CD recherche-theses-allison-fiorentino
Recherche, cartographie et analyse des thèses de doctorat françaises via theses.fr (API ABES) et TEL (HAL). Spécialisée droit avec filtrage par sous-disciplines juridiques. Ouverte sur d'autres domaines universitaires. Capacités : (1) recherche multi-critères — sujet, directeur, jury, établissement, école doctorale, période, statut soutenue/en préparation, discipline ; (2) cartographie académique — qui dirige sur quel sujet, qui siège dans quels jurys, réseaux de co-direction, écoles doctorales productives ; (3) analyses temporelles — évolution d'un sujet, détection de saturation, calendrier des soutenances à venir ; (4) filtrage sous-discipline juridique — droit privé, public, social, affaires, international, etc. Déclencher dès que l'utilisateur mentionne thèse, doctorat, directeur de thèse, jury de thèse, école doctorale, soutenance, doctorant, ou demande une analyse d'écosystème doctoral. Pour articles ou ouvrages de doctrine, utiliser plutôt recherche-doctrine.
Recherche, cartographie et analyse des thèses de doctorat françaises via theses.fr (API ABES) et TEL (HAL). Spécialisée droit avec filtrage par…
As a process D 44/100 · 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: 2. 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 44/100
- 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
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 70Execution cost. Instruction body is 4425 tokens
- 100Steps. 38 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- low 12 top-level sections: this looks like several domains in one skill
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 980: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 27 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.