Agent Code Analyzer
ruvnet/ruflo
Agent skill for code-analyzer - invoke with $agent-code-analyzer
TileLang Pass 功能分析与对比工具。触发条件:(1) 用户询问特定 pass 的功能、作用、原理、实现细节,关键词包括"XXpass是干什么的"、"介绍XXpass"、"XXpass的功能"、"XXpass怎么实现的"、"分析XXpass";(2) 对比两个 pass 的差异、联系;(3) 查询某类 pass 列表;(4) 模糊匹配 pass…
$ npx skills add tile-ai/tilelang-ascend --skill tilelang-pass-analyzer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tile-ai/tilelang-ascend tilelang-pass-analyzer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/tile-ai/tilelang-ascend.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/tilelang-pass-analyzer .claude/skills/tilelang-pass-analyzer && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "tilelang-pass-analyzer" agent skill from https://github.com/tile-ai/tilelang-ascend/tree/ascendc_pto/.agents/skills/tilelang-pass-analyzer into .claude/skills/tilelang-pass-analyzer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tilelang-pass-analyzer", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/tile-ai/tilelang-ascend/tree/ascendc_pto/.agents/skills/tilelang-pass-analyzerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add tile-ai/tilelang-ascend --skill tilelang-pass-analyzer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tile-ai/tilelang-ascend tilelang-pass-analyzer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tile-ai/tilelang-ascend.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/tilelang-pass-analyzer .agents/skills/tilelang-pass-analyzer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "tilelang-pass-analyzer" agent skill from https://github.com/tile-ai/tilelang-ascend/tree/ascendc_pto/.agents/skills/tilelang-pass-analyzer into .agents/skills/tilelang-pass-analyzer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tilelang-pass-analyzer", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tile-ai/tilelang-ascend --skill tilelang-pass-analyzer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tile-ai/tilelang-ascend tilelang-pass-analyzer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tile-ai/tilelang-ascend.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/tilelang-pass-analyzer .cursor/skills/tilelang-pass-analyzer && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "tilelang-pass-analyzer" agent skill from https://github.com/tile-ai/tilelang-ascend/tree/ascendc_pto/.agents/skills/tilelang-pass-analyzer into .cursor/skills/tilelang-pass-analyzer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tilelang-pass-analyzer", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/tile-ai/tilelang-ascend.git --path .agents/skills/tilelang-pass-analyzer--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add tile-ai/tilelang-ascend --skill tilelang-pass-analyzer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tile-ai/tilelang-ascend tilelang-pass-analyzer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tile-ai/tilelang-ascend.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/tilelang-pass-analyzer .gemini/skills/tilelang-pass-analyzer && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "tilelang-pass-analyzer" agent skill from https://github.com/tile-ai/tilelang-ascend/tree/ascendc_pto/.agents/skills/tilelang-pass-analyzer into .gemini/skills/tilelang-pass-analyzer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tilelang-pass-analyzer", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install tile-ai/tilelang-ascend tilelang-pass-analyzerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add tile-ai/tilelang-ascend --skill tilelang-pass-analyzer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tile-ai/tilelang-ascend.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/tilelang-pass-analyzer .github/skills/tilelang-pass-analyzer && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "tilelang-pass-analyzer" agent skill from https://github.com/tile-ai/tilelang-ascend/tree/ascendc_pto/.agents/skills/tilelang-pass-analyzer into .github/skills/tilelang-pass-analyzer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tilelang-pass-analyzer", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tile-ai/tilelang-ascend --skill tilelang-pass-analyzer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tile-ai/tilelang-ascend tilelang-pass-analyzer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tile-ai/tilelang-ascend.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/tilelang-pass-analyzer .opencode/skills/tilelang-pass-analyzer && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "tilelang-pass-analyzer" agent skill from https://github.com/tile-ai/tilelang-ascend/tree/ascendc_pto/.agents/skills/tilelang-pass-analyzer into .opencode/skills/tilelang-pass-analyzer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tilelang-pass-analyzer", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
tilelang-pass-analyzerTileLang Pass 功能分析与对比工具。触发条件:(1) 用户询问特定 pass 的功能、作用、原理、实现细节,关键词包括"XXpass是干什么的"、"介绍XXpass"、"XXpass的功能"、"XXpass怎么实现的"、"分析XXpass";(2) 对比两个 pass 的差异、联系;(3) 查询某类 pass 列表;(4) 模糊匹配 pass…
Tilelang Pass Analyzer is an agent skill from tile-ai/tilelang-ascend. TileLang Pass 功能分析与对比工具。触发条件:(1) 用户询问特定 pass 的功能、作用、原理、实现细节,关键词包括"XXpass是干什么的"、"介绍XXpass"、"XXpass的功能"、"XXpass怎么实现的"、"分析XXpass";(2) 对比两个 pass 的差异、联系;(3) 查询某类 pass 列表;(4) 模糊匹配 pass 名称。支持精确匹配和模糊匹配,返回由浅入深的 Markdown 分析报告,包含伪代码、IR 变换示例、代码位置等。
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 22 other files, including reference files (for example `T.pipelined.md`, `evals/evals.json` and `references/ir-examples.md`).
