Borrowing it
Nothing to install: this file belongs to tile-ai/tilelang-ascend. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tile-ai/tilelang-ascend/ascendc_pto/.agents/skills/tilelang-op-test-design/SKILL.mdgit clone --depth 1 https://github.com/tile-ai/tilelang-ascendWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tile-ai/tilelang-ascend/tilelang-op-test-design)<a href="https://agentmods.dev/skills/tile-ai/tilelang-ascend/tilelang-op-test-design"><img src="https://agentmods.dev/badge/skills/tile-ai/tilelang-ascend/tilelang-op-test-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tile-ai/tilelang-ascend/tilelang-op-test-design"><img src="https://agentmods.dev/badge/skills/tile-ai/tilelang-ascend/tilelang-op-test-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00102 | $0.10561 |
| Opus 5 | $0.00051 | $0.05280 |
| Sonnet 5 | $0.00020 | $0.02112 |
| Haiku 4.5 | $0.00010 | $0.01056 |
Grade A, and why
tilelang-op-test-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 788 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TileLang-Ascend 算子测试设计
1. 技能定位与支持场景
1.1 支持的多种场景
本技能支持 4 种主要场景：
| 场景 | 输入来源 | 适用时机 | 工作流程 |
|---|---|---|---|
| 场景 A | design.md | 算子设计阶段 | 从设计文档提取信息 → 智能判断测试策略 → 生成测试配置建议 |
| 场景 B | examples/{op}/*.py | 算子已实现 | 从实现代码提取信息 → 分析现有测试 → 补充缺失用例 |
| 场景 C | 用户口头描述 | 早期讨论阶段 | 用户交互收集信息 → 智能判断测试策略 → 生成测试模板 |
| 场景 D | 现有测试分析 | 测试完善阶段 | 分析现有测试覆盖率 → 智能判断缺失场景 → 补充测试用例 |
1.2 场景触发关键词
| 场景 | 触发关键词示例 |
|---|---|
| 场景 A | "为这个算子设计测试"、"根据 design.md 生成测试配置" |
| 场景 B | "补充这个算子的测试"、"完善现有测试" |
| 场景 C | "我想开发一个 softmax 算子，帮我设计测试"、"算子是 xxx，数学公式是 yyy" |
| 场景 D | "分析测试覆盖率"、"现有测试不够全面，需要补充" |
2. 算子类别划分依据
2.1 划分依据来源
算子类别划分参考 tilelang-op-design skill §4 算子特征分析决策树，基于以下三个维度：
- 计算类型（硬件特性）
- 复杂度级别（计算步骤）
- 数学公式特征（数学运算）
2.2 计算类型划分（硬件特性）
依据：算子主要使用哪类硬件单元
| 计算类型 | 使用的硬件单元 | 数学公式特征 | 测试重点 |
|---|---|---|---|
| 纯 Cube | Cube 核（矩阵乘单元） | 仅含 matmul / @ | 矩阵维度组合、block size |
| 纯 Vector | Vector 核（向量单元） | 无 matmul，仅 element-wise/reduction | dtype 组合、shape 组合 |
| 混合（CV 融合） | Cube + Vector 核 | matmul + element-wise 后处理 | 核间协作正确性。Developer 模式默认消除显式 workspace（threads=2 + 片上直连），测试聚焦 CV 交互结果；Expert/混合或回退才涉及显式 workspace（GM 中转）+ 跨核同步 |
判断方法：理解算子实现逻辑后判断
2.3 复杂度级别划分（计算步骤）
依据：算子有多少个计算步骤
| 复杂度级别 | 计算步骤数 | 典型算子 | 测试特点 |
|---|---|---|---|
| 单步（Single） | 1 步 | Add, Mul, ReLU | 简单配置，快速验证 |
| 多步（Multi） | 2~5 步 | Softmax, LayerNorm | 详细配置，多 dtype |
| 融合（Fusion） | 多算子组合 | FlashAttention | 复杂配置，测试完整数据流 |
判断方法：分析数学公式或算法描述，理解计算步骤后判断
2.4 数学公式特征划分
依据：数学公式中的关键运算
| 数学公式特征 | 算子类别 | 测试策略 |
|---|---|---|
含 matmul / @ / 矩阵乘 |
GEMM 类 | 三维参数（M/N/K），block size 组合多 |
含 exp + sum + div 组合 |
Softmax 类 | 多 dtype，精度按 dtype 不同 |
含 mean + var + sqrt 组合 |
Normalization 类 | eps 参数重要，多 dtype |
含 sigmoid / relu / gelu |
Activation 类 | 简单配置，逐元素验证 |
含 sum(dim) / max(dim) |
Reduction 类 | 归约维度重要 |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 788 lines · 102 tokens per session scan A 4efc129f3d83
tilelang-op-test-design is a skill published in the GitHub repository tile-ai/tilelang-ascend (364 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 10,561 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
migrate-xunit-to-xunit-v3
Migrate .NET test projects from xUnit.net v2 to xunit.v3 and fix v3 breaks. Use for package/CPM conversion, OutputType=Exe, preserving the VSTest or MTP runner (including projects currently using YTest.MTP.XUnit2), incompatible TFMs, async void tests, string-to-Type attributes, custom Fact/Theory/BeforeAfterTest…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
mobiai-ios-testing
Use when writing or running tests in an iOS project — unit tests, UI tests, snapshot tests, choosing the right framework.
restore-internals-seams-in-finally-blocks-after-each-test
When delegating a task affected by this skill, include.
testing-llm
LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.