AB alibabacloud-oss-image-processing-diagnosis
Read-only diagnostics for OSS image processing. Use when an x-oss-process error occurs, an image style or watermark is not applied, image preview fails or the default domain forces download, original image protection 403, unsupported-format BadRequest, WebP conversion errors, HEIC thumbnail 400 errors, image-processing action order differences, or dynamic WebP processing failures. Triggers: "x-oss-process error", "image style not working", "original image protection 403", "watermark not applied", "image preview fails", "image forced download", "WebP conversion error", "HEIC thumbnail 400", "image-processing action order", "dynamic WebP processing". Not for transfer error codes, endpoints, billing, presigned URL/V4, direct-access links, or static hosting (use the matching OSS diagnosis skill); video / blind-watermark / document-preview (IMM) is out of scope.
Read-only diagnostics for OSS image processing.
As a process B 65/100 · Nearly there — weak spots: result and completion, running it twice
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 ≈ 6557 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 65/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 7 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
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6557 tokens
- 100Steps. 63 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- 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 response is described with custom markup (12 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 869: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 24 headings
- +3Step-by-step instructions: 63 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.