Graphsignal
graphsignal/graphsignal
Profile AI inference workloads (vLLM, SGLang, TensorRT-LLM, PyTorch, any GPU application) with the Graphsignal profiler and read the results from its local /signals JSON endpoint.
自动化 verl msprobe 精度数据采集；开始前检查/预装 msprobe（pip install mindstudio-probe）。自动识别三种模式：(1) 训练采集——globalprofiler + precisiondebugger stages；(2) 推理采集——vLLM/SGLang rollout dump；(3) 训推一致性——engine patch +…
Install Rl Msprobe
$ npx skills add ascend-ai-coding/awesome-ascend-skills --skill rl-msprobe -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills rl-msprobe --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/training/rl-msprobe .claude/skills/rl-msprobe && 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 "rl-msprobe" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/rl-msprobe into .claude/skills/rl-msprobe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rl-msprobe", 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/training/rl-msprobeType 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 rl-msprobe -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills rl-msprobe --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/training/rl-msprobe .agents/skills/rl-msprobe && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "rl-msprobe" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/rl-msprobe into .agents/skills/rl-msprobe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rl-msprobe", 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 rl-msprobe -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills rl-msprobe --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/training/rl-msprobe .cursor/skills/rl-msprobe && 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 "rl-msprobe" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/rl-msprobe into .cursor/skills/rl-msprobe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rl-msprobe", 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/training/rl-msprobe--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 rl-msprobe -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ascend-ai-coding/awesome-ascend-skills rl-msprobe --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/training/rl-msprobe .gemini/skills/rl-msprobe && 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 "rl-msprobe" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/rl-msprobe into .gemini/skills/rl-msprobe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rl-msprobe", 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 rl-msprobeInstalls 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 rl-msprobe -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/training/rl-msprobe .github/skills/rl-msprobe && 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 "rl-msprobe" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/rl-msprobe into .github/skills/rl-msprobe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rl-msprobe", 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 rl-msprobe -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 rl-msprobe --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/training/rl-msprobe .opencode/skills/rl-msprobe && 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 "rl-msprobe" agent skill from https://github.com/ascend-ai-coding/awesome-ascend-skills/tree/main/skills/training/rl-msprobe into .opencode/skills/rl-msprobe/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "rl-msprobe", 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
rl-msprobe- GitHub stars
- 174
- Token cost
- ~2.4k tokens
- SKILL.md length
- 470 words
- Files
- 24 (incl. scripts, references, assets)
- Skills in repo
- 70
- Repo updated
- First seen
- Licence
- None found
At a glance
自动化 verl msprobe 精度数据采集；开始前检查/预装 msprobe（pip install mindstudio-probe）。自动识别三种模式：(1) 训练采集——globalprofiler + precisiondebugger stages；(2) 推理采集——vLLM/SGLang rollout dump；(3) 训推一致性——engine patch +…
- Tasks that involve LLM inference and serving
- SKILL.md covers 前置：msprobe 环境（必做）, 第 0 步：识别采集模式, 路径 A：训练采集（training） and 路径 B：推理采集（inference）, plus 4 more sections
- Runs Python scripts from its folder; calls bash, python3 and pip
- Tasks that involve Performance optimization
What it does
Rl Msprobe is an agent skill from ascend-ai-coding/awesome-ascend-skills. 自动化 verl msprobe 精度数据采集；开始前检查/预装 msprobe（pip install mindstudio-probe）。自动识别三种模式：(1) 训练采集——globalprofiler + precisiondebugger stages；(2) 推理采集——vLLM/SGLang rollout dump；(3) 训推一致性——engine patch + PROMPTSONLY。触发词：verl dump、msprobe、mindstudio-probe、训练采集、推理采集、训推一致性、PrecisionDebugger。
Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 26 other files, including scripts, reference files and assets (for example `references/consistency-auxiliary-patches.md`, `references/consistency-engine-worker.md` and `references/dump-output-correlation.md`).
It sits in AI & LLM Engineering, covering LLM inference and serving and Performance optimization. It works with SGLang and vLLM. 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
- Tasks that involve LLM inference and serving
- Tasks that involve Performance optimization
Example prompts
- “/rl-msprobe”
Requirements
- Python 3
- A Bash shell
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 2 files in scripts/ (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
bashpython3pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
gitcode.com
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
Rl Msprobe loads about 2.4k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 73 tokens; SKILL.md has 470 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 470 words (~2,444 tokens).
- name
- rl-msprobe
- keywords
- verl, msprobe, dump, precision_debugger, 训推一致性, 训练采集, 推理采集, vllm, sglang, fsdp, megatron, enforce_eager, global_profiler, mindstudio-probe
Files
SKILL.md and 23 other files (scripts, references, assets) in skills/training/rl-msprobe of ascend-ai-coding/awesome-ascend-skills.