The repository describes itself as: Ascend TileLang adapter. The licence is MIT.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 83b0ece. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and python).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Tilelang Pass Analyzer loads about 1.7k tokens when it runs, and up to ~121k if it reads all its reference files. Until then it costs about 65 tokens; SKILL.md has 285 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from tile-ai/tilelang-ascend at commit 83b0ece, republished under its MIT licence (© tile-ai). 285 words, ~1,696 tokens.
.claude/skills/tilelang-pass-analyzer/SKILL.md (or your agent's skills folder). This skill also uses 19 other files; get the full folder from GitHub.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 |
|---|---|---|
| 首次回答 | ✅ 优先使用 reference 文件 | read(references/*.md) |
| 用户追问深入细节 | ✅ 读取源码补充 | read(src/transform/*.cc) |
执行规则:
用户首次提问 Pass 功能
↓
1. 立即读取 reference 文件(pass-registry-*.md / pass-classification.md)
↓
2. 基于 reference 信息生成报告(足够回答 90% 的查询)
↓
3. 仅在用户追问"具体实现"、"源码细节"、"某个函数逻辑"时才读取源码禁止行为:
src/transform/*.cc 源码文件根据用户输入判断查询类型:
| 意图类型 | 关键词特征 | 处理方式 |
|---|---|---|
| 单 Pass 分析 | "XX pass 是做什么的"、"分析 XX pass"、"XX 的功能" | 查 registry → 分析代码 → 生成报告 |
| 双 Pass 对比 | "XX 和 YY 的区别"、"对比 XX YY"、"XX YY 的差异" | 生成对比报告(每节对比) |
| 双 Pass 联系 | "XX 和 YY 的联系"、"XX YY 的关系"、"XX YY 协作" | 生成联系报告(每节分析关系) |
| 分类查询 | "XX 类的 pass"、"内存相关 pass"、"Ascend pass 有哪些" | 查 classification → 列表报告 |
| 模糊匹配 | "sync 相关"、"vector pass"、"那个插入同步的" | 搜索 → 返回候选列表 |
精确匹配:
1. 读取 references/pass-registry-ascend.md 或 pass-registry-general.md
2. 根据名称获取:C++ 文件路径、Python 函数名、配置键
3. 定位到具体文件模糊匹配策略:
1. 提取用户输入的关键词(去除 pass、transform 等通用词)
2. 在 registry 中搜索名称包含关键词的所有 pass
3. 返回候选列表(最多 5 个):序号、名称、简述、分类
4. 提示用户选择序号或输入完整名称分类查询:
1. 读取 references/pass-classification.md
2. 根据用户指定的分类(如"内存管理"、"同步"、"Ascend平台")返回列表
3. 按子分类组织输出⚠️ 重要:首次提问时跳过此步骤,仅使用 reference 文件信息。
仅在用户追问以下问题时才执行此步骤:
按以下顺序分析 Pass 实现:
1. Python API 层
tilelang/transform/__init__.py2. C++ 实现层
src/transform/<pass_name>.cc/*! \file ... */IRMutatorWithAnalyzer、StmtExprVisitor 等)Substitute、VisitStmt、VisitExpr)TVM_REGISTER_PASS_CONFIG_OPTION 或 TVM_REGISTER_GLOBAL3. 配置层
