agentleFS
annatomkaannatomka/skills/tldr/SKILL.md

tldr

Skill1 starsChanged 6 months agoMITView on GitHub

Shrink Claude's previous answer (or every finding so far in the session) into a one-sentence verdict plus up to three short findings. Use only when the user types /tldr or asks for "the short version", "one-sentence verdict", "summarize what you found".

40 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use explain, handoff and 2 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.
  • sunnyclinches44Skill

    explain

    Explains code using real-world analogies and ASCII diagrams

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 6 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 3 projects that use this

  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 3 projects that use this

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 35 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
  1. Distinctive:

    No argument: your previous answer in this conversation.

    line 14
  2. Distinctive:

    If the answer corrected an earlier claim, the summary uses the corrected version.

    line 44
  3. Distinctive:

    Keep a caveat only if it changes the decision.

    line 45
  4. Distinctive:

    Never use the em dash character.

    line 47
  5. Distinctive:

    No headers other than the ones in the shape above.

    line 48

“Common” is measured: kept by at least 6 in 10 of the 35 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

TL;DR

Turn a long answer into something that can be read in ten seconds.

What to summarize

  • No argument: your previous answer in this conversation.
  • all: every finding and conclusion so far in this session, with later corrections replacing the earlier claims they correct.

Output

Exactly this shape, nothing before or after it:

**Verdict:** <one sentence that answers the user's question: yes / no / partly, and why>

- <finding 1>
- <finding 2>
- <finding 3>

**Next:** <the one thing to do, or "nothing">
  • The verdict is one sentence, at most about 25 words. Lead with the answer ("No, ...", "Yes, ...", "Partly: ...").
  • At most three findings, one line each, at most about 20 words each. Pick the ones that change what the user does. Fewer is fine.
  • A finding may end with one pointer (a file:line, test name or link) only when it is the main evidence.
  • "Next" is one action at most. Write "nothing" when there is no action.

Rules

  • Summarize only what was already said. Add no new claims, checks or opinions. If something looks wrong while summarizing, say so in one extra line after "Next" instead of silently fixing it.
  • If the answer corrected an earlier claim, the summary uses the corrected version.
  • Keep a caveat only if it changes the decision. Drop the rest.
  • Plain words. No jargon unless it is the name of the thing.
  • Never use the em dash character. Use straight quotes only.
  • No headers other than the ones in the shape above. No tables.

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.