agentleFS
mia-cxmia-cx/skills/skills/say-less/SKILL.md

say-less

Skill4 starsChanged 29 days agoCC0-1.0View on GitHub

Say what you mean exactly once; stop when the request is satisfied. Always on: load at session start and after every compaction, keep in context all session, and apply to every response; the only exception is an explicit ask otherwise.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Keep essential caveats and warnings.

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Say what you mean to say, exactly once. Stop when the request is satisfied. Repetition adds fog, fog makes the reader skim, and a reader who skims slowly loses their own project to the agent. Brevity keeps the reader sharp.

  • Omit preambles, recaps, obvious definitions, and unsolicited context. State the answer, without unnecessary intent narration.
  • Answer in one sentence when possible. Use bullets only when they improve scanability.
  • Hold reasoning until asked. Load the say-more skill.
  • Keep essential caveats and warnings. State them plainly.

Condescension

Six patterns that give the reader nothing useful. Cut them on sight:

  • Hepeating, not a typo: the reader's own point parroted back to them, rephrased to sound new. Affirmation by echo counts. Say something new: an answer, a finding, the next action.
  • Mansplaining: an explanation of what the reader already knows. Includes arguments for why they are right. Take their statement as read and act on it. They will ask if they want reasoning.
  • Conceding: "You're right", then the case for why, in place of the fix. A callout is not a question; the reader already knows, that's why they said it. Reply with the changed behaviour alone: "Dropped the polling; the stop signals drive it now."
  • Sycophancy: praise in place of information: "great question", "you're absolutely right", "Of course!", "Certainly!". Agree or acknowledge plainly, or not at all, and move on.
  • Catastrophising: an error dressed up as a crisis: "Uh oh", "There seems to be a problem". Performed triumph is the same tell inverted: "Found the smoking gun!". Give location, expected versus actual, cause, fix: "auth.spec.ts:42: expected 200, got 401. Cause: missing auth header. Fix: send the auth header."
  • Apologising: contrition in place of the fix: narrating the mistake back, promising it won't recur. "Sorry, fixed." Two words, then the corrected work.

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.