Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
TileLang Ascend Developer/Expert 模式选择与 passconfigs 配置指南。当需要确定编程模式、配置 passconfigs、或在两种模式之间转换时触发。API 详情请参考 tilelang-api-best-practices skill。
Install Tilelang Programming Model Guide
$ npx skills add tile-ai/tilelang-ascend --skill tilelang-programming-model-guide -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tile-ai/tilelang-ascend tilelang-programming-model-guide --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-custom-skill/tilelang-programming-model-guide .claude/skills/tilelang-programming-model-guide && 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-programming-model-guide" agent skill from https://github.com/tile-ai/tilelang-ascend/tree/ascendc_pto/.agents/skills/tilelang-custom-skill/tilelang-programming-model-guide into .claude/skills/tilelang-programming-model-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tilelang-programming-model-guide", 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-custom-skill/tilelang-programming-model-guideType 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-programming-model-guide -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tile-ai/tilelang-ascend tilelang-programming-model-guide --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-custom-skill/tilelang-programming-model-guide .agents/skills/tilelang-programming-model-guide && 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-programming-model-guide" agent skill from https://github.com/tile-ai/tilelang-ascend/tree/ascendc_pto/.agents/skills/tilelang-custom-skill/tilelang-programming-model-guide into .agents/skills/tilelang-programming-model-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tilelang-programming-model-guide", 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-programming-model-guide -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tile-ai/tilelang-ascend tilelang-programming-model-guide --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-custom-skill/tilelang-programming-model-guide .cursor/skills/tilelang-programming-model-guide && 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-programming-model-guide" agent skill from https://github.com/tile-ai/tilelang-ascend/tree/ascendc_pto/.agents/skills/tilelang-custom-skill/tilelang-programming-model-guide into .cursor/skills/tilelang-programming-model-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tilelang-programming-model-guide", 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-custom-skill/tilelang-programming-model-guide--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-programming-model-guide -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tile-ai/tilelang-ascend tilelang-programming-model-guide --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-custom-skill/tilelang-programming-model-guide .gemini/skills/tilelang-programming-model-guide && 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-programming-model-guide" agent skill from https://github.com/tile-ai/tilelang-ascend/tree/ascendc_pto/.agents/skills/tilelang-custom-skill/tilelang-programming-model-guide into .gemini/skills/tilelang-programming-model-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tilelang-programming-model-guide", 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-programming-model-guideInstalls 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-programming-model-guide -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-custom-skill/tilelang-programming-model-guide .github/skills/tilelang-programming-model-guide && 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-programming-model-guide" agent skill from https://github.com/tile-ai/tilelang-ascend/tree/ascendc_pto/.agents/skills/tilelang-custom-skill/tilelang-programming-model-guide into .github/skills/tilelang-programming-model-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tilelang-programming-model-guide", 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-programming-model-guide -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-programming-model-guide --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-custom-skill/tilelang-programming-model-guide .opencode/skills/tilelang-programming-model-guide && 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-programming-model-guide" agent skill from https://github.com/tile-ai/tilelang-ascend/tree/ascendc_pto/.agents/skills/tilelang-custom-skill/tilelang-programming-model-guide into .opencode/skills/tilelang-programming-model-guide/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tilelang-programming-model-guide", 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.
Facts
- Skill name
tilelang-programming-model-guide- GitHub stars
- 400
- Token cost
- ~1.8k tokens
- SKILL.md length
- 430 words
- Files
- 2 (incl. references)
- Skills in repo
- 20
- Repo updated
- First seen
- Licence
- MIT
At a glance
TileLang Ascend Developer/Expert 模式选择与 passconfigs 配置指南。当需要确定编程模式、配置 passconfigs、或在两种模式之间转换时触发。API 详情请参考 tilelang-api-best-practices skill。
- Works in 4 steps: 模式对比 → pass_configs 详解（核心） → 模式转换规则（Expert → Developer） → …
- Development work in your project
- SKILL.md covers 1. 模式对比, 2. pass_configs 详解（核心）, 3. 模式转换规则（Expert → Developer） and 4. 示例代码与代码对比
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Tilelang Programming Model Guide is an agent skill from tile-ai/tilelang-ascend. TileLang Ascend Developer/Expert 模式选择与 passconfigs 配置指南。当需要确定编程模式、配置 passconfigs、或在两种模式之间转换时触发。API 详情请参考 tilelang-api-best-practices skill。
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/mode-examples.md`).
