The Art of Debugging
stas00/the-art-of-debugging
Condensed debugging method and tool recipes for Unix, Python and PyTorch programs: crashes, hangs, segfaults, wrong output, CUDA OOM, NaN values and slowness.
End-to-end AscendC custom operator development for Ascend NPU in an ascend-kernel (csrc/ops + build.sh + torchnpu PyTorch custom op) project.
Install Ascendc
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill ascendc -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills ascendc --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/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ops/ascendc .claude/skills/ascendc && 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 "ascendc" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/ops/ascendc into .claude/skills/ascendc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ascendc", 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/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/ops/ascendcType 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 ascend-ai-coding/awesome-ascend-skills --skill ascendc -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills ascendc --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ops/ascendc .agents/skills/ascendc && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ascendc" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/ops/ascendc into .agents/skills/ascendc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ascendc", 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 ascend-ai-coding/awesome-ascend-skills --skill ascendc -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills ascendc --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ops/ascendc .cursor/skills/ascendc && 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 "ascendc" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/ops/ascendc into .cursor/skills/ascendc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ascendc", 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/ascend-ai-coding/awesome-ascend-skills.git --path skills/ops/ascendc--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 ascend-ai-coding/awesome-ascend-skills --skill ascendc -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills ascendc --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ops/ascendc .gemini/skills/ascendc && 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 "ascendc" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/ops/ascendc into .gemini/skills/ascendc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ascendc", 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 ascend-ai-coding/awesome-ascend-skills ascendcInstalls 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 ascend-ai-coding/awesome-ascend-skills --skill ascendc -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ops/ascendc .github/skills/ascendc && 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 "ascendc" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/ops/ascendc into .github/skills/ascendc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ascendc", 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 ascend-ai-coding/awesome-ascend-skills --skill ascendc -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills ascendc --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ops/ascendc .opencode/skills/ascendc && 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 "ascendc" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/ops/ascendc into .opencode/skills/ascendc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ascendc", 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
ascendc- GitHub stars
- 174
- Token cost
- ~3.5k tokens
- SKILL.md length
- 1,406 words
- Files
- 89 (incl. scripts, references)
- Skills in repo
- 69
- Repo updated
- First seen
- Licence
- None found
At a glance
End-to-end AscendC custom operator development for Ascend NPU in an ascend-kernel (csrc/ops + build.sh + torchnpu PyTorch custom op) project.
- Works in 11 steps: Environment and requirements → Project init → Design (design.md) → …
- Tune a new AscendC operator from a name and a math/functional spec
- SKILL.md covers How to use this skill, When to use, Lifecycle overview and Phase 0 — Environment and…, plus 15 more sections
- Runs Python scripts from its folder; calls conda, bash and pip
What it does
Ascendc is an agent skill from ascend-ai-coding/awesome-ascend-skills. End-to-end AscendC custom operator development for Ascend NPU in an ascend-kernel (csrc/ops + build.sh + torchnpu PyTorch custom op) project. Use to design, generate, build, test, document, and tune a new AscendC operator from a name and a math/functional spec. Covers project init, two-level tiling design, ophost/opkernel code generation, framework registration, compile/install/debug, PyTorch-style API docs, precision evaluation and root-cause debugging, torchnpu.profiler performance benchmarking, performance…
Its SKILL.md is about 3.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 92 other files, including scripts and reference files (for example `examples/layer_norm_profiler_reference/LAYER_NORM_PROFILER_PERF_GUIDE.md`, `examples/layer_norm_profiler_reference/README.md` and `examples/layer_norm_profiler_reference/benchmark_layer_norm_torch_npu_profiler.py`).
It sits in Development, covering Performance optimization, Deep learning and Technical documentation. It works with PyTorch. The repository describes itself as: A comprehensive knowledge base for Huawei Ascend NPU development, structured as distributed Agent Skills. https://ascend-ai-coding.github.io/awesome-ascend-skills/.
When your agent uses it
- Tune a new AscendC operator from a name and a math/functional spec
- Tasks that involve Performance optimization
- Tasks that involve Deep learning
Example prompts
- “/ascendc”
Requirements
- Python 3
Workflow steps
11 steps, taken from the step headings in SKILL.md.
