agentleFS
noron12234noron12234/loose-ends/skills/loose-ends/SKILL.md

loose-ends

Skill1 starsChanged 4 months agoMITView on GitHub

Use when finishing a reply to a message that contained more than one ask, or when the user asks "did you do everything", "what did you skip", or invokes /loose-ends. Produces a recap mapping each thing the user asked for to what actually happened.

5 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 5

    1. nmamano/isomux★ 43same name
    2. zcaceres/skills★ 7same name
    3. ai-ecoverse/skills★ 1same name
    4. paradite/skills★ 1same name
    5. TucsenRoman/claude-skills★ 0same name

    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.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    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
  1. Distinctive:

    Say when you assumed: If an ask was ambiguous and you picked a reading, the recap line says which.

    line 40
  2. Distinctive:

    Never invent an answer for a fragment that was never a request.

    line 63

“Common” is measured: kept by at least 6 in 10 of the 4 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

Loose ends

The hook decides when a recap is owed. This decides what a good one looks like.

The shape

## Loose ends
1. <the user's ask, in their words> → <what happened, one line, with the path/URL/number>
2. ...

### Not done / needs you
- <ask> → <why not, and what you need>

Drop the second section when everything got done. Never drop an ask to avoid writing that section — an honest "not done" is the entire point of the tool.

Rules

Mirror their words, not yours. They asked to "make the login thing stop being annoying." Don't recap it as "refactored auth middleware." They won't recognize their own request and will read right past it.

One line each. The recap is a checklist for the eye, not a second copy of the answer. Detail lives above it.

Their order, not yours. List asks in the order raised, even when you did them in a different order. Users scan against their own message.

Asides count. Anything after "also", "btw", "one more thing", "順便", "對了", "另外" is exactly the kind of ask that gets dropped — those are the reason this exists.

Say when you assumed. If an ask was ambiguous and you picked a reading, the recap line says which. That is where a wrong assumption gets caught cheaply.

Match their language. Chinese conversation, Chinese recap.

Anti-patterns

Don'tDo
Recap your todo listRecap their message
"Investigated the issue""Cause was a stale cache key, fixed in x.py:42"
Silently omit an ask you skippedList it under Not done, with the reason
Merge two asks into one lineOne line per ask, even if related
Pad each line into a paragraphOne line means one line

If the hook misfired

The detector is deliberately blunt and sometimes splits one request into two, or reads a stray clause as an ask. Say so in one line and move on:

(The hook counted "然後部到 prod" separately — that was part of ask 1.)

Never invent an answer for a fragment that was never a request.

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.