BD financial-receipt-recognition-and-extract
支持增值税专用发票、增值税普通发票、增值税电子发票、出租车票、火车票、飞机行程单、过路费发票、定额发票、客运汽车票、财政票据等30+常见国内票据类型的自动分类与全量字段抽取，输出结构化JSON，零配置开箱即用，适用于费用报销、财务记账、发票验真、差旅报销自动化等场景。
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostREADME-CN.md:29Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.sh | bash
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostREADME.md:30Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.sh | bash
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostSKILL.md:98Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.sh | bash
Files scanned: 7. 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 (financial-receipt-recognition-and-extract) differs from the folder (adp-financial-receipt-recognition-and-extract)
- 100Tools and files. No external tools needed
- 100Steps. 23 steps
- 100Execution cost. Instruction body is 3255 tokens
- 100Running it twice. No mutating operations
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 tags): a typed call is more reliable
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
- -212 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 134: enough signal without eating the budget
- +4Structure: 32 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (17 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.