- Environment and requirements
- Project init
- Design (design.md)
- Test cases
- Code generation + framework adaptation
- Compile, install, test, debug
- Interface docs
- Precision evaluation
- Performance evaluation
- Performance optimization (optional, closed loop)
- Code review (optional)
What it can do on your machine
Read from SKILL.md and the folder at commit 62a4ecb. 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
Ships 1 file in scripts/ (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
condabashpippythonpytest
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
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
Ascendc loads about 3.5k tokens when it runs, and up to ~19k if it reads all its reference files. Until then it costs about 142 tokens; SKILL.md has 1,406 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); the scripts in this folder are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 1,406 words (~3,525 tokens).
“This skill drives a new AscendC custom operator from a spec to a production-ready, benchmarked operator inside an ascend-kernel project (a PyTorch custom-op project that exposes operators as torch.ops.npu. via csrc/ops/, csrc/register.cpp, and build.sh). It is self-contained: every phase, template…”
- name
- ascendc
- keywords
- ascend, ascendc, operator, kernel, npu, ascend-kernel, op_host, op_kernel, tiling, code generation, precision, performance, profiler, code review, end-to-end
Files
SKILL.md and 88 other files (scripts, references) in skills/ops/ascendc of ascend-ai-coding/awesome-ascend-skills.
- SKILL.md
- examples/layer_norm_profiler_reference/LAYER_NORM_PROFILER_PERF_GUIDE.md
- examples/layer_norm_profiler_reference/README.md
- examples/layer_norm_profiler_reference/benchmark_layer_norm_torch_npu_profiler.py
- examples/layer_norm_profiler_reference/layer_norm_perf_cases.jsonl
- examples/layer_norm_profiler_reference/layer_norm_profiler_common.py
- examples/precision-debug/async-sync-missing.md
- examples/precision-debug/fp16-no-upcast.md
- examples/precision-debug/gm-offset-error.md
- examples/precision-debug/multicore-tiling-overlap.md
- examples/precision-debug/tail-tile-misalign.md
- examples/sample_perf_cases.jsonl
- examples/sample_report.md
- references/00-environment.md
- references/01-project-init.md
- references/02-design.md
- references/03-testcase-gen.md
- … and 72 more
Open the folder on GitHubat commit 62a4ecb
Compare with similar skills
Ascendc 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 |
|---|---|---|---|---|---|---|
| Ascendc this skillascend-ai-coding/awesome-ascend-skills | 174 | — | ~3.5k | Automated safety check: Pass | None | |
| The Art of Debuggingstas00/the-art-of-debugging | 1.7k | — | ~6.1k | Automated safety check: Notes | CC-BY-SA-4.0 | |
| Veomni DebugByteDance-Seed/VeOmni | 2.2k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Docstringpytorch/pytorch | 104k | 2 repos | ~2.6k | Automated safety check: Pass | Custom licence | |
| Qualcomm QNN Backend Developmentpytorch/executorch | 5.1k | — | ~1.8k | Automated safety check: Pass | Custom licence | |
| Pt2 Bug Basherpytorch/pytorch | 104k | — | ~3.5k | Automated safety check: Pass | Custom licence |
Similar skills
Veomni Debug
ByteDance-Seed/VeOmni
A skill your agent uses for ANY bug, error, crash, wrong output, loss divergence, gradient explosion, test failure, CUDA error, distributed training hang, checkpoint load failure, or unexpected…
Docstring
pytorch/pytorch
Write docstrings for PyTorch functions and methods following PyTorch conventions.
Qualcomm QNN Backend Development
pytorch/executorch
Helps build, test and extend the Qualcomm AI Engine Direct (QNN) backend in ExecuTorch, with routes for new ops, model export, Buck-vs-CMake parity fixes and per-layer accuracy debugging.
Pt2 Bug Basher
pytorch/pytorch
Debug PyTorch 2 compiler stack failures including Dynamo graph breaks, Inductor codegen errors, AOTAutograd crashes, and accuracy mismatches.
