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-pass-generate/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-pass-generate)<a href="https://agentmods.dev/skills/tile-ai/tilelang-ascend/tilelang-pass-generate"><img src="https://agentmods.dev/badge/skills/tile-ai/tilelang-ascend/tilelang-pass-generate/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-pass-generate"><img src="https://agentmods.dev/badge/skills/tile-ai/tilelang-ascend/tilelang-pass-generate.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 | $0.00122 | $0.04937 |
| Opus 5 | $0.00061 | $0.02469 |
| Sonnet 5 | $0.00024 | $0.00987 |
| Haiku 4.5 | $0.00012 | $0.00494 |
Grade A, and why
tilelang-pass-generate 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TileLang-Ascend Pass 代码生成 Skill
1. 目标与边界
1.1 本 skill 负责（In Scope）
把已经定型的 Pass 设计文档（pass-design.md）落到代码上，覆盖：
- C++ 实现：
src/transform/<pass_name>.cc - Python 封装：
tilelang/transform/__init__.py - 配置键（可选）：
tilelang/transform/pass_config.py - Pipeline 接入：
tilelang/engine/phase.py - 最小冒烟验证：导入是否成功、Pipeline 是否仍然能跑通最小 example、跨文件命名是否一致
1.2 本 skill 不做（Out of Scope）
- ❌ 不生成 UT / ST 测试代码 —— 由后续单独的测试生成 skill 负责
- ❌ 不重做 Pass 定位与方案决策（属于
tilelang-pass-design） - ❌ 不修改 TVM 原生 Pass
所有重大决策必须沿用
pass-design.md已经写定的内容；如果设计文档里某项是「待确认」或缺失，则停下来回到tilelang-pass-design补齐，不在本 skill 里临时拍板。
完成代码生成后，提示用户调用「Pass 测试生成 skill（待创建）」补 UT/ST，不在本 skill 里偷跑。
2. 必需输入
| 字段 | 说明 | 缺失处理 |
|---|---|---|
pass-design.md |
已通过 tilelang-pass-design 自检的 Pass 设计文档 |
询问用户位置；若没有则建议先跑 tilelang-pass-design |
| Pass 名称 | C++ 类名、Python 函数名、注册名 | 从 pass-design.md §1.1 读取 |
| 阶段归属与位置 | Phase 1 / Phase 2，以及插入位点 |
从 pass-design.md §2 读取 |
| 父类与核心方法 | IRMutatorWithAnalyzer / StmtExprVisitor / StmtExprMutator 等 |
从 pass-design.md §4.1 读取 |
| 输入/输出 attrs | 上下游数据传递 | 从 pass-design.md §2.4、§3 读取 |
设计文档 §5「测试方案」本 skill 不消费，仅作为下游测试 skill 的输入保留。
输入校验规则：
- 若
pass-design.md不存在 → 立即停止，引导用户使用tilelang-pass-design - 若设计文档中 §2 / §3 / §4 任一关键章节出现「待确认」「待补充」「TODO」 → 立即停止，列出缺口并要求补齐
- 若 Pass 名称、阶段归属、Pipeline 位置任何一项不明确 → 立即停止，要求用户先回到 design skill
3. 工作流程
「先骨架、再代码、最后冒烟」三段式流程，骨架阶段不可跳过。
[输入校验]
↓
[Phase A: 信息收集]
↓
[Phase B: 生成实现骨架文档 pass-impl-skeleton.md] ← 框架设计文档
↓
[用户确认骨架]
↓
[Phase C: 落代码（C++ / Python / pass_config / phase.py）]
↓
[Phase D: 最小冒烟验证（不跑 UT/ST）]
↓
[Phase E: 收尾报告 + 引导补测试]
Phase A：信息收集
按以下顺序读取，禁止一上来就 grep 整个 src/transform/：
- 设计文档：用户指定路径，或默认在当前目录
pass-design.md - 总体约束：
.agents/skills/tilelang-pass-agents-guide.md - 实现模式：
.agents/skills/tilelang-pass-design/references/pass-impl-patterns.md - Pipeline 现状：
tilelang/engine/phase.py（确认插入位点的上下文与函数签名） - Python 封装现状：
tilelang/transform/__init__.py（确认现有命名风格、_ffi_api调用方式） - 相似 Pass 源码：
pass-design.md§4.1 指定的参考 Pass，仅读 1–2 个最接近的实现，不得扫整目录
What ships with it
3 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 · 316 lines · 122 tokens per session scan A bf6199dfc96d
tilelang-pass-generate is a skill published in the GitHub repository tile-ai/tilelang-ascend (364 stars, last pushed today), licensed MIT. It adds 122 tokens to every session and 4,937 once invoked, about $0.0006 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
zoom-meeting-sdk-unreal
Zoom Meeting SDK for Unreal Engine wrapper integrations. Use when building Unreal projects that embed Zoom meetings with C++ and Blueprint wrappers, including wrapper-to-SDK mapping concerns.
ax-cpp-gen
Use when writing C++ code with axllm for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.
doca-argp
Use this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing / renaming flags; wiring docaargpinit → register params → docaargpstart → docaargpdestroy in order; picking a parameter type from the full public enum (DOCAARGPTYPESTRING, INT, BOOLEAN, DEVICE, DEVICEREP…
cpu-kernels
Provides guidance for writing, optimizing, and benchmarking C++ CPU kernels with SIMD intrinsics (AVX2/AVX512) for the Hugging Face kernels ecosystem. Includes a two-phase workflow: Phase 1 correctness (generic → AVX2) and Phase 2 performance exploration (AVX512 with branching trial loop), runtime CPU dispatch, OpenMP…
llvm-learning
Comprehensive learning resources and tutorials for LLVM, Clang, and compiler development. Use this skill when helping users learn LLVM internals, find educational resources, or understand compiler concepts.
llvm-security
Expertise in LLVM security features including sanitizers, hardening techniques, exploit mitigations, and secure compilation. Use this skill when implementing security-focused compiler features, analyzing vulnerabilities, or hardening applications.