BD invoice-guard
InvoiceGuard · 发票合规管家 — AI 驱动发票查重、验真、合规报告生成工具。用于：发票上传/扫码识别、发票重复报销检测（AI 查重）、发票真伪官方验真（金税四期）、合规报告生成（财会便函〔2023〕18号）、批量发票处理。当用户提到：发票、查重、验真、报销、合规、重复报销、假发票、发票识别、OFD、PDF发票时使用此技能。
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
This is a copy of a skill from another catalog; the rating counts the canonical one: invoice-guard (ClawHub)
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
- 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: 10. 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")
Process rating: all ten parameters 49/100
- 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 (invoice-guard) differs from the folder (invoice-guard-pro)
- 100Tools and files. No external tools needed
- 100Steps. 26 steps
- 100Execution cost. Instruction body is 1148 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
- -31 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 170: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 26 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (3 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.
External checks
ClawHub: suspicious
The skill mostly does invoice checking, but it needs review because it overstates official tax verification and under-discloses external storage of sensitive invoice data.
LLM: suspicious (high) · VirusTotal: benign · 28 May 2026