CD mandarinat
Assistant académique des enseignants-chercheurs en droit (professeurs, maîtres de conférences, doctorants, ATER, chargés de TD). Six tâches : recherche juridique approfondie à dominante doctrinale ; relecture de documents (thèses, articles, copies, mémoires) avec commentaires Word, vérification des références, indices de plagiat ou d'IA, cohérence argumentative ; sujets et corrigés d'examen ; mise à jour de cours, d'ouvrages et de documents ; création de cours avec support Word et PowerPoint ou Slides ; fiches de TD. Recherche outillée (LibreJustice, OpenLegi, Themia, LegalDataHunter, doctrine HAL/OpenAlex), noyau anti-hallucination avec tableau de vérification remis en document séparé. À utiliser pour toute demande liée à l'enseignement ou à la recherche en droit — cours, TD, examen, sujet, corrigé, dissertation, commentaire d'arrêt, relecture, mise à jour, bibliographie, recherche doctrinale — même si la skill n'est pas nommée. Pas pour les QCM ni les exercices rapides (skill qcm-exercices).
Assistant académique des enseignants-chercheurs en droit (professeurs, maîtres de conférences, doctorants, ATER, chargés de TD).
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: 30. 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. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (mandarinat) differs from the folder (mandarinat-christophe-quezel-ambrunaz)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 32 steps
- 100Execution cost. Instruction body is 3930 tokens
- low The response is described with custom markup (3 tags): a typed call is more reliable
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 1008: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -34 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 10 headings
- +3Step-by-step instructions: 32 items
- +4Reference files are cited in the instructions (20 of 20)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.