samber avatar

Humaniseur Fr

If you work with French content and you've ever gotten back text that sounds like it was translated from corporate English, this is for you. It hunts down 27 AI writing patterns specific to French: overuse of "crucial" and "notamment," anglicisms like "faire du sens," fake analysis with participle chains, formulaic openings like "À l'ère de," and typographic tells like curly quotes instead of guillemets. The rewrite instructions are smart about register. French professional writing is naturally more formal than English, so it won't dumb down soutenu prose into casual tone. It just strips the mechanical filler while keeping actual precision intact. Trigger it with "humaniser" or "déslopifier" and it runs a full scan plus final anti-AI pass.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.
5
skills.sh installs
5.6K
GitHub stars
242
last updated
Aug 21, 2026

Install

$ npx -y skills add samber/cc-skills --skill humaniseur-fr --agent claude-code

Installs into .claude/skills of the current project.

Files

Humaniseur : supprimer les patterns d'écriture IA du français

Your task

When given French text to humanize:

  1. Clarify the target register first - Abbreviations, argot, orality, emojis and typography all depend on the expected niveau de langage. If it is not clear from the request or the input (soutenu, courant, familier ? for which medium ?), ask the user before starting to humanize
  2. Identify AI patterns - Scan for all 38 patterns listed below
  3. Rewrite problematic sections - Replace AI-isms with natural French alternatives
  4. Preserve meaning - Keep the core message intact
  5. Maintain voice - Match the intended tone and register
  6. Add soul - Don't just remove bad patterns; inject actual personality (see Part 4)
  7. Do a final anti-AI pass - Ask: "Qu'est-ce qui rend ce texte évidemment généré par IA ?" Answer briefly with remaining tells, then ask "Maintenant, fais en sorte qu'il ne le soit plus" and revise accordingly. Apply the three-signal rule: one isolated marker is noise (most are normal French), but three or more co-occurring in the same passage make a reader flinch — revise until no paragraph accumulates three

Sponsors

Details

Repository
github.com/samber/cc-skills
Categories
Documentation, AI & Agent Building
First seen
Jul 14, 2026

More from samber/cc-skills

All 21
1trailofbits avatardwarf-experttrailofbits/skillsAnalyzes DWARF debug information in compiled binaries. Use when inspecting .debug_* sections, DIE trees, or DW_TAG_/DW_AT_ entries with dwarfdump/llvm-dwarfdump5.6Kskills.sh installs
2jeffallan avatarplaywright-expertjeffallan/claude-skillsUse when writing E2E tests with Playwright, setting up test infrastructure, or debugging flaky browser tests. Invoke to write test scripts, create page objects,5.6Kskills.sh installs
3affaan-m avatarcode-touraffaan-m/eccCreate CodeTour `.tour` files — persona-targeted, step-by-step walkthroughs with real file and line anchors. Use for onboarding tours, architecture walkthroughs5.5Kskills.sh installs
4forcedotcom avatarintegration-connectivity-connected-app-configureforcedotcom/sf-skillsSalesforce Connected Apps and External Client Apps OAuth configuration with 120-point scoring. Use this skill to configure OAuth flows, JWT bearer auth, Connect5.5Kskills.sh installs
5aws avatarmanaging-amazon-mskaws/agent-toolkit-for-awsOperates Amazon MSK Provisioned clusters (Standard and Express brokers). Required for ANY MSK Provisioned task — training data conflates Standard and Express, w5.5Kskills.sh installs
6trailofbits avataryara-rule-authoringtrailofbits/skillsGuides authoring of high-quality YARA-X detection rules for malware identification. Use when writing, reviewing, or optimizing YARA rules. Covers naming convent5.5Kskills.sh installs