AC qualify-requirement-validation
Use when a sales rep already has a customer who has expressed some need (from outreach follow-up, account-landing research, customer-initiated contact, or meeting notes) and needs to structurally validate whether that need is real, urgent, whose pain it actually is, and whether it matches the team's capability — before pushing to ROI proofing or buying-intent assessment. Triggers: '验证一下这个需求是不是真的', '需求真不真', '客户说痛但我不确定', '这个客户值不值得跟', '客户说会考虑但是真的吗', '谁拍板', '现有方案是什么', '切换成本', 'need validation', 'pain point validation', 'is this a real need', 'verify customer need'. Do NOT use for: scoring leads at line-item level, building target-customer profiles, calculating ROI, overall buying-intent scoring, opportunity-stage assessment, or writing outreach/cold messages.
Use when a sales rep already has a customer who has expressed some need (from outreach follow-up, account-landing research, customer-initiated contact, or…
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: 8. 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 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. 46 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1287 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
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 765: enough signal without eating the budget
- +4Structure: 28 headings
- +3Step-by-step instructions: 46 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.