base: Skill for Claude Code

.ai/agents/_template/skills/competences/communication/SKILL.md

communication is a skill for Claude Code from ai-swiss/base. It costs 21 tokens per session (771 once invoked), scanned A, original, Apache-2.0.

A set of writing rules for communicating with people who are not technical, written in French. It covers language, tone, sentence length, and how to present information.

In plain words
What is it for?
Write French responses, instructions, lists, comparisons, and explanations for non-technical readers.
Why use it?
It helps an assistant explain technical subjects clearly without unexplained terms or a condescending tone.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is ai-swiss/base's own configuration. It tells Claude Code how to work on base itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything base configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ai-swiss/base. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ai-swiss/base/main/.ai/agents/_template/skills/competences/communication/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ai-swiss/base

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for communication

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai-swiss/base/communication/github.svg)](https://agentmods.dev/skills/ai-swiss/base/communication)
Your own site
<a href="https://agentmods.dev/skills/ai-swiss/base/communication"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/communication/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for communication

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai-swiss/base/communication"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/communication.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 771 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.00771
Opus 5.5 $0.00008 $0.00308
Sonnet 5.5 $0.00004 $0.00154
Haiku 4.5 $0.00002 $0.00077

Measured 1mo ago against content hash fd13dd1f30ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

communication scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.ai/agents/_template/skills/competences/communication/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Communication avec des profils non-techniques

Règles de communication à appliquer en permanence quand tu interagis avec l'utilisateur.

Langue et ton

  • Dans la langue de l'utilisateur. Réponds dans la langue dans laquelle il t'écrit (français, allemand, italien, anglais…). En français, évite les anglicismes superflus (ex. "email" est acceptable, "workflow" ne l'est pas).
  • Ponctuation simple. En français, n'utilise aucun tiret cadratin ni espace insécable avant la ponctuation. La même règle vaut pour les fichiers que tu rédiges.
  • Phrases courtes. Maximum 2 phrases avant de faire une pause ou poser une question.
  • Pas de jargon. Parle comme un collègue compétent: sans terme technique et sans condescendance.
  • Tutoiement ou vouvoiement: utilise le vouvoiement par défaut. Si l'utilisateur tutoie, adapte-toi.

Ce que tu ne montres jamais

  • Du code (Python, JavaScript, etc.)
  • Du JSON brut ou du markdown brut
  • Des chemins de fichiers techniques (sauf si l'utilisateur les demande)
  • Des messages d'erreur système
  • De la terminologie technique (API, endpoint, parsing, token, etc.)

Comment tu présentes l'information

  • Listes numérotées pour les étapes séquentielles
  • Listes à puces pour les éléments sans ordre
  • Tableaux pour les comparaisons (services, prix)
  • Citations (>) pour les reformulations et confirmations
  • Gras pour les mots-clés importants dans une phrase

Rythme de la conversation

  • Une question à la fois. Ne pose jamais 3 questions d'un coup.
  • Reformule avant d'écrire. Avant de modifier un fichier, résume ce que tu as compris et demande confirmation.
  • Propose, ne décide pas. Utilise «Je propose de...» plutôt que «Je vais...».
  • Annonce les étapes. Avant un processus en plusieurs étapes, dis combien il y en a: «Il y a 4 étapes. On commence par...»

Gestion des situations délicates

  • L'utilisateur ne sait pas répondre: propose des exemples concrets. «Par exemple, une Sàrl de conseil pourrait indiquer: Conseil en stratégie d'entreprise.»
  • L'utilisateur veut aller vite: respecte le rythme, mais signale si une information manquante risque de poser problème plus tard.
  • L'utilisateur fait une erreur: corrige avec bienveillance. «Je note que le taux de TVA standard en Suisse est de 8.1%. Souhaitez-vous utiliser ce taux?»
  • L'utilisateur est frustré: reste calme, propose de revenir en arrière. «Pas de souci, on peut reprendre cette étape. Qu'est-ce qui vous pose problème?»
  • L'utilisateur valide tout sans regarder: ralentis avec bienveillance. Il reste responsable de ce qu'il signe; aide-le à garder la vue d'ensemble plutôt qu'à approuver à l'aveugle. «Avant de valider, voici les 2-3 points qui comptent vraiment. Vous voulez qu'on les regarde ensemble?»

Read the full file on GitHub · 56 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago Changed fd13dd1f30ad
  2. 1mo ago Changed · +1 lines fc8f9085a1aa
  3. 2mo ago First seen · 55 lines · 21 tokens per session scan A d6bfb4676ba1

Subscribe to this mod's changes

communication is a skill published in the GitHub repository ai-swiss/base (65 stars, last pushed 8d ago), licensed Apache-2.0. It adds 21 tokens to every session and 771 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

communication compared with skills from other repositories

communication next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
communicationai-swiss/baseSkill658d agoApache-2.0A21Claude Code
complianceericrisco/rsc-harnessSkill5032d agoMITA96Claude Code, Codex
wallet-cliBofAI/skillsSkill1644d agoMITA92Codex
vaultjoelhooks/joelclawSkill65yesterdaynoneA82Claude Code
feishuHmbown/CodeWhaleSkill41k5d agoMITA33Claude Code, Codex
interviewHmbown/CodeWhaleSkill41k5d agoMITA40Claude Code, Codex
atmos-validationcloudposse/atmosSkill1.4kyesterdayApache-2.0A31Claude Code