AB alibabacloud-oss-backup-integration-diagnosis
Zero-cloud-API diagnosis of Alibaba Cloud OSS integration problems for third-party backup software (Veeam, Synology NAS, Rclone, generic S3 clients): S3 compatible interface checks (endpoint form, path-style), V1-signature-forbidden routing to V4, retrieval-fee attribution for IA/Archive backup buckets, whitelist (jia-bai) request guidance. Configuration advice only; never executes changes. Do NOT use for: upload/download error codes (use alibabacloud-oss-transfer-error-code-diagnosis), billing line-items (use alibabacloud-oss-billing-diagnosis), lifecycle rules (use alibabacloud-oss-lifecycle-runtime-diagnosis), presigned URLs (use alibabacloud-oss-presigned-url-v4-diagnosis). Triggers: "Veeam backup to OSS", "Synology backup OSS", "rclone sync OSS", "S3 compatible interface", "high retrieval fee from backup", "V1 signature forbidden on backup tool". Invoke immediately on any trigger; the entry script collects missing inputs via its "Inputs still missing" report instead of interviewing the user first.
Zero-cloud-API diagnosis of Alibaba Cloud OSS integration problems for third-party backup software (Veeam, Synology NAS, Rclone, generic S3 clients): S3…
As a process B 72/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5041 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 72/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70Execution cost. Instruction body is 5041 tokens
- 100Steps. 37 steps
- 100When it triggers. States when to use and when not to
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 1 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 17 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 (4 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 1017: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 19 headings
- +3Step-by-step instructions: 37 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.