Explore skills
Search every indexed skill by name, description, repository or instructions, then narrow the results.
Showing 53071–53100 of 57339 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| spike-root-cause-analysisAscend/msagent分布式训练梯度尖刺 (Gradient Spike) 根因定位。基于梯度监控数据 (trend.db/CSV)、 msprobe dump 统计数据,三阶段渐进式从异常坐标定位逐层深入到算子级根因。 当用户明确指明分析梯度尖刺问题时使用此 skill。 即便用户提供以上数据,但未指明分析梯度尖刺问题时,不可使用此skill。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| train-infer-op-diff-scannerAscend/msagentRL 强化学习训练与推理(rollout)路径的算子差异性扫描。当用户提供训练启动脚本路径,要求对比 Megatron 训练路径与 vLLM 推理路径的算子差异(尤其是融合算子 vs 单算子不一致)时使用此 skill。典型触发词包括"训推算子扫描"、"训推差异性"、"算子差异报告"、"融合算子对比"、"train vs infer op diff"。注意:本 skill 通过运行完整 RL 训练脚本(集成 profiling)来采集真实运行时算子(非静态源码扫描,非独立分离运行)。当训练、推理使用不同脚本时禁止触发。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| verl-omni-msprobe-dumpAscend/msagent为 verl-omni 接入或修复 MSProbe 训推一致性采集,生成打点代码、样本关联日志和诊断启动脚本。 用于 diffusion/omni 的 rollout 与 actor 数据采集、dump 缺失或配对失败;不负责精度根因分析。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| github-raw-fetchAscend/msagent当用户提供 GitHub 文件页面链接,或希望读取某个仓库中的源码、配置、README、Markdown、docs 内容时,使用此技能。技能支持将 `github.com/<owner>/<repo>/blob/<ref>/...` 转换为 `raw.githubusercontent.com` 链接并获取内容;读取仓库 docs 时先列出仓库根目录、按真实结构定位 `docs/` 目录(语言子目录、索引),不要假设所有仓库都有固定目录或 `agent_router.md`(该文件仅当根目录确实存在时才可选参考)。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| aisbench-dataset-compression-herdingAscend/msagent当用户直接要求进行数据集压缩测评,或在量化调优过程中需要使用 AISBench 评测工具输出数据集精度等场景时使用。 本 Skill 负责:使用 AISBench 数据集压缩代码、用 RBF Kernel Herding 算法生成压缩后的数据子集(coreset),并按用户目标交付两种产物之一: ① 接入量化调优主流程:产出独立的 coreset 数据集配置(不覆盖原始数据),回传「全集 config_name + coreset config_name」给编排层,供 evaluation.yaml 切换; ② 仅数据集压缩测评(不做量化调优):基于 example 模板生成「全集测试脚本」和「子集测试脚本」两份 shell 脚本。 暂时支持 AIME 2025 和 GPQA,其他数据集需要再结合 aisbench tools目录下 herding_coreset_selector 源码进行分析。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| run-aisbench-evaluationAscend/msagent解析中文自然语言中的 AISBench 测评需求,检查 Python 与 AISBench 运行环境,通过分轮追问确认关键配置,将基准名称映射为仓库内的数据集任务,在用户最终确认后生成并执行 AISBench CLI,并返回精度指标和产物路径。适用于用户要求使用 AISBench 评测模型或运行数据集;不适用于实现新数据集或仅解释基准概念。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| document-ux-reviewAscend/msagent当用户希望你像第一次接触项目的人一样,真实按仓库的 README、安装文档或 quick start 跑一遍,并判断“新人能不能走通”“文档是否可用”“哪里会卡住”“安装/启动说明是否对新手友好”时,使用这个 skill。它适用于 repo onboarding audit、documentation UX review、quickstart validation、README walkthrough、按文档验证安装与运行并输出问题报告的场景;即使用户只是说“按 README 试一下”“帮我检查这个仓库文档能不能跑通”“看看 quick start 为什么带不动新人”,也应触发。不要用于纯翻译、润色、摘要、风格对比、治理项检查,或只想直接修环境/修单个报错而不做完整文档体验审查的请求。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| msmodeling-device-configAscend/msagent在需要根据自然语言规格为未支持硬件新增或更新 DeviceProfile 设备画像条目时使用 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| msmodeling-env-installerAscend/msagentInstall and verify the msmodeling development environment. Use when the user explicitly asks to install msmodeling dependencies, set up this repository, create `myenv` with `uv`, install this repository's `requirements.txt`, set project `PYTHONPATH`, or configure `HF_ENDPOINT`; if the user only says to install an environment, ask whether they mean msmodeling dependencies before proceeding. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| msmodeling-optix-deployAscend/msagent当用户需要部署 msmodeling optix 服务化自动寻优工具时使用。负责安装与验证。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| msmodeling-optix-param-recommendAscend/msagent当首次使用 msmodeling optix 的用户需要根据硬件、模型、负载和优化目标推荐 MindIE/vLLM 寻优参数、搜索范围、benchmark 侧字段或 config.toml 片段时使用。