BC clawcut
Generate AI-powered short videos from a topic or reference video using Google Gemini + Veo 3.1 on Vertex AI. Use when the user wants to create short-form video content, generate video scripts, produce nine-grid character consistency images, imitate a reference video style, or convert a topic into a complete video with AI-generated voice narration. Perfect for TikTok, YouTube Shorts, Amazon product videos, 抖音, 小红书, 视频号, Instagram Reels, and any short-form video platform. Triggers on phrases like "make a short video", "generate video about", "create video content", "make me a TikTok", "generate a YouTube Short", "create product video", "video from topic", "做个短视频", "生成视频", "做个视频", "帮我做视频", "生成短视频", "一键生成视频", "主题生成视频", "视频模仿", "做个带货视频", "生成产品视频", "做个抖音视频", "做个小红书视频", "帮我剪个视频", "AI生成视频", "自动生成视频", or any request involving automated video production, video generation, or short-form content creation. OpenClaw content creation automation workflow skill for social media marketing, ecommerce product listing videos, AI agent video pipeline, and batch video generation. Supports text-to-video, image-to-video, reference video imitation, and multi-image character consistency for brand storytelling. Built on Gemini 3 Pro (Nano Banana Pro), Veo 3.1, Google Vertex AI. Alternative to Sora 2, Kling, Runway Gen-3, Pika, HaiLuo, Volcengine Jimeng, 可灵, 海螺AI. Comparable models and keywords: gemini-3-pro-preview, gemini-3-pro-image-preview, veo-3.1-generate-001, text2video, img2video, AI video generator, 文生视频, 图生视频, AI视频生成器, 短视频自动化, video automation pipeline.
As a process C 57/100 · Has gaps — weak spots: result and completion, failures and branches, running it twice
How to improve
- Shorten the description to 1024 characters.
- 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
-
low Exfiltration
read-dotenvSKILL.md:63Reads a .env filecp assets/.env.example clawcut/.env
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1560 chars, limit 1024 - note
description-budgetdescription takes 1560 of the ~15000-char shared budget for all skills
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 20 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 509 tokens
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1560: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- -32 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 16 example trigger phrases
- +4Structure: 9 headings
- +3Step-by-step instructions: 20 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 53.