It sits in Development. The repository describes itself as: Ascend TileLang adapter. The licence is MIT.
When your agent uses it
- Development work in your project
Example prompts
- “/tilelang-programming-model-guide”
Requirements
- Python 3
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 3d17c28. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are python).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Tilelang Programming Model Guide loads about 1.8k tokens when it runs, and up to ~6.1k if it reads all its reference files. Until then it costs about 44 tokens; SKILL.md has 430 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.
Safety
Auto-check passed
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.
SKILL.md
The full file from tile-ai/tilelang-ascend at commit 3d17c28, republished under its MIT licence (© tile-ai). 430 words, ~1,837 tokens.
Download SKILL.mdSave it as
.claude/skills/tilelang-programming-model-guide/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- tilelang-programming-model-guide
- description
- TileLang Ascend Developer/Expert 模式选择与 pass_configs 配置指南。当需要确定编程模式、配置 pass_configs、或在两种模式之间转换时触发。API 详情请参考 tilelang-api-best-practices skill。
TileLang Ascend 编程模式与 pass_configs 指南
API 用法详情（内存分配、计算原语、同步原语等）请参考 tilelang-api-best-practices skill，本文档不再重复。
1. 模式对比
| 维度 | Developer 模式 | Expert 模式 |
|---|---|---|
| 内存分配 | T.alloc_shared / T.alloc_fragment | T.alloc_L1 / T.alloc_ub / T.alloc_L0A/L0B/L0C |
| 计算表达 | T.Parallel + 符号运算 | T.tile.xxx 扩展原语 |
| 作用域 | 编译器自动分离 Cube/Vector | 手动 with T.Scope("C"/"V") |
| 同步 | 编译器自动插入 | 手动 T.barrier_all / T.set_flag / T.wait_flag |
| CV 交互 | 默认消除 workspace+vid（threads=2 + 片上直连，见 §3.1.1） | 显式 GM workspace + 手动 vid 二分 |
| pass_configs | 全部开启 | 全部关闭或不设 |
| 适用场景 | 大多数算子，跨平台兼容 | 极致性能优化，需要底层控制 |
| 示例目录 | examples/developer_mode/ | examples/flash_attention/fa_opt/flash_attn_bhsd_expert_*.py |
混合模式：Developer 主体 + 少量 Expert / Ascend 专属 T.tile.xxx。使用 Developer 的 pass_configs，不写 T.Scope 和手动同步。大多数实际算子使用混合模式。
2. pass_configs 详解（核心）
2.1 四个 Ascend 专用开关
import tilelang
pass_configs = {
tilelang.PassConfigKey.TL_ASCEND_AUTO_SYNC: True, # ① 自动核内同步
tilelang.PassConfigKey.TL_ASCEND_MEMORY_PLANNING: True, # ② 自动内存规划
tilelang.PassConfigKey.TL_ASCEND_AUTO_CV_COMBINE: True, # ③ 自动CV分离
tilelang.PassConfigKey.TL_ASCEND_AUTO_CV_SYNC: True, # ④ 自动核间同步
}① TL_ASCEND_AUTO_SYNC（自动核内同步）
- 底层 key：
"tl.ascend_auto_sync"，默认 False - 功能：自动在数据搬运和计算之间插入
T.barrier_all()等同步指令 - 开启时：无需手写
T.barrier_all()、T.set_flag/T.wait_flag - 关闭时：必须手动插入所有同步点
