AF company-research
Multi-source company research tool that generates structured due-diligence reports. Use when the user asks to research, look up, or investigate a company — including questions about shareholders, legal representative, registered capital, equity structure, beneficial owner, funding history, investors, valuation, lawsuits, court judgments, enforcement records, blacklist / dishonest debtor status, administrative penalties, operating anomalies, trademarks, patents, government procurement / bidding, recruitment profile, negative news, competitors, or industry position. Also triggers on: "帮我查一下XX公司", "XX公司背景", "XX的股东是谁", "XX有没有诉讼/被执行/失信", "XX融了多少钱", "XX股权结构", "尽调", "公司调研", "公司背景调查", "is X company reliable", "due diligence on X", "background check on X company".
As a process F 42/100 · Will not run — References files that are not bundled: URL
How to improve
- 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: URL
Process rating: all ten parameters 42/100
- 0Tools and files. 1 referenced file(s) missing: URL
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (company-research) differs from the folder (company-search)
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Steps. 56 steps
- 100Execution cost. Instruction body is 2065 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +3Description length 765: enough signal without eating the budget
- +4Structure: 28 headings
- +3Step-by-step instructions: 56 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.