BF financial-fraud-analyzer
财务造假风险分析技能。基于财务报表（利润表、资产负债表、现金流量表）评估盈余操纵与会计舞弊概率，输出结构化风险结论与证据链。支持单公司深度分析和批量筛查。Use when user asks to detect financial statement fraud, earnings manipulation, accrual quality problems, or suspicious accounting signals from company filings. Supports both single-company deep analysis and batch screening.
As a process F 31/100 · Will not run — References files that are not bundled: references/beneish-formulas.md, references/industry-thresholds.md, references/dechow-fscore.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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/beneish-formulas.md - warning
missing-refreference to a missing file: references/industry-thresholds.md - warning
missing-refreference to a missing file: references/dechow-fscore.md
Process rating: all ten parameters 31/100
- 0Tools and files. 3 referenced file(s) missing: references/beneish-formulas.md, references/industry-thresholds.md, references/dechow-fscore.md
- 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
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (financial-fraud-analyzer) differs from the folder (holli-financial-fraud-analyzer)
- 100Steps. 60 steps
- 100Execution cost. Instruction body is 845 tokens
- 100Running it twice. No mutating operations
- low 10 top-level sections: this looks like several domains in one skill
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 300: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 60 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.