your Closeout Report by:

  1. Marking all milestones as completed with commit/PR references.
  2. Replacing in-flight WIP notes with live production deployment verification (/api/health 200, build SHA).
  3. If closing out work adopted from a peer, posting a direct [<SUB_TAG>-><ORIGINAL_TAG>] notification to #Work-In-Progress.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.