AB maibei-upload-audit
Upload local/inbound media to Maibei/MaybeAI, copy the audit spreadsheet, analyze uploaded files into the sheet, run the audit stage, generate a visual HTML report, and share it via trycloudflare tunnel. Use when a user asks to upload product images/videos to https://maibei.maybe.ai/e-commerce/upload-audit-file, continue an existing audit batch, fetch the generated spreadsheet link, run the audit pipeline end-to-end, or replay any step with a valid MaybeAI token and user-id. Triggers on: "上传文件并审核", "maybe audit", "maibei audit", "run audit pipeline", "上传审核", "生成审核报告", "分享审核链接".
As a process B 67/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, running it twice
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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Exfiltration
exfil-webhook-urlSKILL.md:134Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)# outputs: https://xxxx.trycloudflare.com/file.html
placeholder -
low Exfiltration
exfil-webhook-urlSKILL.md:217Webhook / callback URL commonly used for exfiltration (verify the destination) (documentation of a security skill; the skill's own vendor host)✅ 报告已发布: https://xxx.trycloudflare.com/audit_report.html
security skillvendor-host
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Upload local/inbound media to Maibei/MaybeAI, copy the audit sprea… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 67/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 3 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 56 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1728 tokens
- 100Progress reporting. Reports progress
- low 16 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
- +4Description does not say when NOT to use the skill (false activations)
- -32 of 4 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 584: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 56 items
- +3Output format is stated explicitly
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.