AC zmm-cut
📐 詹明明·口播剪辑 ——口播成片剪辑技能。把拍好的素材剪成可发布的成片：**按文案规则做内容层重组**（删废镜头/去重复/重排顺序）→ 语音剪辑（去口癖/停顿）→ 加速 → 字幕 → B-roll → 交付。 🔴 **只删和重排，不加词** —— 说话人没说过的话一个字都不加。 詹明明账号的默认参数已固化（抖音 · 保持原长 · 1.15× · HarmonyOS Sans 粗体字幕 · 黄色 #FFE20A 高亮），**不需要每次重说**；换账号只改 §一 那张表，正文流程不变。 检测不到 ChatCut 会引导安装，并给出**本机转写旁路** —— 内容层的活全部不需要 ChatCut。 触发方式：/zmm-cut、/剪辑、/剪片、/zmm-剪、「把这条剪出来」「素材剪成成片」「去口癖」「加字幕」「这条视频剪一下」「重新排一下顺序」 Talking-head footage → publishable cut. Restructures content by copy rules (delete/reorder only, never add words), then cleans speech, speeds up, captions, B-roll. Falls back to local transcription when ChatCut is unavailable. Trigger: /zmm-cut, "cut this footage", "clean up the fillers", "add captions", "reorder this" —— 📐 詹明明 · 不给公式，给判据。每条规则都标了实测代价。
📐 詹明明·口播剪辑 ——口播成片剪辑技能。把拍好的素材剪成可发布的成片：按文案规则做内容层重组（删废镜头/去重复/重排顺序）→ 语音剪辑（去口癖/停顿）→ 加速 → 字幕 → B-roll → 交付。 🔴 只删和重排，不加词 —— 说话人没说过的话一个字都不加。 詹明明账号的默认参数已固化（抖音 · 保持原长…
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName"
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 54 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1587 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)
- +3Output format is not stated: the model decides each time
- -237 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +3Description length 731: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 54 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.