- SKILL.md
- assets/config_actor.json.example
- assets/config_generate.json.example
- assets/config_training_statistics.json.example
- assets/config_training_tensor.json.example
- assets/run_consistency_dump.sh.example
- assets/run_consistency_dump_megatron.sh.example
- references/consistency-auxiliary-patches.md
- references/consistency-engine-worker.md
- references/dump-output-correlation.md
- references/fsdp-engine-patch.md
- references/inference-sglang-dump.md
- references/inference-vllm-dump.md
- references/megatron-engine-patch.md
- references/shared-prerequisites.md
- references/training-profiler-dump.md
- scripts/check-consistency-patch.py
- scripts/check-engine-patch.py
- … and 6 more
Open the folder on GitHubat commit 62a4ecb
Compare with similar skills
Rl Msprobe 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 |
|---|---|---|---|---|---|---|
| Rl Msprobe this skillascend-ai-coding/awesome-ascend-skills | 174 | — | ~2.4k | Automated safety check: Pass | None | |
| Graphsignalgraphsignal/graphsignal | 257 | — | ~6.2k | Automated safety check: Pass | Apache-2.0 | |
| LLM Torch Profiler Trace AnalysisBBuf/AI-Infra-Auto-Driven-SKILLS | 925 | — | ~2.8k | Automated safety check: Pass | None | |
| LLM Pipeline Profiler AnalysisBBuf/AI-Infra-Auto-Driven-SKILLS | 925 | — | ~3.9k | Automated safety check: Pass | None | |
| LLM Serving Framework BenchmarkBBuf/AI-Infra-Auto-Driven-SKILLS | 925 | — | ~7.5k | Automated safety check: Pass | None | |
| Magpie Kernel Evaluatoramd/skills | 406 | — | ~2.3k | Automated safety check: Pass | MIT |
Similar skills
LLM Torch Profiler Trace Analysis
BBuf/AI-Infra-Auto-Driven-SKILLS
Analyzes Torch Profiler traces from SGLang, vLLM and TensorRT-LLM servers into kernel attribution, overlap and fusion tables.
LLM Pipeline Profiler Analysis
BBuf/AI-Infra-Auto-Driven-SKILLS
Breaks LLM torch profiler traces down by forward pass, layer and kernel, with timing tables and Perfetto time ranges for the layers you want to inspect.
LLM Serving Framework Benchmark
BBuf/AI-Infra-Auto-Driven-SKILLS
Compares SGLang, vLLM, TensorRT-LLM and TokenSpeed on one model and workload, searching server flags to find the best deployment command within a latency SLA.
Magpie Kernel Evaluator
amd/skills
Benchmarks LLM inference and drives GPU kernel optimization with Magpie.
LLM Torch Profiler Analysis
sgl-project/sglang
Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.
More from ascend-ai-coding/awesome-ascend-skills
All 70 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…
Ascendc
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.
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.
Related
Categories
Questions about Rl Msprobe
What does Rl Msprobe do?
自动化 verl msprobe 精度数据采集；开始前检查/预装 msprobe（pip install mindstudio-probe）。自动识别三种模式：(1) 训练采集——globalprofiler + precisiondebugger stages；(2) 推理采集——vLLM/SGLang rollout dump；(3) 训推一致性——engine patch +…. Rl Msprobe is an agent skill from ascend-ai-coding/awesome-ascend-skills.
When should I use Rl Msprobe?
Rl Msprobe fits situations like: tasks that involve LLM inference and serving; tasks that involve Performance optimization.
How do I install Rl Msprobe in Claude Code?
Run `npx skills add ascend-ai-coding/awesome-ascend-skills --skill rl-msprobe -a claude-code`. Or copy the skill folder (skills/training/rl-msprobe in ascend-ai-coding/awesome-ascend-skills) into .claude/skills/rl-msprobe in your project. Claude Code loads it when a task matches its description.
How do I install Rl Msprobe in Codex?
Run `npx skills add ascend-ai-coding/awesome-ascend-skills --skill rl-msprobe -a codex`. Or copy the skill folder (skills/training/rl-msprobe in ascend-ai-coding/awesome-ascend-skills) into .agents/skills/rl-msprobe in your project. Codex loads it when a task matches its description.
Can I use Rl Msprobe 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 rl-msprobe -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/rl-msprobe, .gemini/skills/rl-msprobe, .github/skills/rl-msprobe and .opencode/skills/rl-msprobe in your project.
What does Rl Msprobe need to run?
Going by SKILL.md and its folder, Rl Msprobe needs Python for the scripts in its folder and the command-line tools its instructions call (bash, python3 and pip). Our summary lists: Python 3; A Bash shell.
Does Rl Msprobe access the network?
SKILL.md names 1 domain. As links in the text: gitcode.com. This is read from the text; nothing was executed.
Is Rl Msprobe 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 Rl Msprobe use?
No licence was found for Rl Msprobe or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Rl Msprobe use?
About 2.4k tokens (SKILL.md is roughly 9.8k 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 12k tokens, read only when the agent opens those files.
What are the alternatives to Rl Msprobe?
Skills that share tags, products or a category with Rl Msprobe: Graphsignal (graphsignal/graphsignal, 257 stars), LLM Torch Profiler Trace Analysis (BBuf/AI-Infra-Auto-Driven-SKILLS, 925 stars), LLM Pipeline Profiler Analysis (BBuf/AI-Infra-Auto-Driven-SKILLS, 925 stars) and LLM Serving Framework Benchmark (BBuf/AI-Infra-Auto-Driven-SKILLS, 925 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Rl Msprobe?
ascend-ai-coding (a GitHub organization) maintains it in ascend-ai-coding/awesome-ascend-skills, which has 174 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on October 9, 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.