CD reel-faceless-f100k
Convierte un tema en un Reel 9:16 faceless (30-90 s) donde la usuaria GRABA la voz pero nunca sale en cámara. Escribe el guion con gancho, retención y cierre de venta, arma el teleprompter, recibe la nota de voz por Telegram, saca los tiempos (transcripción por API si hay llave, o estimados) y el Clip Director decide por gancho el visual de cada tramo (B-roll cinemático IA, card de dato, pixel-meme; mezcla obligatoria). Genera los clips con Higgsfield (con ✅ de créditos), renderiza las cards a PNG con Chromium y junta los clips en orden en un solo video mudo con ffmpeg concat. Entrega ese video + la voz + las cards + el plan para montar la voz y el texto en CapCut o Edits. Activar con 'hazme un reel faceless de X', 'video faceless sin mi cara', 'explainer faceless', 'convierte este tema en video sin grabarme en cámara', 'reel solo con mi voz'. NO para talking-head con su cara, VSL (broll-vsl-formula100k) ni carruseles.
Convierte un tema en un Reel 9:16 faceless (30-90 s) donde la usuaria GRABA la voz pero nunca sale en cámara.
As a process D 40/100 · Unfinished process — References files that are not bundled: assets/seg0.mp4
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 Edit AskUserQuestion mcp__higgsfield__generate_video mcp__higgsfield__generate_image mcp__higgsfield__job_status mcp__higgsfield__media_upload mcp__higgsfield__media_con
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") - warning
missing-refreference to a missing file: assets/seg0.mp4
Process rating: all ten parameters 40/100
- 0Tools and files. 1 referenced file(s) missing: assets/seg0.mp4
- 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
- 50Failures and branches. 0 branches, has a failure section
- 100Steps. 28 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2868 tokens
- 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 932: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +4Structure: 15 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.