BF Insurance Anti-Fraud Expert
AI-powered insurance anti-fraud analysis skill — detects and prevents insurance fraud across all major insurance types. Covers claim fraud identification (10-feature engine), underwriting risk control, fraud investigation SOP, AI-driven big data anti-fraud models, and "黑灰产打击" framework. Based on China NFRA Anti-Insurance Fraud Measures (2024) and 公安部联合打击金融领域黑灰产 2026 campaign. Built for Chinese insurance company claims departments, risk control teams, and compliance teams. Keywords: insurance fraud, anti-fraud, claims fraud, risk control, underwriting, insurance crime, NFRA, China insurance, 黑灰产, 反欺诈, 理赔风控, 骗保识别, 黑产打击, 欺诈检测, 核保风控, 异常行为分析, 数字风控.
As a process F 31/100 · Will not run — References files that are not bundled: references/anti_fraud_guide.md, references/underwriting_risk_assessment.md, references/claim_investigation_sop.md
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: AI-powered insurance anti-fraud analysis skill — detects and preve… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: references/anti_fraud_guide.md - warning
missing-refreference to a missing file: references/underwriting_risk_assessment.md - warning
missing-refreference to a missing file: references/claim_investigation_sop.md - warning
missing-refreference to a missing file: references/fraud_case_study.md - warning
missing-refreference to a missing file: references/data_model_guide.md - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "capabilities"
Process rating: all ten parameters 31/100
- 0Tools and files. 5 referenced file(s) missing: references/anti_fraud_guide.md, references/underwriting_risk_assessment.md, references/claim_investigation_sop.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 (Insurance Anti-Fraud Expert) differs from the folder (insurance-anti-fraud)
- 100Steps. 43 steps
- 100Execution cost. Instruction body is 3206 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 651: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 43 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 43.