BC purchase-order-recognition-and-extract
Accurate extraction of all fields from purchase orders and sales orders in various formats — PO number, order date, seller name, buyer/customer name, buyer/customer address, receiver name, delivery address, currency, total amount, and line items (including material code, description, quantity, tax rate, unit price incl. tax, total amount incl. tax, delivery date). Outputs structured JSON, zero-configuration out-of-the-box, suitable for e-commerce order entry, supply chain reconciliation, and warehouse management automation.
As a process C 57/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, consistency
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
-
low Dangerous commands
cmd-pipe-to-shell-known-hostREADME-CN.md:29Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)curl -fsSL https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.sh | bash
security skill -
low Dangerous commands
cmd-pipe-to-shell-known-hostREADME.md:30Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)curl -fsSL https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.sh | bash
security skill -
low Dangerous commands
cmd-pipe-to-shell-known-hostSKILL.md:63Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)curl -fsSL https://raw.githubusercontent.com/laiye-ai/adp-cli/main/scripts/adp-init.sh | bash
security skill
Files scanned: 5. 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
body-longSKILL.md body ≈ 5033 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 57/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 40Consistency. Frontmatter name (purchase-order-recognition-and-extract) differs from the folder (adp-purchase-order-recognition-and-extract)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 5033 tokens
- 100Steps. 23 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Progress reporting. Reports progress
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (18 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)
- +2Single-language instructions
- +3Description length 529: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 23 items
- +3Output format is stated explicitly
- +4Has examples (17 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.