What is tilelang-pass-workflow-analyzer?

A guide to the workflow of TileLang compiler passes, which are processing stages that transform or analyze code. It describes their order, dependencies, and where a new stage should be added.

Use it to understand the pass pipeline, trace relationships between passes, investigate execution order, or decide where to place a new pass.

Without the pipeline structure, adding or changing a pass can break required data dependencies or run it at the wrong time.

How tile-ai/tilelang-ascend configures Claude Code and Codex

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/tile-ai/tilelang-ascend/ascendc_pto/.agents/skills/tilelang-pass-workflow-analyzer/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/tile-ai/tilelang-ascend

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tile-ai/tilelang-ascend/tilelang-pass-workflow-analyzer/github.svg)](https://agentmods.dev/skills/tile-ai/tilelang-ascend/tilelang-pass-workflow-analyzer)

Your own site

<a href="https://agentmods.dev/skills/tile-ai/tilelang-ascend/tilelang-pass-workflow-analyzer"><img src="https://agentmods.dev/badge/skills/tile-ai/tilelang-ascend/tilelang-pass-workflow-analyzer/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tile-ai/tilelang-ascend/tilelang-pass-workflow-analyzer"><img src="https://agentmods.dev/badge/skills/tile-ai/tilelang-ascend/tilelang-pass-workflow-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,684 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00098	$0.02684
Opus 5.5	$0.00039	$0.01074
Sonnet 5.5	$0.00020	$0.00537
Haiku 4.5	$0.00010	$0.00268

Measured 28d ago against content hash 6c80edcd7b7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tilelang-pass-workflow-analyzer 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 28d 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.

.agents/skills/tilelang-pass-workflow-analyzer/SKILL.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TileLang Pass 工作流分析 Skill

⭐ 核心约束：分阶段信息获取

严格遵守以下信息获取优先级：

查询阶段	信息来源	工具使用
理解现有模型	✅ 先读对应 reference	`read(references/*.md)`
给出精确顺序或修改建议	✅ 再核对当前源码	`read(tilelang/engine/phase.py)`

执行规则：

用户首次提问 Pass 工作流
  ↓
1. 立即读取 reference 文件（pass-pipeline-overview.md / pass-dependency-graph.md）
  ↓
2. 若只解释概念，基于 reference 回答
  ↓
3. 若要给出精确顺序、插入点或改代码，核对当前 phase.py 与相关 pass 源码

禁止行为：

❌ 跳过 reference，重新发明一套依赖模型
❌ 在没有核对当前 phase.py 时给出可执行的插入点
❌ 把 reference 中的固定步骤号当成比源码更高的权威

核心目标

这个 skill 用于：

串联 Pass 关系 - 展示 Pass 之间的依赖关系和数据流传递
解释 Pipeline 架构 - 说明两阶段编译流程及其设计原理
定位新 Pass - 帮助用户确定新 Pass 应该添加在 Pipeline 的哪个位置

与 tilelang-pass-analyzer 的区别：

tilelang-pass-analyzer：侧重于单个 Pass 的功能、原理、实现细节
tilelang-pass-workflow-analyzer：侧重于 Pass 之间的关系、整体工作流、新 Pass 定位

工作流程

当用户提出与 Pass 工作流相关的询问时，按照以下步骤响应：

Step 1: 识别用户意图

判断用户是想要：

了解整体架构 → 提供 Pipeline overview
理解 Pass 关系 → 展示依赖关系图
添加新 Pass → 提供定位指南和建议
查询特定阶段 → 定位到具体阶段并解释

Step 2: 选择合适的分析方式

根据意图，使用以下工具：

用户意图	参考文档	分析方式
了解整体架构	`references/pass-pipeline-overview.md`	展示两阶段架构图，解释设计原理
理解 Pass 关系	`references/pass-dependency-graph.md`	展示依赖关系图，说明数据传递
添加新 Pass	`references/new-pass-placement-guide.md`	分析 Pass 功能特征，给出定位建议
查询特定阶段	根据阶段名称查找	定位到具体 Pass，展示上下游关系

Step 3: 提供分析报告

输出格式：

# Pass 工作流分析报告

## 用户问题
[用户的具体问题]

## 分析结果

### [根据意图提供对应内容]

### 关键要点
- [要点 1]
- [要点 2]

### 建议操作
[如果用户要添加新 Pass，给出具体建议]

两阶段 Pipeline 架构概要

TileLang-Ascend 采用两阶段编译流程：

Python DSL (@tilelang.jit)
    ↓
[Phase 1: LowerAndLegalize] ← 前端标准化、Lowering
    - 目标：将高级 DSL 转换为标准化、可分析的 TIR
    - 特点：前端规范化与必要的 Ascend early lowering
    ↓
[Phase 2: OptimizeForTarget] ← 后端优化、平台特化
    - 目标：针对 Ascend 硬件特性的优化
    - 特点：硬件相关、性能导向
    ↓
CANN 工具链 → NPU 执行

详细架构请查阅： references/pass-pipeline-overview.md

Pass 依赖关系核心概念

数据传递方式

Pass 之间既通过 PrimFunc attrs，也通过结构性 IR contract 传递数据：

Read the full file on GitHub · 287 lines

Files

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.

Changes

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.

1mo ago Changed · +4 lines 6c80edcd7b7e
2mo ago First seen · 283 lines · 98 tokens per session scan A 6fdf916c9494

Subscribe to this mod's changes

tilelang-pass-workflow-analyzer is a skill published in the GitHub repository tile-ai/tilelang-ascend (427 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 2,684 once invoked, about $0.0004 per session on Opus 5.5. 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.

tilelang-pass-workflow-analyzer next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tilelang-pass-workflow-analyzertile-ai/tilelang-ascend	Skill	427	yesterday	MIT	A	98	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

tilelang-ascend: Skill for Claude Code