AB alibabacloud-oss-presigned-url-v4-diagnosis
Zero-cloud-API diagnosis of OSS presigned (share) URL failures and V1-to-V4 migration: parses a pasted URL, routes to causes (expired, clock skew, V1 signature forbidden, credential rotation, method mismatch, malformed x-oss-credential, SDK config misuse, proxy header tampering). Triggers: "share link expired", "SignatureDoesNotMatch on presigned URL", "V1 signature is forbidden", "x-oss-credential error", "signed URL stops working"; Chinese ticket wording routes via the embedded catalog keyword layer. Do NOT use for transfer error codes, billing, endpoints, traffic abuse / AK-leak, CDN back-to-origin or Referer hotlink configuration requests, or other OSS domains (backup / image processing / direct-access links / static hosting) — route to the matching alibabacloud-oss-* skill. A presigned-URL signature failure stays here even when a CDN or a proxy sits in front of the bucket.
Zero-cloud-API diagnosis of OSS presigned (share) URL failures and V1-to-V4 migration: parses a pasted URL, routes to causes (expired, clock skew, V1…
As a process B 66/100 · Nearly there — weak spots: result and completion, 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: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 66/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70Execution cost. Instruction body is 4603 tokens
- 100Steps. 42 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 top-level sections: this looks like several domains in one skill
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
- low The response is described with custom markup (3 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
- +3Description length 890: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 18 headings
- +3Step-by-step instructions: 42 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 97.