SKILLEMALL.ai

CF zencreator-video Skill\n\n## Overview\n\nZenCreator.pro is a professional, uncensored NSFW AI content generator for phot

zencreator video skill

modbender/skill-library-mcp Agent Skills author: modbender MIT 1 file body ≈ 665 tokens Open the sourcegithub.com analyzed 2 d ago

zencreator video skill

As a process F 24/100 · Will not run — weak spots: steps, result and completion, when it triggers

GeneratorMedia and videotype and topics are labelled automatically from the skill text
JSON
Technical rating
C
74/100
safety, quality, tests
Safety 60%
100
Quality 40%
34
Run on models
none yet
Process rating
F
24/100
Will not run
Steps w 15
0
Result and completion w 14
0
When it triggers w 12
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.
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: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error name-long name is longer than 64 chars
  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning description-short description under 40 chars: too little signal for triggering
  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 24/100

  • 0Steps. Prose only: no discrete steps
  • 0Result and completion. Does not say what the result is
  • 0When it triggers. No condition that starts the skill
  • 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
  • 40Consistency. Frontmatter name (zencreator-video Skill\n\n## Overview\n\nZenCreator.pro is a professional, uncensored NSFW AI content generator for photos and videos. Full creative freedom, no content filters. Supports high-quality image-to-video and video-to-video generation using models like Kling, Wan, Seedance Pro.\n\n- **Website**: https://zencreator.pro\n- **App**: https://app.zencreator.pro (requires account & credits)\n- **Video Features**: Image-to-Video (start frame, start/end frame), Video-to-Video (animate/replace), Lipsync\n- **Qualities**: Up to 1080p, 5-10s clips\n- **Credits**: e.g., Kling 720p 5s = 7 credits, Seedance Pro 1080p 10s = 15-30 credits\n\nGet 30 free credits on signup. Buy more via card/crypto.\n\n## Requirements\n- ZenCreator account logged in\n- Credits balance\n- Use `profile=\"chrome\"` in browser tool (attach your logged-in Chrome tab)\n\n## Usage\n\n1. Open https://app.zencreator.pro/ai-video-generator in Chrome\n2. Click OpenClaw Browser Relay toolbar button to attach tab\n3. Use `browser` tool with `profile=\"chrome\"`:\n - `snapshot` to inspect UI\n - `act` to click/type/upload\n\n### Text → Video\n1. Generate image (use text-to-image tool or manually)\n2. Image → Video\n\n### Image → Video\n- Upload image\n- Select model (e.g., \"Seedance Pro Fast Start Frame 1080p\")\n- Prompt: motion description (\"woman dancing sensually\", NSFW ok)\n- Generate → Download\n\n## Example Prompts (NSFW OK)\n\nFrom ZenCreator AI University:\n\n- \"A beautiful woman slowly undressing, seductive gaze, cinematic lighting\"\n- \"Couple in intimate embrace, passionate kiss, soft bedroom lighting\"\n- \"Model posing in lingerie, slow rotation, professional studio\"\n\nMotion: \"gentle head turn and smile\", \"sensual body wave\", \"walking towards camera\"\n\n## Tool Calls Example\n```\n# Snapshot UI\nbrowser action=snapshot profile=\"chrome\" targetUrl=\"https://app.zencreator.pro/ai-video-generator\"\n\n# Upload image\nbrowser action=act request={kind: \"upload\", path: \"/path/to/image.png\"} profile=\"chrome\"\n\n# Enter prompt\nbrowser action=act request={kind: \"type\", ref: \"prompt-input\", text: \"sensual dance\"} profile=\"chrome\"\n\n# Select model, generate\n# ...\n```\n\n## Credit Costs\n| Model | 5s 720p | 10s 720p |\n|-------|---------|----------|\n| Kling 2.1 Start | 7 | 13 |\n| Wan 2.5 Audio 720p | 10 | 20 |\n| Seedance Pro 1080p Start/End | 15 | 30 |\n\n## Install\nPlace `zencreator-video.skill/` in workspace. Restart agent or run `openclaw skill load zencreator-video.skill`\n\n## Notes\n- Uncensored: NSFW content allowed\n- Privacy: End-to-end encrypted\n- High quality: 4K upscale available separately) differs from the folder (zencreator-video-skill)
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 100Execution cost. Instruction body is 665 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 22: 120–800 characters recommended
  • +4Structure: 1 headings, hard to scan
  • +3No numbered steps or checklist
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Has examples (1 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 34.