tilelang/transform/pass_config.py分析方法:
- 快速浏览文件头注释,理解 pass 目标
- 找到主类的 Substitute 或 VisitXxx 方法,理解核心逻辑
- 分析算法流程:遍历 → 匹配 → 变换 → 输出
- 查看 common/ 目录下的辅助工具类根据查询类型选择模板:
| 查询类型 | 模板选择 |
|---|---|
| 单 Pass 分析 | 使用【单 Pass 分析报告模板】 |
| 双 Pass 对比 | 使用【双 Pass 对比报告模板】 |
| 双 Pass 联系 | 使用【双 Pass 联系报告模板】 |
| 分类查询 | 使用【分类查询报告模板】 |
| 模糊匹配 | 使用【模糊匹配候选列表模板】 |
通用风格要求:
✅ 由浅入深:先一句话总结,再逐步展开细节
✅ 伪代码精简:不超过 10 行,每个关键步骤标注函数名和备注
✅ IR 示例清晰:简化结构,标注变化点
✅ 核心函数标识:指出函数名,不引用完整代码片段
✅ 伪 IR 说明:首次使用时标注"本示例为伪 IR",真实 TIR 格式见 ir-examples.md格式模板:
# 伪代码示例 (精简版)
输入: PrimFunc / IR Module
处理流程:
1. 遍历 IR 结构 → VisitStmt() # [备注: 深度优先遍历每个语句]
2. 匹配目标模式 → MatchPattern() # [备注: 检查是否为特定 op/buffer 类型]
3. 执行变换操作 → TransformStmt() # [备注: 生成新的 IR,保持语义等价]
输出: 变换后的 PrimFunc
# 关键点备注
- VisitStmt: 继承 IRMutatorWithAnalyzer,访问 Stmt 节点
- MatchPattern: 检查 buffer scope、op type 等属性
- TransformStmt: 根据规则生成新语句,可能涉及同步/地址映射等编写规则:
# [备注: ...] 说明该步骤的作用或决策依据参考 references/ir-examples.md 的格式。
基本格式:
**输入伪 IR:**
# 变换前状态(简要说明)
[简化 IR 结构]
**输出伪 IR:**
# 变换后状态(简要说明)
[简化 IR 结构,用 ← 标注变化点]
**变换要点:**
- [变化点1]
- [变化点2]注意事项:
本示例为伪 IR 格式,真实 TIR 结构见 ir-examples.md← 标注新增/修改,用 # [备注] 添加说明以下模板用于生成不同类型的 Pass 分析报告。
# [Pass名称] 功能分析报告
## 一句话总结
> [核心功能概括,不超过 30 字]
## 功能详解
### 1. 作用与目的
[解决的问题和必要性]
### 2. 工作原理
输入: PrimFunc → 遍历 IR → 匹配模式 → 执行变换 → 输出: PrimFunc
核心函数: [函数名1]、[函数名2]
### 3. IR 变换示例
变换前: [简化IR] → 变换后: [简化IR,←标注变化]
要点: [变化点1]、[变化点2]
### 4. 使用场景与触发条件
| 项目 | 说明 |
| 适用平台 | Ascend 专用 / 通用 |
| 启用配置 | `配置键` (默认值) |
| 触发时机 | 编译阶段 |
### 5. Pass 关系与工作流
如需了解本 Pass 在 Pipeline 中的位置、与其他 Pass 的依赖关系,请使用 **tilelang-pass-workflow-analyzer** skill。
## 代码位置
| 组件 | 路径 | 核心元素 |
| Python API | `路径` | `函数名()` |
| C++ 实现 | `路径` | `类名::方法` |
| 配置项 | `路径` | `配置键` |# [Pass1] 与 [Pass2] 对比分析报告
## 一句话总结
> [共同点和核心差异,不超过 40 字]
## 功能对比
### 1. 作用与目的对比
| 维度 | [Pass1] | [Pass2] |
| 核心目标 | [简述] | [简述] |
| 解决问题 | [简述] | [简述] |
### 2. 工作原理对比
| Pass | 输入 | 处理 | 输出 |
| [Pass1] | ... | [函数名] | ... |
| [Pass2] | ... | [函数名] | ... |
关键差异: [差异点1]、[差异点2]
### 3. IR 变换对比
| Pass | 变换前 | 变换后 |
| [Pass1] | [IR] | [IR,←变化] |
| [Pass2] | [IR] | [IR,←变化] |
### 4. 使用场景对比
| 维度 | [Pass1] | [Pass2] |
| 适用平台 | ... | ... |
| 启用配置 | `key1` | `key2` |
### 5. 关系分析
执行顺序: [PassA] → [PassB] (原因: ...)
