AC high-performance-coding
Use when writing or optimizing performance-critical code — batch processing, concurrent/parallel systems, async pipelines, GPU computing, scientific computing, or any code where throughput, latency, or resource efficiency matters. Also trigger when the user mentions "performance", "optimize", "scale", "concurrency", "make it faster", "speed up", "throughput", "latency", "GPU", "memory bound", "CPU bound", "checkpoint", "resume", "断点续传", "中断恢复", "idempotent", or asks about resource usage or making long-running tasks resumable. This skill encodes universal performance principles distilled from real systems — resource-aware parallelism, async pipeline design, GPU acceleration, interruption-tolerant computation, lock-free data structures, and progressive validation.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5382 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, git, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5382 tokens
- 100Steps. 66 steps
- 100Failures and branches. 14 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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
- medium 7 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 12 example trigger phrases
- +3Description length 772: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 66 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.