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| msmodeling-text-generate-executorAscend/msagentInteractively gather parameters for `python -m cli.inference.text_generate`, generate a concrete text generation simulation command, explain assumptions, ask for execution confirmation, then run the command and summarize performance metrics. Use when the user wants to validate a specific model, hardware profile, batch/query size, prefill or decode scenario, TP/DP/EP/MOE parallel strategy, profiling database, chrome trace, empirical metrics export, or a best row produced by throughput_optimizer. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| msmodeling-throughput-optimizer-executorAscend/msagentInteractively gather parameters for `python -m cli.inference.throughput_optimizer`, generate a deployment simulation command, explain assumptions, ask for execution confirmation, then run the simulation and summarize the best parallel strategy. Use when the user wants to evaluate a model on one or more hardware profiles, compare hardware targets, compare aggregation versus disaggregation versus PD ratio optimization, choose TP/EP/MOE-DP search ranges, or obtain recommended concurrency, throughput, TTFT, and TPOT results from throughput modeling. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| msdebug-basic-usageAscend/msagent昇腾AscendC算子调试工具(msDebug)技能,含两大流程:①上板调试——算子加 -g -O0 编译后由 msdebug 拉起,支持断点、单步、变量/内存打印、核切换、寄存器读取;②coredump解析——用户指定 core 文件路径后,msdebug 加载解析挂掉代码行/异常调用栈/现场变量。触发关键词:msdebug、算子调试、上板调试、断点、单步调试、打印变量、读内存、核切换、寄存器、coredump、core文件、调用栈、崩溃解析 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| msot-msopprof-operator-profilerAscend/msagent当用户希望使用 msOpProf(`msprof op` / `msprof op simulator`)对昇腾 AI 算子做上板或仿真性能调优、解释 `aic-metrics`/`trace.json`/`visualize_data.bin`、选择 device vs simulator 路径、排查 `--soc-version`/`--export`/`signal 6`/`Bad address`/热点图或流水图相关问题,或要求生成固定分析报告模板(算子基本信息 / 关键数据 TOP5 / 核心瓶颈 TOP5 / 优化建议 TOP5)时,使用本技能。它负责先判定模式、输入形态与芯片/能力边界,再给出正确命令、结果解读、固定报告输出与高频踩坑规避;不要把经验案例当成通用规则。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| mssanitizer-basic-usageAscend/msagent昇腾AscendC算子异常检测工具(msSanitizer)。检测内存越界、内存泄漏、数据竞争、未初始化读取、同步异常等缺陷。触发关键词:mssanitizer、sanitizer、检测工具、内存检测、竞争检测、初始化检测、同步检测 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| mstx-report-soft-syncAscend/msagent分析 AscendC 算子中自实现的软同步代码,判断其所属同步语义(核间 barrier/set-wait、卡间 barrier/signal),并接入 mssanitizer 的 Sanitizer 接口(sanitizer_report.h)上报软同步语义,避免 racecheck 对软同步误报。触发:算子存在自实现软同步(GM 地址轮询、flag 计数、跨核/跨卡信号等)需要配合 mssanitizer 检测、需要上报软同步语义、需要判断某段同步代码属于哪种同步语义时。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ops-performance-tuningAscend/msagentCompile, profile, diagnose, optimize, and compare Ascend NPU operators across CANN versions and A2/A3/A5 for Ascend C, CATLASS, Triton-Ascend, TileLang-Ascend, PyPTO, and SHMEM/MC2. Use when an operator already has a runnable implementation and the user asks for msOpProf collection, bottleneck analysis, source-level tuning, or a reproducible before/after performance report. Do not use as the primary workflow for operator creation, migration, or unresolved correctness failures. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ascend-cluster-compareAscend/msagentAscend cluster comparison tool. Invoke when user asks to compare two cluster datasets (DB or TEXT), or to generate cluster_analysis_output from raw profiling data via msprof-analyze and then compare. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ascend-cluster-fast-slow-rank-detectorAscend/msagent专门用于 Ascend 集群 Profiling 性能数据的“快慢卡”诊断专家技能。当用户提供【集群性能数据目录/路径】并要求分析【快慢卡】、【慢节点】、【负载不均衡】或【集群瓶颈】时,必须触发此技能。该技能会自动接收集群路径,调度相关工具输出快慢卡的宏观定性与微观根因(如 Host 下发瓶颈、算子计算劣化)。