agentleFS
Sign inStart free
zedarvateszedarvates/botte-secrete/skills/caveman/SKILL.md

caveman

Skill2 starsChanged 3 months agoMITView on GitHub

Produire un prompt de réponse concise ou analyser la taille d'un fichier en lecture seule. Ne compresse pas le fichier et ne mesure pas les économies d'un modèle.

184 other projects use a version of this.

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

Create a free account to mount
Files
SKILL.md

Caveman — concision explicite

Utiliser prompt pour obtenir une instruction de style à transmettre explicitement au modèle. Conserver la langue demandée, les négations, conditions, incertitudes, commandes, identifiants, preuves et conséquences. Privilégier la clarté.

NiveauStyle demandé
lightPhrases courtes, sans remplissage
fullPhrases ou fragments sans ambiguïté
ultraUn point court par ligne, avec les explications nécessaires
classicalChinois classique uniquement sur demande explicite de l'utilisateur
python -m skills.caveman.cli prompt --level light
python -m skills.caveman.cli compress mon_fichier.md --format json
python -m skills.caveman.cli stats

compress conserve son nom historique : il lit le fichier complet sans le modifier et rend une analyse de taille. --dry-run est un alias de ce comportement. Les octets UTF-8 sont mesurés ; les tokens sont estimés par caractères/4. Le texte rendu reste intact, son gain est donc nul. style_savings_pct: null signifie que le gain d'une future réponse du modèle reste non mesuré.

Les prompts sont dans prompts.py. Ces commandes n'injectent pas automatiquement de prompt et ne modifient ni le routage ni le budget de raisonnement. Comparer des sorties réelles appariées et leur qualité avant de publier un gain.

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.

Check your setup, free