② TL_ASCEND_MEMORY_PLANNING（自动内存规划）
- 底层 key：
"tl.ascend_memory_planning"，默认 False - 功能：自动分析 buffer 生命周期，实现片上内存复用
- 开启时：自动复用 buffer 空间，减少片上内存占用
- 关闭时：需手动通过
T.annotate_address规划内存地址
③ TL_ASCEND_AUTO_CV_COMBINE（自动 CV 分离）
- 底层 key：
"tl.ascend_auto_cv_combine"，默认 False - 功能：自动将 kernel 中的 Cube 操作和 Vector 操作分离到不同的执行核
- 开启时：无需手写
with T.Scope("C")/with T.Scope("V")，编译器根据 buffer 类型和所用原语自动识别 - 关闭时：必须手动用
T.Scope标注每段代码的执行域
注意：避免在开启 AUTO_CV_COMBINE 同时手写
T.Scope，可能会导致编译器无法正确处理代码
④ TL_ASCEND_AUTO_CV_SYNC（自动核间同步）
- 底层 key：
"tl.ascend_auto_cross_core_sync"，默认 False - 功能：自动在 Cube Scope 和 Vector Scope 之间插入
T.set_cross_flag/T.wait_cross_flag - 开启时：无需手写核间同步
- 关闭时：必须手动管理核间同步
2.2 按场景选择 pass_configs
| 场景 | AUTO_SYNC | MEMORY_PLANNING | AUTO_CV_COMBINE | AUTO_CV_SYNC | 手动 Scope |
|---|---|---|---|---|---|
| 纯 Vector 算子（elementwise, softmax） | ✅ | ✅ | ❌ | ❌ | ❌ |
| Developer GEMM（完全自动） | ✅ | ✅ | ✅ | ✅ | ❌ |
| Developer Flash Attention（核间流水线） | ✅ | ✅ | ✅ | ✅ | ❌ |
| Developer CV 融合（Vector计算+Cube GEMM） | ✅ | ✅ | ✅ | ✅ | ❌ |
| 混合模式 CV 融合 | ✅ | ✅ | ❌ | ❌ | ✅ |
Developer Flash Attention / Developer CV 融合：默认消除 workspace+vid（
threads=2+ 片上直连），写法见 §3.1.1 与 mode-examples.md §6。 | Expert 极致性能 | ❌ | ❌ | ❌ | ❌ | ✅ |
纯 Vector 算子（来自 Programming Guide §2.2）：
pass_configs = {
tilelang.PassConfigKey.TL_ASCEND_AUTO_SYNC: True,
tilelang.PassConfigKey.TL_ASCEND_MEMORY_PLANNING: True,
}Developer GEMM / Developer CV 融合（推荐配置）：
pass_configs = {
tilelang.PassConfigKey.TL_ASCEND_AUTO_CV_COMBINE: True, # 自动分离 Cube/Vector
tilelang.PassConfigKey.TL_ASCEND_AUTO_SYNC: True, # 自动核内同步
tilelang.PassConfigKey.TL_ASCEND_MEMORY_PLANNING: True, # 自动内存规划
tilelang.PassConfigKey.TL_ASCEND_AUTO_CV_SYNC: True, # 自动核间同步
}Expert 全手动：
pass_configs = {
tilelang.PassConfigKey.TL_ASCEND_AUTO_CV_COMBINE: False,
tilelang.PassConfigKey.TL_ASCEND_AUTO_CV_SYNC: False,
tilelang.PassConfigKey.TL_ASCEND_MEMORY_PLANNING: False,
tilelang.PassConfigKey.TL_ASCEND_AUTO_SYNC: False,
}3. 模式转换规则（Expert → Developer）
3.1 转换步骤
- 开启 pass_configs：添加完整 4 个 True 开关
- 内存分配：
T.alloc_L1→T.alloc_shared，T.alloc_L0C→T.alloc_fragment，T.alloc_ub→T.alloc_shared - 删除作用域：移除
with T.Scope("C")/with T.Scope("V") - 删除同步：移除
T.barrier_all()、T.set_flag/T.wait_flag、T.set_cross_flag/T.wait_cross_flag - 计算转换（可选）：
T.tile.exp(dst, src)→for i,j in T.Parallel(...): dst[i,j] = T.exp(src[i,j]) - 删除手动内存规划：移除
T.annotate_address
Show full SKILL.md (192 more words)Show less
3.1.1 Developer 模式 CV 交互：优先消除 workspace / vid
Developer 模式下 Cube↔Vector 交互默认不写 GM workspace、不手动二分 vid，交给编译器自动处理。前提链（按序，不可跳级）：
