SKILLEMALL.ai

BF declaracion-renta-espana

Asistente para la Declaración de la Renta (IRPF) en España, ejercicio 2025. Dos modos de trabajo: (1) Revisión: analiza borradores de la AEAT o de haciendas forales, identifica deducciones no aplicadas y oportunidades de ahorro fiscal. (2) Preparación: calcula la declaración desde cero a partir de nóminas, certificados bancarios, facturas y otros documentos en bruto. Usa este skill siempre que el usuario mencione declaración de la renta, IRPF, borrador de Hacienda, deducciones fiscales en España, impuestos en España, renta 2025, campaña de la renta, Agencia Tributaria, preparar la renta, calcular la renta, autónomo/autónoma, o cualquier consulta relacionada con la fiscalidad personal en España. También cuando el usuario quiera revisar si su gestor ha incluido todas las deducciones posibles, o cuando suba un PDF/documento del borrador de la AEAT, o cuando quiera calcular su declaración a partir de documentación en bruto.

ClawHub Agent Skills author: José Conti v2025.4.1 MIT-0 31 files body ≈ 6 478 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process F 34/100 · Will not run — References files that are not bundled: references/regiones/[comunidad].md

ProcedureInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
B
81/100
safety, quality, tests
Safety 60%
100
Quality 40%
53
Run on models
none yet
Process rating
F
34/100
Will not run
References files that are not bundled: references/regiones/[comunidad].md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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: 31. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 6478 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/regiones/[comunidad].md

Process rating: all ten parameters 34/100

Will not run. References files that are not bundled: references/regiones/[comunidad].md
  • 0Tools and files. 1 referenced file(s) missing: references/regiones/[comunidad].md
  • 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
  • 70Execution cost. Instruction body is 6478 tokens
  • 100Steps. 167 steps
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. No mutating operations

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 933: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +4Structure: 19 headings
  • +3Step-by-step instructions: 167 items
  • +4Reference files are cited in the instructions (4 of 4)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.

External checks

ClawHub: clean
This instruction-only Spanish tax helper matches its stated purpose, but it handles very sensitive tax documents and should be used with redacted data and professional verification.
LLM: benign (high) · VirusTotal: · 29 May 2026