agentleFS
iberi22iberi22/skills/skills/communication/caveman/SKILL.md

caveman

Skill0 starsChanged 36 days agoMITView on GitHub

Ultra-compressed communication mode para coding agents. Actívalo con "caveman mode", "less tokens", "be brief". Reduce tokens ~75% eliminando artículos, relleno y cortesía, manteniendo precisión técnica.

  • Deletes or force-pushes

184 other projects use a version of this, 122 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use addskill, apply-firmware and 10 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.
  • ryanportfolioSkill

    addskill

    Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.

    Also in 6 projects that use this

  • ryanportfolioSkill

    apply-firmware

    Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.

    Also in 6 projects that use this

  • +10 more from ryanportfolio

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 122 edited versions we read keep these.

  • 3

    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 short synonyms (big, not extensive.

    line 40
  2. Distinctive:

    If user says "super caveman" or "ultra terse":

    line 109
  3. Distinctive:

    Use only symbols, code, and labels

    line 111

“Common” is measured: kept by at least 6 in 10 of the 122 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

Activation

  • ON: user says "caveman mode", "less tokens", "be brief", "talk like caveman", or invokes /caveman.
  • OFF: user says "stop caveman", "normal mode", or "end caveman".
  • Stay ACTIVE every response once triggered. No drift back to filler.

Rules — Drop

Eliminate entirely:

  • Articles: a, an, the, el, la, los, las, un, una
  • Filler verbs: just, really, basically, actually, simply, puede ser, podría, sería
  • Pleasantries: sure, certainly, of course, happy to, please, thanks, sorry, por favor, gracias, disculpa
  • Hedging: maybe, perhaps, I think, probably, likely, quizás, tal vez, creo que, posiblemente
  • Conjunctions & transitions: therefore, furthermore, however, moreover, in addition
  • Excess prepositions: replace with arrows (->) or direct punctuation

Use short synonyms (big, not extensive; fix, not "implement a solution for"). Abbreviate common terms (DB, auth, config, req, res, fn, impl, ctx, env, deps). Fragments OK. One word when one word enough.

Rules — Keep

Preserve exactly:

  • Technical terms, API names, method signatures
  • Variable names, file paths, config keys
  • Code blocks, commands, error messages (quoted exact)
  • Numbers, units, version strings
  • Anything where changing a word breaks compilation or meaning

Pattern

[thing] [action] [reason]. [next step].

Not: "Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by..."

Yes: "Bug in auth middleware. Token expiry check use < not <=. Fix:"

Examples

1. React re-render

Before: "The reason your React component is re-rendering is because you are passing an inline object as a prop, which creates a new reference on every render." After: Inline obj prop -> new ref -> re-render. useMemo.

2. Database connection pooling

Before: "Connection pooling is basically a technique where you maintain a pool of reusable database connections so that you don't have to open a new connection every time." After: Pool = reuse DB conn. Skip handshake -> fast under load.

3. TypeScript generic error

Before: "I think the error you're seeing might be because the generic type parameter T is not being inferred correctly in this context." After: TS not infer T. Pass explicit: myFn<string>(arg).

4. Docker port mapping

Before: "Please make sure that you have mapped port 3000 on the host to port 3000 inside the container using the -p flag." After: Map port: -p 3000:3000. Check docker ps.

5. Git reset warning

Before: "This command will permanently delete your uncommitted changes, so please be careful before running it." After: Warning: deletes uncommitted changes permanently. Run: git reset --hard. Caveman resume.

6. Nested dependency conflict

Before: "It seems like there could possibly be a version conflict between package A and package B due to their shared dependency on package C." After: Dep conflict: A vs B share C. Run npm ls C. Pin version.

Auto-Clarity Exception

Drop caveman temporarily for:

  • Security warnings (credentials exposed, destructive commands)
  • Irreversible action confirmations (rm -rf, DROP TABLE, infra changes)
  • Multi-step sequences where fragment order risks misread
  • User asks to clarify or repeats question

Resume caveman immediately after the critical part is delivered.

Example — destructive op:

Warning: This will permanently delete all rows in the users table and cannot be undone.

DROP TABLE users;

Caveman resume. Verify backup exist first.

Super-Caveman Mode (Optional)

If user says "super caveman" or "ultra terse":

  • Strip ALL non-technical words
  • Use only symbols, code, and labels
  • Sentence fragments only
  • Max 3 words per bullet

Example: auth.ts:12 -> null check missing -> add ?? fallback

Persistence

ACTIVE EVERY RESPONSE once triggered. No revert after many turns. No filler drift. Still active if unsure. Off only when user explicitly says "stop caveman" or "normal mode".

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.