agentleFS
anthony-chaudharyanthony-chaudhary/fak/.agents/skills/signal-first/SKILL.md

signal-first

Skill49 starsChanged 14 days agoApache-2.0View on GitHub

Shape an answer for fast scanning with result-first sentences, concrete verbs, compact structure, and selectable compression while preserving every correctness-critical detail. Use when the user asks for Caveman-style output, terse or low-token prose, executive scanning, fewer words, or a concise rewrite whose substance must remain intact.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Put the result, decision, or next action in the first line.

    line 28
  2. Distinctive:

    Use concrete nouns and active verbs.

    line 30
  3. Distinctive:

    Keep the evidence beside the claim it supports.

    line 32
  4. Distinctive:

    When compression competes with correctness, keep correctness and move to a lighter level.

    line 46
  5. Distinctive:

    every paragraph adds a new fact, reason, or action.

    line 53
  6. Distinctive:

    every claim retains its evidence or uncertainty.

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Signal First

Make the useful part easy to find and safe to act on.

Choose the compression level

Honor an explicit level. Otherwise select the lightest level that meets the request.

LevelShapeBest fit
lightAnswer first, then useful explanationTeaching, unfamiliar material, nuanced decisions
focusedResult first, then action-critical contextDefault for concise work and status updates
compressedShort subject-first lines and dense bulletsExpert readers, repeated workflows, operational handoffs
minimalShortest complete answer or requested artifactExact lookups, commands, confirmations, structured output

Expand one level when the task has ambiguity, meaningful tradeoffs, safety impact, or a novice audience. Compress one level when the format is exact or the reader already has the context.

Write the answer

  1. Put the result, decision, or next action in the first line.
  2. Give each line one job.
  3. Use concrete nouns and active verbs.
  4. Group parallel facts into compact bullets or a small table.
  5. Keep the evidence beside the claim it supports.
  6. End with the next checkable action when one exists.

Preserve substance

Include every detail that keeps the answer correct and usable:

  • safety boundaries and warnings;
  • uncertainty, assumptions, and material tradeoffs;
  • exact commands, code, identifiers, citations, and paths;
  • user-requested sections and output formats;
  • evidence needed to support completion or performance claims;
  • accessibility and respectful professional language.

When compression competes with correctness, keep correctness and move to a lighter level.

Final pass

Confirm that:

  • the first line carries the main result;
  • every paragraph adds a new fact, reason, or action;
  • every claim retains its evidence or uncertainty;
  • the response satisfies the requested format;
  • a reader can act without reconstructing omitted context.

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.