BC humaniseur-fr
Remove AI-writing patterns from French text and inject voice, personality, and soul. Use when editing, reviewing, rewriting, or cleaning up French content that reads like ChatGPT/Claude output. Humanize, humanise, déslopifier. Detects and fixes 27 patterns: AI vocabulary overuse (crucial, essentiel, notamment, par ailleurs, dans le paysage), anglicisms from English-first models (faire du sens, adresser un problème), copula avoidance, formulaic openings (À l'ère de, Dans le paysage actuel), superficial participle analyses (-ant), em dash overuse, redundant adjective doublets, rule of three, sycophantic tone, typographic tells (curly quotes instead of guillemets). Trigger on: humaniser, déslopifier, rendre plus humain, nettoyer le texte IA, enlever le slop, réécrire pour que ça sonne humain, make it sound human.
As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5993 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 13 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5993 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 62 steps
- 100Consistency. Name and required fields are in place
- medium 14 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 821: 120–800 characters recommended
- +4No input/output examples
- +2Single-language instructions
- +4Structure: 39 headings
- +3Step-by-step instructions: 62 items
- +3Output format is stated explicitly
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.