CD ricerca-giuridica-it
Ricerca giuridica su fonti italiane e UE: normativa, prassi e giurisprudenza in ogni materia (civile, penale, amministrativo, lavoro, tributario e specialistiche). Usare quando l'utente chiede di trovare, inquadrare o citare una norma ("cosa dice l'articolo...", "quale legge disciplina...", "è ancora in vigore...", "che estremi ha..."), cercare sentenze, massime o orientamenti, verificare la vigenza di una disposizione, verificare una citazione o l'esistenza di una pronuncia ("questa sentenza esiste?", "controlla le citazioni di questo atto"), cercare precedenti a favore e contro una tesi ("conformi e difformi", "sentenze pro e contro"), trovare un CCNL o le decisioni di ABF, ACF, AGCM o del Garante, creare un documento fondato su fonti (atti, pareri, clausole, contratti, memorie, diffide), o impostare una strategia processuale ("come imposto la causa", "come gestiresti questo caso", "conviene agire o transigere"), anche quando la fonte non è nominata. Non usare per domande non giuridiche.
Ricerca giuridica su fonti italiane e UE: normativa, prassi e giurisprudenza in ogni materia (civile, penale, amministrativo, lavoro, tributario e…
As a process D 43/100 · 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.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 9. 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") - warning
body-longSKILL.md body ≈ 10860 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 43/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (ricerca-giuridica-it) differs from the folder (ricerca-giuridica-it-silvio-mistretta)
- 40Execution cost. Instruction body is 10860 tokens: crowds the task out of the window
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 133 steps
- 100Running it twice. No mutating operations
- low 16 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1004: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
- +4Structure: 25 headings
- +3Step-by-step instructions: 133 items
- +4Reference files are cited in the instructions (7 of 7)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.