SKILLEMALL.ai
GitHub ↗ RU Sign in

CD recursos-de-video-formula100k

Convierte un video grabado por la usuaria en un set de RECURSOS de edición (B-roll, overlays, referencias visuales) y un MANIFEST.md para montarlos en su editor. 4 modos: (1) IA — pixel-avatar mascot e infografía pixel generados con Higgsfield, fondo quitado; (2) WEB — recursos reales de Pinterest, Google Imágenes, TikToks virales (como link) y noticias, sin stock; (3) HÍBRIDO — ambos por momento; (4) UI/TUTORIAL — capturas tipo terminal/callout/paso con capturas-tutorial-formula100k. Admite capturas propias. Trabaja sobre la transcripción o el .srt del video; no edita ni renderiza el video. Activar cuando la usuaria mande un video o su .srt y diga 'cázame recursos para este video', 'busca b-roll real', 'tráeme recursos web', 'mezcla IA + recursos reales', 'overlays UI para mi tutorial'. Entrega: carpeta en entregables/ + MANIFEST.md en .zip por Telegram.

ClawHub Agent Skills author: Fórmula 100K v1.0.0 MIT-0 1 file body ≈ 13 993 tokens Open the sourceclawhub.ai↗ analyzed 8 d ago

Convierte un video grabado por la usuaria en un set de RECURSOS de edición (B-roll, overlays, referencias visuales) y un MANIFEST.md para montarlos en su…

As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureTelegramMedia and videotype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
78/100
safety, quality, tests
Safety 60%
94
Quality 40%
53
Run on models
none yet
Process rating
D
46/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

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.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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.
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 · 2

✓ No critical or high findings

Medium and low: 2
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: Bash Read Write Edit AskUserQuestion Skill mcp__higgsfield__generate_image mcp__higgsfield__job_status mcp__higgsfield__job_display mcp__claude_ai_supadara__supadata_scrape mcp__claude_
  • low Dangerous commands cmd-pipe-to-shell-known-host SKILL.md:581
    Pipe-to-shell installer from a well-known host (still executes remote code) (quoted — discussed, not commanded)
    command: "curl -fsSL https://claude.ai/install.sh | bash"
    quoted

Files scanned: 1. 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 ≈ 13993 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "delegates-to"

Process rating: all ten parameters 46/100

  • 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
  • 30Running it twice. 1 mutating operations with no state check
  • 40Execution cost. Instruction body is 13993 tokens: crowds the task out of the window
  • 50Failures and branches. 0 branches, has a failure section
  • 60Steps. 200 steps, 4 vague phrases
  • 100Tools and files. Tools declared in frontmatter
  • 100Consistency. Name and required fields are in place
  • low 10 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (41 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)
  • +3Description length 867: 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: 34 headings
  • +3Step-by-step instructions: 200 items
  • +4Has examples (23 code blocks)

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

External checks

ClawHub: suspicious
The skill mostly matches its video-resource purpose, but it should be reviewed because it may upload personal face photos to an external service and contains conflicting OpenClaw instructions about downloads and delivery.
LLM: suspicious (medium) · 17 Sept 2026