AA alibabacloud-dataworks-semantic
Always use this Skill for any Alibaba Cloud DataWorks semantic analysis job or run request, including read-only and preflight requests that intentionally make no API call, such as checking whether the public DataWorks semantic OpenAPI or dataworks-public plugin commands (for example create-semantic-job) are ready. It also applies when the requested outcome is only a refusal or a user choice with no API call. This includes comparing or disambiguating supplied semantic job candidates, validating or refusing an unsafe, path-traversal, or non-writable semantic result directory before any download, and inspecting artifacts for an exact run. Use it to create, run, stop, monitor, diagnose, or download results for semantic jobs backed by MaxCompute, Hologres, StarRocks, or an already uploaded CSV/XLSX reference. Do not use it for ordinary metadata lookup, lineage analysis, SQL development, workflow scheduling, file upload, published semantic model/version management, or semantic job deletion.
Always use this Skill for any Alibaba Cloud DataWorks semantic analysis job or run request, including read-only and preflight requests that intentionally make…
As a process A 87/100 · Runs to the end — no weak spots found
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: 7. 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 87/100
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 26 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 6 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3515 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 999: 120–800 characters recommended
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 14 headings
- +3Step-by-step instructions: 26 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.