CF broll-vsl-formula100k
Genera entre 15-25 clips de B-roll cinematográficos para VSL o videos largos usando Higgsfield Seedance 2.0 y Cinema Studio 3.0. Regla 80/20: 80% de los clips incluyen el avatar/presentadora con foto de referencia (Seedance 2.0 + medias identity), 20% son tomas cinemáticas abstractas sin persona (Seedance 2.0 o Cinema Studio 3.0 puro). Estética configurable (default: cyberpunk azul eléctrico). Input: guion VSL (texto). Output: catálogo completo con URLs de video + frase exacta del guion donde insertar cada clip. Activar cuando se diga 'genera b-roll para mi VSL', 'clips para video largo', 'recursos cinematográficos para mi guion', 'haz los b-rolls de mi VSL', o cualquier variación que combine un guion largo (VSL, webinar, masterclass) con producir clips de b-roll con Higgsfield.
Genera entre 15-25 clips de B-roll cinematográficos para VSL o videos largos usando Higgsfield Seedance 2.0 y Cinema Studio 3.0. Regla 80/20: 80% de los clips…
As a process F 31/100 · No process to follow — References files that are not bundled: <URL>
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read Write AskUserQuestion mcp__higgsfield__generate_video mcp__higgsfield__job_status mcp__higgsfield__media_upload mcp__higgsfield__media_confirm
Files scanned: 1. 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
missing-refreference to a missing file: <URL>
Process rating: all ten parameters 31/100
- 0Tools and files. 1 referenced file(s) missing: <URL>
- 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 4233 tokens
- 85Steps. 43 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- low The response is described with custom markup (4 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)
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Description length 789: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 43 items
- +4Has examples (16 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.