threads=2 ──► vid 消除 ──► workspace 消除四步改造：
- 加
threads=2：T.Kernel(block_num, is_npu=True) as (cid, vid)→T.Kernel(block_num, threads=2, is_npu=True) as (cid)（编译器自动并行 2 个 V 核，这是消 vid 的前提）。 - 删
workspace_idx：@tilelang.jit(out_idx=[N], workspace_idx=[...], ...)→@tilelang.jit(out_idx=[N], ...)，并删除 kernel 签名里的workspace_*参数。 - 去 vid 偏移：
v_block不再// 2，循环恢复整程range(BI)，删除全部vid * ...索引偏移。 - 片上直连：原「片上 buffer ↔
workspace[cid,...]↔ 另一片上 buffer」两跳 GM 往返，合并为片上T.copy一跳；中转/同步交给四个 pass。
完整模板、映射表、代码骨架、自检清单与回退条件见 mode-examples.md §6。 复杂同步/多版本流水场景可回退保留 workspace+vid 写法（见 mode-examples.md §7）。
3.2 转换对照表
| Expert 写法 | Developer 写法 |
|---|---|
T.alloc_L1(shape, dtype) | T.alloc_shared(shape, dtype) |
T.alloc_ub(shape, dtype) | T.alloc_shared(shape, dtype) |
T.alloc_L0A/L0B(shape, dtype) | 删除（gemm_v0 内部处理） |
T.alloc_L0C(shape, dtype) | T.alloc_fragment(shape, dtype) |
with T.Scope("C"): ... | 直接写代码（编译器自动分离） |
T.barrier_all() | 删除（编译器自动插入） |
T.set_flag/T.wait_flag(...) | 删除 |
T.set_cross_flag/T.wait_cross_flag(...) | 删除 |
T.tile.exp(dst, src) | for i,j in T.Parallel(...): dst[i,j] = T.exp(src[i,j]) 或保留 |
T.annotate_address({...}) | 删除（开启 MEMORY_PLANNING） |
@jit(..., workspace_idx=[...]) + 签名 workspace_* 参数 | 删除（CV 交互改片上直连，见 §3.1.1） |
T.Kernel(..., is_npu=True) as (cid, vid) | T.Kernel(..., threads=2, is_npu=True) as (cid)（消 vid 前提） |
T.copy(buf, ws[cid,...]) + T.copy(ws[cid,vid*..], buf2) 两跳 | T.copy(buf, buf2) 片上一跳直连 |
4. 示例代码与代码对比
| 模式 | 目录 | 说明 |
|---|---|---|
| Developer | examples/developer_mode/ | GEMM、elementwise 等 |
| Developer（消除 workspace/vid） | examples/developer_mode/sparse_flash_attn_developer_vid_reduce.py（新）vs sparse_flash_attn_developer.py（旧） | threads=2 + 片上直连，逐行对照消除范式 |
| Expert | examples/gemm/example_gemm_intrinsic.py、examples/flash_attention/fa_opt/flash_attn_bhsd_expert_*.py | 极致性能优化 |
| 混合（核间流水线） | examples/flash_attention/flash_attn_bhsd_cc_sync.py、examples/flash_attention/fa_opt/flash_attn_bhsd_auto_pipeline_*.py | FA 核间流水线 |
| 纯 Vector | examples/elementwise/、examples/softmax/ | 无 Cube 操作 |
| CV 融合 | examples/dequantize_gemm/、examples/quant_batch_matmul/ | Vector 计算 + Cube GEMM |
完整代码对比（Developer vs Expert）：
- → mode-examples.md
- 包含 GEMM、Flash Attention、Softmax、CV 融合（消除 workspace/vid 推荐写法 §6 / workspace+vid 兜底写法 §7） 等示例
© 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
Files
SKILL.md and 1 other file (references) in .agents/skills/tilelang-custom-skill/tilelang-programming-model-guide of tile-ai/tilelang-ascend.
