AB alibabacloud-oss-cross-account-auth-diagnosis
Read-only OSS cross-account auth diagnosis: attributes NoPermission/AccessDenied to trust-policy gaps, RAM-policy scope, Bucket-Policy+RAM dual-grant, AssumeRole failures; emits templates only. Triggers: "cross-account access failed", "trust policy error", "cross-account replication permission error", "AssumeRole failed on OSS", "cross-account migration authorization", "peer account cannot read my bucket", company/partner account, account transfer, EncodedDiagnosticMessage decode. Do NOT use: transfer/timeout (use alibabacloud-oss-transfer-error-code-diagnosis); endpoint (use alibabacloud-oss-endpoint-internal-diagnosis); CRR health (use alibabacloud-oss-crr-config-check); ossfs (use alibabacloud-oss-ossfs-mount-diagnosis); direct-link 403 (use alibabacloud-oss-direct-access-link-diagnosis); signed-URL (use alibabacloud-oss-presigned-url-v4-diagnosis); same-account RAM (use alibabacloud-oss-security-incident-forensics).
Read-only OSS cross-account auth diagnosis: attributes NoPermission/AccessDenied to trust-policy gaps, RAM-policy scope, Bucket-Policy+RAM dual-grant…
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 ≈ 7418 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. 11 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 7418 tokens
- 100Steps. 58 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 933: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 23 headings
- +3Step-by-step instructions: 58 items
- +4Has examples (7 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.