BA huawei-cloud-ascendc-operator-performance-optim
Develop and optimize custom operators using AscendC programming language. Analyze operator performance bottlenecks and conduct optimization validation. Based on AscendC and CANN toolkit Use this skill when the user wants to: (1) optimize performance-critical operators on Ascend NPU, (2) develop custom operators for specific workloads, (3) improve model inference performance through operator optimization Trigger: user mentions "AscendC", "operator optimization", "custom operator", "performance", "NPU optimization", "Ascend operator", "算子优化", "自定义算子", "算子开发", "AscendC算子", "性能优化"
Develop and optimize custom operators using AscendC programming language.
As a process A 80/100 · Runs to the end — weak spots: failures and branches, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 · 11
✓ No critical or high findings
Medium and low: 11
-
medium Dangerous commands
cmd-privilegereferences/troubleshooting.md:97Privilege escalation / world-writable permissionschmod 777 /tmp/opprof
-
medium Dangerous commands
cmd-privilegeskill-card.md:21Privilege escalation / world-writable permissionsMitigation: Use a private profiling output directory with restrictive permissions instead of following chmod 777 guidance. <br>
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: bashallowed-tools: python3 bash ascendc
-
low Secrets in code
secret-high-entropy-tokenreferences/ascendc-api/basic-data-structures-api.md:231High-entropy token-like string (may be an id, hash or a credential)| A1 | rule…tL1 |
-
low Secrets in code
secret-high-entropy-tokenreferences/ascendc-api/basic-data-structures-api.md:232High-entropy token-like string (may be an id, hash or a credential)| A2 | rule…L0A |
-
low Secrets in code
secret-high-entropy-tokenreferences/ascendc-api/basic-data-structures-api.md:233High-entropy token-like string (may be an id, hash or a credential)| B1 | rule…tL1 |
-
low Secrets in code
secret-high-entropy-tokenreferences/ascendc-api/basic-data-structures-api.md:234High-entropy token-like string (may be an id, hash or a credential)| B2 | rule…L0B |
-
low Secrets in code
secret-high-entropy-tokenreferences/ascendc-api/basic-data-structures-api.md:235High-entropy token-like string (may be an id, hash or a credential)| CO1 | rule…L0C |
-
low Secrets in code
secret-high-entropy-tokenreferences/ascendc-api/data-copy-api.md:124High-entropy token-like string (may be an id, hash or a credential)// GM -> UB, Supp…ign
-
low Secrets in code
secret-high-entropy-tokenreferences/ascendc-api/resource-management-api.md:59High-entropy token-like string (may be an id, hash or a credential)| depth | teamcolumnDeep Dive (push…as1, Tens…as0) |
-
low Dangerous commands
cmd-privilegeskill-card.md:20Privilege escalation / world-writable permissions (detector / deny-list definition)Risk: The skill includes unsafe chmod 777 guidance for profiling output directories. <br>
detector
Files scanned: 22. 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 80/100
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 3 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 81 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1837 tokens
- 100Progress reporting. Reports progress
- low 13 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)
- -34 of 4 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 583: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 81 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (3 of 9)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.