AC aikey-flow
AI KEY·哪里会被划走 ——口播稿「划走点」专项。替观众把稿子听一遍：每一拍观众手里有什么、在等什么，断在哪一拍 —— 等的没来、手里有了还在给、正在给的听不清。诊断完默认主动问是否标记式改稿。不负责发布红线和能不能发（→ aikey-review）、内容戳不戳人（→ aikey-resonate）、单独换开头或标题（→ aikey-hook / aikey-title）。 触发方式：/aikey-flow、/会不会划走、/顺稿、/aikey-顺稿、「这稿子顺不顺」「哪里会划走」「逻辑有没有断」「读起来卡不卡」「完播会不会掉」 Drop-off check for talking-head scripts: walk the script as a listener, beat by beat — what the viewer holds, what they are waiting for, and where that chain breaks. Not for: red lines and publish-readiness (aikey-review), whether it resonates (aikey-resonate), replacing just the opening or title (aikey-hook / aikey-title). Trigger: /aikey-flow, "does this script flow", "where will viewers drop off", "check retention risk" —— AI KEY · 不给公式，给判据。每条规则都标了实测代价。
AI KEY·哪里会被划走 ——口播稿「划走点」专项。替观众把稿子听一遍：每一拍观众手里有什么、在等什么，断在哪一拍 —— 等的没来、手里有了还在给、正在给的听不清。诊断完默认主动问是否标记式改稿。不负责发布红线和能不能发（→ aikey-review）、内容戳不戳人（→…
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 3. 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 57/100
- 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
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 23 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 998 tokens
- 100Running it twice. No mutating operations
- low 11 top-level sections: this looks like several domains in one skill
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 3 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 729: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.