BF bank-credit-admission-review
面向银行风险条线（授信审批、风险管理岗）的授信准入审查专家能力，含「一般负面情况」红线快筛。输入企业客户信息（企业名称、行业、拟授信品种与金额、可获取资料如财报/征信/工商/舆情等），输出结构化准入初审报告。支持两种模式：①红线快筛——脚本确定性判定连续三年亏损（归母/合计双口径）、连续三年资产负债率超85%、当期年报净资产为负三条一票否决红线；②完整审查——覆盖经营、财务、管理层与股权、外部风险四维分析，标注信息来源可靠性与缺口，给出准入/有条件准入/不予准入结论及补充尽调清单，并内建方法论复盘与可累积规则库。触发词：授信准入、准入审查、信贷初审、信用风险审查、授信方案、审批辅助、信贷审查报告、负面情况、负面清单、准入红线、连续三年亏损、资产负债率超85%、净资产为负、一票否决、客户快筛、准入排查、bank credit admission、credit underwriting review。【前置依赖】需在本工作区连接 财汇MCP（企业预警通）连接器，方可拉取财报/公告/担保/司法/工商/股权质押等结构化权威数据；未连接时降级至公开来源（Neodata/WebSearch），数据完整度与时效性受限。
面向银行风险条线（授信审批、风险管理岗）的授信准入审查专家能力，含「一般负面情况」红线快筛。输入企业客户信息（企业名称、行业、拟授信品种与金额、可获取资料如财报/征信/工商/舆情等），输出结构化准入初审报告。支持两种模式：①红线快筛——脚本确定性判定连续三年亏损（归母/合计双口径）、连续三年资产负债率超85%、当期年…
As a process F 35/100 · Will not run — References files that are not bundled: references/provision_coverage.md, references/jishaofeng_methodology.md, references/docx_template.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: 23. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: references/provision_coverage.md - warning
missing-refreference to a missing file: references/jishaofeng_methodology.md - warning
missing-refreference to a missing file: references/docx_template.md - note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 35/100
- 0Tools and files. 3 referenced file(s) missing: references/provision_coverage.md, references/jishaofeng_methodology.md, references/docx_template.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
- 100Steps. 69 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3186 tokens
- 100Running it twice. No mutating operations
- low 11 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 510: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 69 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (17 of 17)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.