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ascend-communication-analysisAscend/msagentAnalyze Ascend NPU collective communication profiling data with a DB-first workflow. Use when the user provides `cluster_analysis_output/cluster_analysis.db`, rank-level `analysis.db`, rank-level `ascend_pytorch_profiler_{rank_id}.db`, together with `profiler_info.json`, and asks about HCCL or hcom communication cost, collective communication TOP ops, wait time, slow rank/straggler, Notify Wait, bandwidth, retry, relay, SDMA/RDMA/HCCS links, communication matrix, or Ascend communication fault patterns. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ascend-computation-analysisAscend/msagentAnalyze Ascend NPU computation-side profiling data for single-card runs or a selected rank from multi-card runs. Use this skill when the user asks to diagnose computation bottlenecks, AI Core / AI Vector / AICPU hotspots, dynamic shape overhead, block dim issues, redundant TransData/Transpose/Cast, cross-stream waits, frequency/runtime-state issues, or fusion opportunities. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ascend-fusion-op-replaceAscend/msagent针对昇腾 NPU 上的 PyTorch 模型,识别可做融合算子替换的代码段、替换为 torch_npu 融合算子并做性能/精度验证。当用户提到融合算子、NPU 算子替换、RMSNorm/SwiGLU/RoPE/Attention 融合、torch_npu 亲和算子等关键词是,使用本 Skill。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ascend-msprof-analyze-cliAscend/msagentMindStudio Profiler Analyze(msprof-analyze)是面向 AI 训练与推理场景的性能分析工具,基于采集得到的 profiling 数据进行统计、比对和诊断,帮助定位计算、通信、调度及集群场景下的性能瓶颈。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ascend-npu-snapshot-analyzerAscend/msagent分析 PyTorch memory snapshot pickle 文件(_dump_snapshot 导出的内存快照),提供内存峰值、碎片、泄漏、OOM 检测与交互式 HTML 报告。仅当用户明确提及 memory snapshot、内存快照、_dump_snapshot、pickle 内存文件 或需要对 snapshot pickle 做内存分析时才触发,不处理一般的 NPU 性能分析、SQLite 查询或通用内存问题。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ascend-prof-compareAscend/msagentCompares two Prof datasets (GPU vs NPU / NPU vs NPU) by auto-installing and calling msprof-analyze compare, then parses the result xlsx into HTML report and Chinese xlsx. Invoke when user provides two prof dirs to compare, or has a compare result xlsx to analyze/translate. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ascend-profiler-collect-adaptionAscend/msagentAdapt torch_npu.profiler interface for AI frameworks and training/inference code on Ascend NPU. Use this skill whenever users need to integrate profiling, add performance data collection, or instrument PyTorch code with torch_npu.profiler on Huawei Ascend NPU platforms. Triggers on: "torch_npu profiler", "NPU profiling", "Ascend profiler", "profiler adaptation", "profile training", "profile inference", "add profiler to framework", "性能采集", "profiling 数据", "昇腾 profiler", and any request to add performance monitoring to Ascend NPU code. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ascend-profiler-data-validationAscend/msagent当用户提供 MindStudio profiler 采集的性能数据(框架 profiler、msprof 命令行)时,对数据完整性、采集状态及关键配置进行校验,确保后续分析工具能正常运行。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ascend-profiler-db-explorerAscend/msagent面向 Ascend PyTorch Profiler / msprof DB(如 ascend_pytorch_profiler*.db、msprof_*.db)的 SQL 分析技能。将自然语言问题(算子耗时、通信、下发、调度、schema/table 查询)转为安全可执行 SQL,并按需从官方文档提取表结构详情。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| ascend-schedule-analysisAscend/msagentAnalyze Ascend NPU schedule, operator dispatch, operator launch, and Host Bound profiling issues in Ascend profiling data. Use when need to diagnose device Free time, framework/operator dispatch latency, launch latency, PYTORCH_API/CANN_API launch gaps, aclrtSynchronizeStream stalls, task queue behavior, CPU scheduling interference, GC/lock pauses, CPU affinity, or schedule-side optimization actions. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |