AA huawei-cloud-ascend-profiler-db-explorer
Convert natural language questions into safe executable SQL to query Ascend PyTorch Profiler / msprof database for operator time consumption, communication, dispatch, and other performance data. Supports table schema extraction from official documentation. Use this skill when the user wants to: (1) analyze Ascend profiling database, (2) query operator performance data, (3) analyze communication and dispatch bottlenecks, (4) check table schema for profiling data. Trigger: user mentions "profiler db", "sqlite", "sql", "table", "schema", "ascend-pytorch-profiler", "msprof", "operator time", "communication time", "dispatch analysis", "性能分析", "算子耗时", "数据库查询", "性能数据", "性能瓶颈"
Convert natural language questions into safe executable SQL to query Ascend PyTorch Profiler / msprof database for operator time consumption, communication…
As a process A 89/100 · Runs to the end — weak spots: 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: 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 89/100
- 0Progress reporting. Says nothing while it works
- 60Steps. 75 steps, 5 vague phrases
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. Tools declared in frontmatter
- 100Result and completion. Output format and completion criterion are stated
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3544 tokens
- 100Running it twice. No mutating operations
- low 17 top-level sections: this looks like several domains in one skill
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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 677: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 75 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (1 of 4)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 99.