base: Skill for Claude Code

.ai/agents/base-contributor/skills/competences/human-writing/SKILL.md

human-writing is a skill for Claude Code from ai-swiss/base. It costs 22 tokens per session (613 once invoked), scanned A, original, Apache-2.0.

French writing rules for BASE documentation and other project prose. They cover punctuation, quotation marks, word choice, and consistent terminology.

In plain words
What is it for?
Use them when writing or reviewing French documentation, README files, governance text, or user-facing messages.
Why use it?
They help keep French text consistent and readable across files and prevent common style or automated-check failures. The rules also guide which technical terms should remain in English.

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/base-contributor/skills/competences/human-writing/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 human-writing

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai-swiss/base/human-writing"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/human-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 613 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 $0.00022 $0.00613
Opus 5.5 $0.00009 $0.00245
Sonnet 5.5 $0.00004 $0.00123
Haiku 4.5 $0.00002 $0.00061

Measured 1mo ago against content hash 7b9e76306b91, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

human-writing 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/base-contributor/skills/competences/human-writing/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conventions d'écriture (français)

Ces conventions valent pour toute la prose française de BASE: documentation, README, gouvernance, messages. Elles visent un rendu cohérent et soigné. Les barrières check-emdash et check-lexique en vérifient une partie automatiquement.

La règle qui prime est la cohérence: une seule convention, tenue d'un bout à l'autre. Un texte à moitié conforme trahit une relecture négligée.

Guillemets

Guillemets français «», en composition serrée, sans espace intérieure: «texte», et non «texte».

Ponctuation (usage suisse romand)

Pas d'espace avant les deux-points, le point-virgule, le point d'exclamation et le point d'interrogation: on écrit «un point:» et non «un point :».

Tiret cadratin

Aucun tiret cadratin dans un texte français (le tiret long, distinct du trait d'union et du tiret moyen). Utiliser les deux-points, une virgule, un point, des parenthèses, ou restructurer la phrase.

Anglicismes

Quand un terme français courant existe, le préférer: «point de friction» plutôt que «pain point», «transmission» plutôt que «handoff», «lacune» plutôt que «gap», «traiter un problème» plutôt que «adresser un problème». Garder les termes techniques établis (commit, hook, MCP, broker).

Quatre objets à ne jamais confondre

Toute présentation de BASE distingue explicitement quatre objets:

  • la méthode est la manière dont le travail est conduit: étapes, sources faisant autorité, règles, contrôles et décisions humaines;
  • la structure BASE est l'ensemble des ressources et des relations qui décrivent cette méthode;
  • la référence est la description approuvée et versionnée de la méthode à un instant donné;
  • l'exécution est ce qu'un modèle, un outil ou une intégration fait effectivement à partir de cette référence, dans un contexte donné.

La structure n'est donc pas la méthode elle-même, et la référence n'est pas son exécution. Une même référence peut conduire à des exécutions différentes selon le modèle, les outils, les données, les permissions et l'intégration. Écrire ce que BASE décrit, conserve, vérifie ou rend accessible. Ne jamais lui attribuer ce que seul le dispositif d'exécution accomplit, ni présenter la référence comme une garantie de comportement.

Read the full file on GitHub · 46 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 · +11 lines 7b9e76306b91
  2. 2mo ago First seen · 35 lines · 22 tokens per session scan A 97d32ed33409

Subscribe to this mod's changes

human-writing is a skill published in the GitHub repository ai-swiss/base (65 stars, last pushed 8d ago), licensed Apache-2.0. It adds 22 tokens to every session and 613 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

human-writing compared with skills from other repositories

human-writing next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
human-writingai-swiss/baseSkill658d agoApache-2.0A22Claude Code
complianceericrisco/rsc-harnessSkill5032d agoMITA96Claude Code, Codex
vs-item-onboardingvolcengine/SearchCLISkill1.2k21d agoApache-2.0B86Claude Code, Codex
wallet-cliBofAI/skillsSkill1644d agoMITA92Codex
translationsmendixlabs/mxcliSkill137yesterdayApache-2.0A80Claude Code
suikonwiizo/suikoSkill115yesterdayMITA192Codex
b2c-localizationSalesforceCommerceCloud/b2c-developer-toolingSkill58yesterdayApache-2.0A107Claude Code