agentleFS
Sign inStart free
playingpossummplayingpossumm/loose-ends/.claude/skills/close/SKILL.md

close

Skill0 starsChanged 33 days agoMITView on GitHub

Close an open loop by producing the artifact that resolves it (a drafted email, event details, a summary, a decision) and mark it done, killed, or someday. Use when the user says "close this", "draft that email", "help me deal with X", or picks something from a brief.

26 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use open, reconcile and 5 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.
  • BlockSkill

    open

    Open markdown documents in Penpal for collaborative review. Use when you want a human to review a document, plan, or research artifact.

    Also in 5 projects that use this

  • howellsSkill

    reconcile

    Audit a project against current plugin conventions and offer to update structure.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    validate

    Run the full CI validation workflow locally before submitting a PR. Use this as a final check to ensure all Azure DevOps CI pipeline steps will pass.

    Also in 4 projects that use this

  • AnthropicSkill

    start

    Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.

    Also in 6 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 8 projects that use this

  • genomewalkerSkill

    resume

    Resume a thread by loading its ~800-token context capsule

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 21 edited versions we read keep these.

  • 5

    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
  1. Distinctive:

    No throat-clearing, no closing remark.

    line 16
  2. Distinctive:

    2. Read its provenance: Every loop cites the source that produced it.

    line 23
  3. Distinctive:

    Write the thing. Do not write *about* the thing.

    line 40
  4. Distinctive:

    5b. When the item is long overdue: If the brief escalated this because it is more than 14 days past its date, do not produce a large …

    line 50
  5. Very specific:

    6. File the artifact: if it is worth keeping, since a summary belongs in wiki/synthesis/ and a sent message does not.

    line 58
  6. Distinctive:

    If closing reveals a new commitment, open a new loop for it and say so.

    line 73

“Common” is measured: kept by at least 6 in 10 of the 21 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

close

Take one open loop and remove the friction that has kept it open. Tracking a loop is worth little; this is where the system earns its place.

How to write

Neutral and plain, a reference article rather than an essay. Follow Orwell's rules: no familiar figures of speech, no long word where a short one works, cut every word that can go, active over passive, everyday English over jargon. Give numbers where you have them. No throat-clearing, no closing remark.

Procedure

1. Find the loop. Named by the user, or picked from loops/open/. If they are referring to something in the last brief, read briefs/ to resolve it. Ambiguous → list candidates.

2. Read its provenance. Every loop cites the source that produced it. Read that source. A draft written without it will be generic, and generic is what makes the user stop using this.

3. Gather context. mem/profile.md for voice and working style, mem/people.md if a person is involved, and any wiki/ pages the loop touches. Cite what you use.

4. Produce the artifact, in full rather than described.

LoopProduce
owes someone an email or messagethe drafted message, subject line included, ready to paste
a date or deadlineevent title, date, time, and the details to paste in
something unreada summary of the actual source, what it says and whether it still matters
an undecided decisionthe options, what the vault knows about each, and a recommendation
a task with no obvious artifactthe smallest concrete next action, written out

Write the thing. Do not write about the thing. "You could email them explaining the delay" is a failure; the email itself is the deliverable.

5. Ask what to do with the loop:

  • done moves it to loops/closed/ with status: done
  • killed moves it to loops/closed/ with status: killed, and records why
  • someday leaves it open with status: someday, and it stops appearing weekly
  • still open leaves it as it is and resets surfaced: 0, since it has now been acted on

5b. When the item is long overdue. If the brief escalated this because it is more than 14 days past its date, do not produce a large artifact by default. Ask which of the three it is, whether to drop it, re-date it or do it now, and only build the artifact for the third. Writing a detailed plan for something the user is about to drop wastes both of your time.

Record the reason when dropping. "Dropped 22 Sep: the deadline passed and the project moved on" is worth keeping; a bare status: killed is not.

6. File the artifact if it is worth keeping, since a summary belongs in wiki/synthesis/ and a sent message does not. Ask if unsure.

7. Log: ## [YYYY-MM-DD] close | <loop> — <outcome>

Rules

  • Never send. Never write a calendar. Never post. Produce and hand over. This is enforced by holding no credentials that could do otherwise; do not work around it.
  • Never invent facts to make a draft read well. Mark what you do not know as [gap: what's missing] and say so. A confident wrong draft about a real person is the worst thing this system could produce.
  • Match their voice, drawn from mem/ and their own writing in raw/. If you have too little to go on, say so and write plainly rather than guessing at a style.
  • One loop per run. Batch-closing produces four mediocre drafts instead of one good one.
  • If closing reveals a new commitment, open a new loop for it and say so.

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.

Check your setup, free