AC benchmark-due-diligence
Runs adversarial due-diligence on a benchmark the user envies — a founder, KOL, company, or product whose claimed success looks inflated — splitting marketing bubble from real signal, then mapping the validated playbook onto the user's own resources. Use whenever the user wants to 尽调/对标/拆解 a competitor or role-model, 抄/偷师 someone's playbook, suspects 水分/泡沫 in their claims (#1 on Product Hunt, 0-to-1M users, funding, 估值几个亿), asks whether wins are 真本事 vs 运气/时机, or says someone is 太成功了/crushing it and wants the real story — even if they never say 尽调. Prefer over deep-research for debunking inflated claims and extracting a replicable playbook rather than a neutral briefing.
Runs adversarial due-diligence on a benchmark the user envies — a founder, KOL, company, or product whose claimed success looks inflated — splitting marketing…
As a process C 52/100 · 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: 5. 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 52/100
- 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
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 28 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2225 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
- +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
- +1No license
- +2Single-language instructions
- +3Description length 678: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 28 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.