数据依赖: [Pass1] 提供 [数据] → [Pass2]
协作方式: 共同完成 [目标]
冲突限制: [限制条件]
## 代码位置对比
| Pass | Python API | C++ 实现 | 配置项 |
| [Pass1] | `路径` | `路径` | `key1` |
| [Pass2] | `路径` | `路径` | `key2` |# [Pass1] 与 [Pass2] 关系分析报告
## 一句话总结
> [协作关系概括]
## 关系分析
### 1. 作用与目的的联系
共同目标: [共同服务的目标]
分工协作: [Pass1] 负责 [职责1],[Pass2] 负责 [职责2]
### 2. 工作原理的联系
数据流: [Pass1] → 输出: [数据] → [Pass2] 输入
依赖关系: [Pass1] 提供 [内容],[Pass2] 需要 [内容]
### 3. IR 变换联系
Pass1 输出: ... (提供给 Pass2) → Pass2 输入: ... (来自 Pass1)
整体效果: [组合后的效果]
### 4. 执行顺序与触发
执行顺序: ... → [Pass1] → ... → [Pass2] → ...
顺序原因: [必须按此顺序的原因]
### 5. 协作场景
典型场景: [具体协作场景]
协作效果: [对比单独使用的效果]
## 代码位置
| Pass | Python API | C++ 实现 | 配置项 |
| [Pass1] | `路径` | `路径` | `key1` |
| [Pass2] | `路径` | `路径` | `key2` |# Pass 分类查询报告:[分类名称]
## 分类概述
> [该类 Pass 的共同特征]
## Pass 列表
### [子分类1]
| Pass 名称 | 功能简述 | 配置项 |
| [Pass1] | [描述] | `配置键` |
| [Pass2] | [描述] | `配置键` |
### [子分类2]
...
## 典型使用场景
场景1: [描述] → 推荐组合: [PassA]+[PassB]# Pass 匹配结果
根据关键词 "**[用户输入]**" 找到以下候选 Pass:
| 序号 | Pass 名称 | 功能简述 | 所属分类 |
| 1 | [Pass1] | [描述] | [分类] |
| 2 | [Pass2] | [描述] | [分类] |
| 3 | [Pass3] | [描述] | [分类] |
请选择你想了解的 Pass(输入序号 1-3 或完整名称):本 skill 包含以下 reference 文件,按需查阅:
| 文件 | 用途 | 使用时机 |
| pass-registry-ascend.md | Ascend Pass 名称→路径 | 精确匹配 Ascend pass |
| pass-registry-general.md | 通用 Pass 名称→路径 | 精确匹配通用 pass |
| pass-classification.md | Pass 分类索引 | 分类查询 |
| ir-examples.md | IR 变换示例 | 编写 IR 示例 |
© tile-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 19 other files (references) in .agents/skills/tilelang-pass-analyzer of tile-ai/tilelang-ascend.
Open the folder on GitHubat commit 83b0ece
Tilelang Pass Analyzer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Tilelang Pass Analyzer this skilltile-ai/tilelang-ascend | 402 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Agent Code Analyzerruvnet/ruflo | 74k | 2 repos | ~1.5k | Automated safety check: Pass | MIT | |
| Agent Pagerank Analyzerruvnet/ruflo | 74k | 2 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Agent Performance Analyzerruvnet/ruflo | 74k | 2 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Diff Analyzeruvnet/ruflo | 74k | — | ~450 | Automated safety check: Notes | MIT | |
| Analyze GitHub Flakeflutter/flutter | 179k | — | ~1.1k | Automated safety check: Pass | BSD-3-Clause |
ruvnet/ruflo
Agent skill for code-analyzer - invoke with $agent-code-analyzer
ruvnet/ruflo
Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer
ruvnet/ruflo
Agent skill for performance-analyzer - invoke with $agent-performance-analyzer
ruvnet/ruflo
Analyze git diffs for risk scoring, reviewer recommendations, and change classification.
