AC video-cut
End-to-end turn an unedited long-form talking-head / vlog / podcast video into a compact "first cut" (rough cut). Use when asked to edit/剪辑 a raw YouTube (or local) video into a tighter version: download, word-level transcribe, diagnose bad-edit spots (slow intro, fillers, dead air, tangents, rambling), decide cuts in a JSON edit plan (each kept/dropped span with in/out + a one-line reason), render with ffmpeg, then self-check the result (re-transcribe + frame/black/ silence checks). Triggers: "剪成第一版", "rough cut", "first cut", "压缩时长", "把这条原片剪短", "cut down this video".
End-to-end turn an unedited long-form talking-head / vlog / podcast video into a compact "first cut" (rough cut).
As a process C 60/100 · Has gaps — weak spots: result and completion, progress reporting
How to improve
- 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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 22 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3477 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 575: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (13 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 9 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 100.