BB video-clip-editor
Video clip editing skill for automatically analyzing video content and generating CapCut draft templates. Uses local Whisper for speech transcription, Qwen-VL-Plus for visual scene description, and edge-tts for narration audio. Intelligently splits by dialogue/keywords/highlights, applies koubo jump-cut editing, and outputs draft_content.json ready to import into CapCut. Use this skill whenever the user mentions: video editing, clip, CapCut draft, highlight extraction, subtitle editing, keyword clipping, movie clip, narration, scene description, or uploads a video and asks to edit it.
As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7850 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 66/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Execution cost. Instruction body is 7850 tokens
- 100Steps. 17 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 17 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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
- -4Absolute local paths (C:\Users, /home/…): not portable
- -42 reference files, but SKILL.md never points to them: the model will not open them
- -35 of 10 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 591: enough signal without eating the budget
- +4Structure: 33 headings
- +3Step-by-step instructions: 17 items
- +4Has examples (31 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.