- Official
Xpu CI Health Check
intel/torch-xpu-ops
Check PyTorch ciflow/xpu (xpu.yml) on the main branch, collect the failing XPU test cases from the most recent completed run(s), analyze the ROOT CAUSE of each failure with AI, and produce a list…
More from ascend-ai-coding/awesome-ascend-skills
All 69 skills in this repoAscend Dmi
ascend-ai-coding/awesome-ascend-skills
当用户需要对华为昇腾 NPU 进行硬件层面的管理、测试或诊断时使用此 skill。典型场景： - 查看 NPU 卡的状态、温度、利用率 - 测试内存带宽（h2d/d2h/d2d/p2p） - 跑算力/功耗基准测试（TFLOPS、TOPS） - 诊断 NPU 硬件故障或做健康检查 - 对 NPU 卡做压力测试（aicore、内存） - 复位/恢复卡住或异常的 NPU 卡 典型用户问题（即使不提…
Atc Model Converter
ascend-ai-coding/awesome-ascend-skills
Complete toolkit for Huawei Ascend NPU model conversion and end-to-end inference adaptation.
External Cannbot Ops Pypto Op Develop
ascend-ai-coding/awesome-ascend-skills
当需要编写 PyPTO 算子实现时使用此 skill。基于需求规格、设计方案和参考实现，生成完整可运行的 PyPTO 算子实现与配套测试、文档。Triggers: 实现算子、写 kernel、编写实现、写 impl、算子编码、开始编码、code the op、写 test、生成测试、写实现代码、op develop、kernel 实现。
External Gitcode Ascend Megatron Change Analyzer
ascend-ai-coding/awesome-ascend-skills
Analyze official Megatron-LM commits, PRs, and branch change sets to identify feature evolution, candidate breaking changes, and migration-relevant events.
External Gitcode Ascend Megatron Commit Tracker
ascend-ai-coding/awesome-ascend-skills
Track and normalize change requests against the official Megatron-LM repository by branch, PR, commit, commit range, or time window.
External Gitcode Ascend Megatron Impact Mapper
ascend-ai-coding/awesome-ascend-skills
Map migration-relevant Megatron changes onto the official MindSpeed repository by resolving branch alignment, locating affected subsystems, and identifying concrete adaptation points.
Related
Works with
Categories
Questions about Ascendc
What does Ascendc do?
End-to-end AscendC custom operator development for Ascend NPU in an ascend-kernel (csrc/ops + build.sh + torchnpu PyTorch custom op) project. Ascendc is an agent skill from ascend-ai-coding/awesome-ascend-skills.sh + torchnpu PyTorch custom op) project.
When should I use Ascendc?
Ascendc fits situations like: tune a new AscendC operator from a name and a math/functional spec; tasks that involve Performance optimization; tasks that involve Deep learning.
How do I install Ascendc in Claude Code?
Run `npx skills add ascend-ai-coding/awesome-ascend-skills --skill ascendc -a claude-code`. Or copy the skill folder (skills/ops/ascendc in ascend-ai-coding/awesome-ascend-skills) into .claude/skills/ascendc in your project. Claude Code loads it when a task matches its description.
How do I install Ascendc in Codex?
Run `npx skills add ascend-ai-coding/awesome-ascend-skills --skill ascendc -a codex`. Or copy the skill folder (skills/ops/ascendc in ascend-ai-coding/awesome-ascend-skills) into .agents/skills/ascendc in your project. Codex loads it when a task matches its description.
Can I use Ascendc 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 ascend-ai-coding/awesome-ascend-skills --skill ascendc -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ascendc, .gemini/skills/ascendc, .github/skills/ascendc and .opencode/skills/ascendc in your project.
What does Ascendc need to run?
Going by SKILL.md and its folder, Ascendc needs Python for the scripts in its folder and the command-line tools its instructions call (conda, bash, pip, python and pytest). Our summary lists: Python 3.
Does Ascendc access the network?
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Ascendc 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Ascendc use?
No licence was found for Ascendc or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Ascendc use?
About 3.5k tokens (SKILL.md is roughly 14k 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 15k tokens, read only when the agent opens those files.
What are the alternatives to Ascendc?
Skills that share tags, products or a category with Ascendc: The Art of Debugging (stas00/the-art-of-debugging, 1.7k stars), Veomni Debug (ByteDance-Seed/VeOmni, 2.2k stars), Docstring (pytorch/pytorch, 104k stars) and Qualcomm QNN Backend Development (pytorch/executorch, 5.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Ascendc?
ascend-ai-coding (a GitHub organization) maintains it in ascend-ai-coding/awesome-ascend-skills, which has 174 GitHub stars. The repository holds 69 skills in this directory. The repository was last updated on October 7, 2026.
Source: ascend-ai-coding/awesome-ascend-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.