BD droit-etrangers-asile
Expertise complète en droit français des étrangers, de l'asile et de la nationalité — entrée et visas, séjour (CESEDA livre IV, AES, étranger malade, regroupement familial, métiers en tension), éloignement et contentieux (OQTF, IRTF, rétention, référés, TA/CAA/CE), asile (OFPRA, CNDA, Dublin, CMA/ADA), nationalité et droits sociaux des étrangers (AME, PUMa, RSA, AAH, ASPA). Interroge en priorité trois connecteurs MCP complémentaires — OpenLegi (textes, jurisprudence administrative), LibreJustice (recherche sémantique tous ordres) et Legal Data Hunter (rétention/JLD, graphe de citations, statut de validité) — puis les sources officielles (Légifrance, ANEF, OFPRA, CNDA) et la doctrine associative (GISTI, Cimade, ADDE, Comede, Anafé). Déclencher dès qu'une question porte sur un étranger en France, même sans vocabulaire juridique — « papier de la préfecture », « récépissé périmé », « la CAF refuse le RSA » — et pour toute consultation, recours, note ou vérification de références dans ces matières.
Expertise complète en droit français des étrangers, de l'asile et de la nationalité — entrée et visas, séjour (CESEDA livre IV, AES, étranger malade…
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.
- 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: 11. 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") - note
frontmatter-keyunknown frontmatter key "last_verified" - note
frontmatter-keyunknown frontmatter key "freshness_window" - note
frontmatter-keyunknown frontmatter key "freshness_category" - note
frontmatter-keyunknown frontmatter key "verified_against"
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
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (droit-etrangers-asile) differs from the folder (droit-etrangers-asile-el-ouertani-faouzi)
- 70Execution cost. Instruction body is 4010 tokens
- 100Tools and files. No external tools needed
- 100Steps. 16 steps
- 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
- +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
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Structure: 9 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (9 of 9)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.