AF data-quality-audit
Independent cross-source audit of a completed CN banker deliverable. Use when the user asks to audit / double-check / 双核实 / 交叉验证 / 数据质量检查 / 审计 an existing deliverable directory. Re-fetches every hard number from the data-provenance.md table using an independent tier-2 source (Tushare vs 东方财富 vs 巨潮 vs FMP) and applies common-sense sanity rules (毛利率 in range / 收入增速 in range / 市值 = 股价 × 股本 / 毛利 = 营收 × 毛利率 / …). Emits an audit-report.md with PASS / FLAG / FAIL classification. This is a post-delivery QA step — the deliverable itself was already produced by customer-investigation / datapack-builder / ppt-deliverable.
Independent cross-source audit of a completed CN banker deliverable.
As a process F 41/100 · Will not run — References files that are not bundled: scripts/common-sense-rules.yaml
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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/common-sense-rules.yaml
Process rating: all ten parameters 41/100
- 0Tools and files. 1 referenced file(s) missing: scripts/common-sense-rules.yaml
- 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
- 70When it triggers. States when to use, but not when not to
- 100Steps. 32 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1454 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
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +3Description length 618: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 32 items
- +4Has examples (2 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.