AC procurement-admission-copilot
Shadow-mode copilot for B2B procurement admission. Given a supplier's raw qualification inputs, it checks material-package completeness and internal consistency; given a set of approval cases, it tracks status, stalls, and gaps. It never drafts contract terms or makes the admission decision — only structures and flags for a human to decide.
Shadow-mode copilot for B2B procurement admission.
As a process C 63/100 · Has gaps — weak spots: consistency, running it twice, progress reporting
How to improve
- 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: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "description_zh" - note
frontmatter-keyunknown frontmatter key "description_en" - note
frontmatter-keyunknown frontmatter key "not_for" - note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 63/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (procurement-admission-copilot) differs from the folder (procurement-admission-copilot-skill)
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 59 steps
- 100Execution cost. Instruction body is 2484 tokens
- low 10 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)
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 342: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 59 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.