AF cn-client-investigation
China mainland client investigation and banker-grade analysis with strict guards for Chinese text accuracy and data provenance. Use when the target is an A-share / STAR / ChiNext / HK-H or private-unicorn Chinese company and the deliverable must not contain Chinese character-level typos or fabricated numbers. Triggers: 中国 / A股 / 港股 / 中概股 / STAR Market / 创业板 / 北交所 / CNINFO / 巨潮 / 天眼查 / Tushare. This skill supersedes the generic customer-investigation + datapack-builder flow for China targets.
As a process F 53/100 · Will not run — References files that are not bundled: references/data-provenance.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 22. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/data-provenance.md
Process rating: all ten parameters 53/100
- 0Tools and files. 1 referenced file(s) missing: references/data-provenance.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4978 tokens
- 100Steps. 67 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (3 tags): a typed call is more reliable
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)
- -36 of 16 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 496: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 67 items
- +3Output format is stated explicitly
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.