CD tabellion
Transforme un modèle juridique (.docx ou .odt : contrat, conclusions, assignation, courrier type, procès-verbal…) en formulaire HTML autonome, exécuté hors ligne, qui produit sans IA le document complété, fidèle au modèle, dans son format d'origine : parties optionnelles et alternatives, listes répétées, accords, montants et dates en lettres, calculs, numérotation et renvois. Déclencher dès que l'utilisateur veut « transformer ce modèle en formulaire », « automatiser un modèle », un « modèle à remplir » ou un « générateur d'actes », réutiliser régulièrement un contrat ou une trame, ou demande « fais-moi un modèle de … à remplir » ; aussi pour faire évoluer un formulaire tabellion existant. Pas pour compléter une seule fois un document. Compétence créée par Christophe Quézel-Ambrunaz, Université Savoie Mont Blanc (V.1.1).
Transforme un modèle juridique (.docx ou .odt : contrat, conclusions, assignation, courrier type, procès-verbal…) en formulaire HTML autonome, exécuté hors…
As a process D 39/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- 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: 24. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 39/100
- 0Result and completion. Does not say what the result is
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 40Consistency. Frontmatter name (tabellion) differs from the folder (tabellion-christophe-quezel-ambrunaz)
- 60Tools and files. Uses tools (python, node) that frontmatter does not declare
- 100Steps. 45 steps
- 100Execution cost. Instruction body is 2965 tokens
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 832: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -38 of 9 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Structure: 15 headings
- +3Step-by-step instructions: 45 items
- +4Reference files are cited in the instructions (4 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.