- SKILL.md
- references/mode-examples.md
Open the folder on GitHubat commit 3d17c28
Compare with similar skills
Tilelang Programming Model Guide 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 Programming Model Guide this skilltile-ai/tilelang-ascend | 400 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Vercel Composition Patternssupabase/supabase | 111k | 59 repos | ~726 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Typescript Advanced Types
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
More from tile-ai/tilelang-ascend
All 20 skills in this repoTilelang Submodule Pull
tile-ai/tilelang-ascend
Automatically pull tilelang repository and its third-party code.
Tilelang Debug Helper
tile-ai/tilelang-ascend
How to add debugging capabilities to TileLang Ascend example operators.
Tilelang A5 Sim Convert
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。
Tilelang Env Check
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…
Tilelang Op Test Design
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。
Tilelang Review
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…
Related
Categories
Questions about Tilelang Programming Model Guide
What does Tilelang Programming Model Guide do?
TileLang Ascend Developer/Expert 模式选择与 passconfigs 配置指南。当需要确定编程模式、配置 passconfigs、或在两种模式之间转换时触发。API 详情请参考 tilelang-api-best-practices skill。. Tilelang Programming Model Guide is an agent skill from tile-ai/tilelang-ascend.
When should I use Tilelang Programming Model Guide?
Tilelang Programming Model Guide fits situations like: development work in your project.
How do I install Tilelang Programming Model Guide in Claude Code?
Run `npx skills add tile-ai/tilelang-ascend --skill tilelang-programming-model-guide -a claude-code`. Or copy the skill folder (.agents/skills/tilelang-custom-skill/tilelang-programming-model-guide in tile-ai/tilelang-ascend) into .claude/skills/tilelang-programming-model-guide in your project. Claude Code loads it when a task matches its description.
How do I install Tilelang Programming Model Guide in Codex?
Run `npx skills add tile-ai/tilelang-ascend --skill tilelang-programming-model-guide -a codex`. Or copy the skill folder (.agents/skills/tilelang-custom-skill/tilelang-programming-model-guide in tile-ai/tilelang-ascend) into .agents/skills/tilelang-programming-model-guide in your project. Codex loads it when a task matches its description.
Can I use Tilelang Programming Model Guide in Cursor, Gemini CLI or GitHub Copilot?
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-programming-model-guide -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-programming-model-guide, .gemini/skills/tilelang-programming-model-guide, .github/skills/tilelang-programming-model-guide and .opencode/skills/tilelang-programming-model-guide in your project.
What does Tilelang Programming Model Guide need to run?
SKILL.md names no scripts, command-line tools or credentials: Tilelang Programming Model Guide is instructions for the agent only. Our summary lists: Python 3.
Does Tilelang Programming Model Guide access the network?
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.
Is Tilelang Programming Model Guide safe to install?
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.
What licence does Tilelang Programming Model Guide use?
Tilelang Programming Model Guide is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Tilelang Programming Model Guide use?
About 1.8k tokens (SKILL.md is roughly 7.3k 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 4.2k tokens, read only when the agent opens those files.
What are the alternatives to Tilelang Programming Model Guide?
Skills that share tags, products or a category with Tilelang Programming Model Guide: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Tilelang Programming Model Guide?
tile-ai (a GitHub organization) maintains it in tile-ai/tilelang-ascend, which has 400 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 8, 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.