BF expense-report-wizard
出差报销整理向导。零配置即用——发票照片 AI 视觉直接识别，按类别+时间整理发票、重建行程日志、生成报销单、自动计算差补、税额分离、退改签/红字发票处理、合规审查（连号发票/人均超标/证据链/住宿缺失/交通断链/抬头核对/发票章检测）。已接入在线文档/批量 OCR/会议日程等服务时自动增强。触发：帮我整理报销、做报销单等。
出差报销整理向导。零配置即用——发票照片 AI 视觉直接识别，按类别+时间整理发票、重建行程日志、生成报销单、自动计算差补、税额分离、退改签/红字发票处理、合规审查（连号发票/人均超标/证据链/住宿缺失/交通断链/抬头核对/发票章检测）。已接入在线文档/批量…
As a process F 34/100 · Will not run — References files that are not bundled: references/policy-template.md, references/invoice-types.md, scripts/rename_files.py
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
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: references/policy-template.md - warning
missing-refreference to a missing file: references/invoice-types.md - warning
missing-refreference to a missing file: scripts/rename_files.py - warning
missing-refreference to a missing file: references/reimbursement-templates.md - warning
missing-refreference to a missing file: scripts/amounts.py - warning
missing-refreference to a missing file: references/compliance-rules.md - note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 34/100
- 0Tools and files. 6 referenced file(s) missing: references/policy-template.md, references/invoice-types.md, scripts/rename_files.py
- 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
- 70Execution cost. Instruction body is 4627 tokens
- 100Steps. 81 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- low 17 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
- -293 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 163: enough signal without eating the budget
- +4Structure: 48 headings
- +3Step-by-step instructions: 81 items
- +4Has examples (13 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.