agentleFS
grinbuddygrinbuddy/claude-skills/skills/tldr/SKILL.md

tldr

Skill0 starsChanged 35 days agoMITView on GitHub

Plain-English recap for a reader who has lost the thread — what happened, whether anything is wrong, and exactly what is needed from them, with no jargon. Use when the user says "tldr", "I'm lost", "in layman's terms", "plain English", "what just happened", "what do you need from me", or seems overwhelmed by a long or technical reply.

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

10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 35 edited versions we read keep these.

  • 10

    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:

    Use these four parts, in this order, with these plain headings.

    line 18
  2. Distinctive:

    If nothing is needed, say "Nothing right now."

    line 31
  3. Distinctive:

    Aim for 150 to 250 words: If it runs longer, you are explaining, not summarising.

    line 48
  4. Distinctive:

    Never soften or drop bad news to keep it simple.

    line 53
  5. Distinctive:

    Never drop a decision because it is hard to explain.

    line 54
  6. Distinctive:

    If something was not checked or not run, say so plainly.

    line 56
  7. Distinctive:

    Do not claim the reader approved anything they have not approved.

    line 57
  8. Distinctive:

    Read each sentence and ask: would a bright friend who has never seen this project understand it?

    line 61
  9. Distinctive:

    If not, rewrite that sentence.

    line 63
  10. Distinctive:

    If the user has had to ask for plain language more than once, and a memory or preferences system is available, save that as a standing …

    line 69

“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

TLDR

The reader is smart but has lost the thread. Your last replies were too long, too technical, or assumed labels they don't carry in their head. Give them the whole picture in under a minute of reading, then stop.

This is a rewrite of what you already know, not new work. Do not run new investigations to produce it. If something is unverified, say so in plain words rather than going to check.

Shape of the answer

Use these four parts, in this order, with these plain headings.

  1. Bottom line — one or two sentences. Answer the two questions the reader actually has: "Is anything broken?" and "Do I need to do something right now?" Lead with bad news if there is any.
  2. What happened — two to four bullets. What was done and why it matters, in everyday words. Say what did NOT change when that is the reassuring part ("this is paperwork; the product behaves the same").
  3. What I need from you — a numbered list, most important first. Each item is one decision or one action, and says:
    • what to do or decide, phrased so a one-word reply works;
    • your recommendation, in one clause;
    • what happens if they do nothing. If nothing is needed, say "Nothing right now."
  4. What can wait — one or two lines on things that are parked and need no attention. Do not list them all; name the group.

Language rules

  • No labels on their own. Ticket numbers, decision-log numbers, checkpoint names, file names, branch names, commit hashes, tool names and acronyms are out. Describe the thing by what it does. If the reader will need a label to find, click or type something, put it in brackets AFTER the plain description: "the settings file is almost at its size limit (TICKET-123)".
  • Swap jargon for its effect. Not "CI is red on pip-audit" but "one of the automatic safety checks is failing because a library needs an upgrade; it is a known item and nothing is at risk today."
  • Short sentences, everyday words. One idea per sentence.
  • No tables, no code blocks, no nested bullets.
  • Numbers only when they change the decision.
  • Aim for 150 to 250 words. If it runs longer, you are explaining, not summarising; cut.

Honesty rules

  • Never soften or drop bad news to keep it simple. Simple words, same truth.
  • Never drop a decision because it is hard to explain. Find the plain version of it.
  • If something was not checked or not run, say so plainly.
  • Do not claim the reader approved anything they have not approved.

Check before sending

Read each sentence and ask: would a bright friend who has never seen this project understand it? Does every request say exactly what reply you need? If not, rewrite that sentence.

Afterwards

  • Stay at this level for the rest of the session. Offer depth ("say 'more' on any item") instead of supplying it.
  • If the user has had to ask for plain language more than once, and a memory or preferences system is available, save that as a standing preference so future sessions start in plain language.

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.