AC aikey-resonate
AI KEY·戳不戳得中人 ——共鸣诊断技能。不从理论出发，从观众出发：这条内容让观众带走了哪一种收获（原来是这样 / 我就说吧 / 他替我说了），会不会动手（收藏 / 转发 / 评论 / 关注），每个判断都指到原文并标它是证据、推断还是待验证。模式A 诊断自己的草稿；模式B 拆一条别人的爆款反推可借的角度；模式C 判一句「我觉得不对劲」背后是一件事还是一群人的事。与 aikey-review 正交：review 防句废，resonate 防结构散。不负责逐句红线和能不能发（→ aikey-review）、哪一拍会划走（→ aikey-flow）、写标题或开头（→ aikey-title / aikey-hook）。 触发方式：/aikey-resonate、/戳不戳人、/共鸣、/aikey-共鸣、「这稿有没有戳中人」「会不会没人看」「这条为什么能火」「拆一下这个爆款」「受众到底想听什么」「这事值不值得拍一条」「我总觉得哪里不对但说不上来」「这是我一个人的事还是大家的事」 Resonance diagnosis, audience-first: which takeaway the piece delivers, which action impulse it triggers, with every claim tied to a quoted line and labelled evidence / inference / to-verify. Mode A: your draft. Mode B: decode a hit. Mode C: test whether a hunch is one incident or a pattern. Not for: line-level red lines and publish-readiness (aikey-review), drop-off beats (aikey-flow), writing titles or openings (aikey-title / aikey-hook). Trigger: /aikey-resonate, "will this resonate", "why did this blow up", "decode this viral post" —— AI KEY · 不给公式，给判据。每条规则都标了实测代价。
AI KEY·戳不戳得中人 ——共鸣诊断技能。不从理论出发，从观众出发：这条内容让观众带走了哪一种收获（原来是这样 / 我就说吧 / 他替我说了），会不会动手（收藏 / 转发 / 评论 / 关注），每个判断都指到原文并标它是证据、推断还是待验证。模式A 诊断自己的草稿；模式B 拆一条别人的爆款反推可借的角度；模式C…
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. 33 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1586 tokens
- 100Running it twice. No mutating operations
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
- +3Description length 1018: 120–800 characters recommended
- +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
- +4Structure: 15 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.