flutter/flutter
Expertise in analyzing flake github issues in the flutter/flutter repository.
sickn33/agentic-awesome-skills
Forensic root cause analyzer for Antigravity sessions. An agent skill from sickn33/agentic-awesome-skills.
tile-ai/tilelang-ascend
Automatically pull tilelang repository and its third-party code.
tile-ai/tilelang-ascend
How to add debugging capabilities to TileLang Ascend example operators.
tile-ai/tilelang-ascend
将 tilelang example 脚本转换为可在 A5 camodel 仿真器上直接运行的版本。输入脚本路径,输出一个新的 sim.py 文件,不覆盖原始文件。触发:仿真运行、camodel、A5 仿真、sim 模式、转换脚本为仿真、不需要 NPU 跑 kernel、simulate A5。
tile-ai/tilelang-ascend
TileLang-Ascend 环境检查与配置验证技能。检查代码仓库完整性、编译安装状态、环境变量配置,并运行简单测试验证环境。发现问题会自动调用相关 skill 进行修复,并按依赖顺序重新执行后续步骤。触发关键词:"环境检查"、"检查环境"、"验证环境"、"环境配置"、"环境搭建"、"env check"、"check environment"、"verify…
tile-ai/tilelang-ascend
TileLang-Ascend 算子测试设计技能。支持多种场景:(1) 从 design.md 设计测试配置 (2) 从 examples/{op}/.py 补充测试 (3) 手动提供算子信息生成测试 (4) 测试覆盖率分析。理解算子实现逻辑后智能判断测试策略。触发:设计算子测试、生成测试用例、补充测试、测试覆盖率不足。
tile-ai/tilelang-ascend
检查代码格式是否符合 CI 规则。自动检测并安装缺失工具(ruff、clang-format),先运行检查生成报告,使用醒目方式询问用户后,仅在用户同意时执行修复。工作流程:检测环境→自动安装缺失工具→运行检查→生成报告→醒目询问→用户确认→执行修复。使用此技能当:用户要求"格式检查"、"格式化代码"、"代码格式化"、"检查代码格式"、"代码…
TileLang Pass 功能分析与对比工具。触发条件:(1) 用户询问特定 pass 的功能、作用、原理、实现细节,关键词包括"XXpass是干什么的"、"介绍XXpass"、"XXpass的功能"、"XXpass怎么实现的"、"分析XXpass";(2) 对比两个 pass 的差异、联系;(3) 查询某类 pass 列表;(4) 模糊匹配 pass…. Tilelang Pass Analyzer is an agent skill from tile-ai/tilelang-ascend.
Run `npx skills add tile-ai/tilelang-ascend --skill tilelang-pass-analyzer -a claude-code`. Or copy the skill folder (.agents/skills/tilelang-pass-analyzer in tile-ai/tilelang-ascend) into .claude/skills/tilelang-pass-analyzer in your project. Claude Code loads it when a task matches its description.
Run `npx skills add tile-ai/tilelang-ascend --skill tilelang-pass-analyzer -a codex`. Or copy the skill folder (.agents/skills/tilelang-pass-analyzer in tile-ai/tilelang-ascend) into .agents/skills/tilelang-pass-analyzer in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tile-ai/tilelang-ascend --skill tilelang-pass-analyzer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tilelang-pass-analyzer, .gemini/skills/tilelang-pass-analyzer, .github/skills/tilelang-pass-analyzer and .opencode/skills/tilelang-pass-analyzer in your project.
SKILL.md names no scripts, command-line tools or credentials: Tilelang Pass Analyzer is instructions for the agent only. Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Tilelang Pass Analyzer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 119k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Tilelang Pass Analyzer: Agent Code Analyzer (ruvnet/ruflo, 74k stars), Agent Pagerank Analyzer (ruvnet/ruflo, 74k stars), Agent Performance Analyzer (ruvnet/ruflo, 74k stars) and Diff Analyze (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
tile-ai (a GitHub organization) maintains it in tile-ai/tilelang-ascend, which has 402 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 9, 2026.
Source: tile-ai/tilelang-ascend on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.