Loading…
Showing 3961–3990 of 10180 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| too-long-to-readaiskillstore/marketplace仅在用户明确说“太长不看”“先讲结论”“把这个讲得好读一点”“压成一屏重点”,或表达同等的快速阅读意图时使用。把用户提供的文本、文章链接、普通网页、金山文档、飞书文档或由宿主 Agent(智能体)解析出的文件内容,转成结论优先的短消息,同时保留会改变判断的条件、风险、数字、行动项和原文歧义。不要只因为内容很长、附有链接或文件就触发;普通总结、翻译、改写请求也不自动触发本 Skill。 | Stars: 487 | Updated | Claude CodeCodex | Verified | Install |
| example-skillaiskillstore/marketplaceThis skill should be used when demonstrating skill structure and format. Provides example patterns for creating new skills. | Stars: 487 | Updated | Claude CodeCodex | Verified | Install |
| skills-proficiency-mapperaiskillstore/marketplaceMaps learning skills to CEFR, Bloom's Taxonomy, and DigComp levels with measurable indicators, prerequisites, and non-regressive progression. | Stars: 487 | Updated | Claude CodeCodex | Verified | Install |
| promptingaiskillstore/marketplacePrompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio. | Stars: 487 | Updated | Claude CodeCodex | Verified | Install |
| api-jwt-authenticatoraiskillstore/marketplaceA conceptual skill for securing FastAPI REST APIs with JWT authentication | Stars: 487 | Updated | Claude CodeCodex | Verified | Install |
| crud-with-spec-kitaiskillstore/marketplaceA conceptual skill for implementing CRUD features driven by Spec-Kit and Claude Code | Stars: 487 | Updated | Claude CodeCodex | Verified | Install |
| next-js-better-auth-integrationaiskillstore/marketplaceA conceptual skill for integrating Better Auth with Next.js App Router | Stars: 487 | Updated | Claude CodeCodex | Verified | Install |
| spec-kit-claude-code-workflowaiskillstore/marketplaceA conceptual skill for guiding the Spec-Kit + Claude Code development workflow | Stars: 487 | Updated | Claude CodeCodex | Verified | Install |
| plugin-json-schemamikeparcewski/wicked-gardenOfficial Claude Code plugin.json schema reference and validation guide. Use when creating or troubleshooting plugin.json manifest files. Covers all fields, auto-discovery behavior, path formats, and common validation errors. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| mini-program-product-spec-skillNocodeMrLi/mini-program-engineering-skill-suiteConvert a vague mini-program idea, feature request, or partially documented product into an evidence-calibrated product specification with target users, core problem, version-one scope, main and exception flows, page responsibilities, state matrices, and testable acceptance criteria. Use when users ask to define an MVP, clarify requirements, organize product flows, specify page behavior, resolve ambiguous product states, or prepare a stable handoff before architecture or implementation. Separates facts, user decisions, assumptions, unknowns, and future ideas; never invents product logic merely to complete a screen or technical plan. | Stars: 101 | Updated | Claude CodeCodex | Verified | Install |
| ralph-specum-feedbacktzachbon/smart-ralphThis skill should be used only when the user explicitly asks to use `$ralph-specum-feedback`, or explicitly asks Ralph Specum in Codex to draft or submit feedback. | Stars: 566 | Updated | Claude CodeCodex | Verified | Install |
| ralph-specum-indextzachbon/smart-ralphThis skill should be used only when the user explicitly asks to use `$ralph-specum-index`, or explicitly asks Ralph Specum in Codex to generate or refresh index artifacts. | Stars: 566 | Updated | Claude CodeCodex | Verified | Install |
| creating-issuesopsmill/nornir-infrahubTurns a single feature idea, improvement, or bug into ONE well-structured GitHub issue. TRIGGER when: the user wants to file/open/create an issue, turn a feature idea or improvement into a ticket, or capture something missing or broken as a ticket. DO NOT TRIGGER when: breaking work into multiple issues or planning a body of work → a planning skill; writing a full Product Requirements Document → creating-prd; the idea is still fuzzy and unhardened → grilling-ideas first. | Stars: 12 | Updated | Claude CodeCodex | Verified | Install |
| jaz-kitteamtinvio/jaz-aiUse this skill when an accountant, bookkeeper, or owner is running real books in Jaz across one or more organizations from the terminal: setting up a workspace, switching between clients, running a month/quarter/year close that survives across sessions, or clearing a queue of drafts for review. Triggers on "open <org>", "close the books for June", "what needs my review", "what's due", "add another organization". | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| consolidatePyModel/pythinker-codeApply an approved sub-skill grouping by moving user-specified skills into a parent bundle, with timestamped backups of every modified directory. | Stars: 29 | Updated | Claude CodeCodex | Verified | Install |
| reviewPyModel/pythinker-codeAnalyze the available skill set and recommend candidate groups that could be consolidated into sub-skill bundles. Read-only — proposes a plan, does not move files. | Stars: 29 | Updated | Claude CodeCodex | Verified | Install |
| gemini-agentsphuryn/product-engineering'Ask Gemini', 'have Gemini build or review this': Google's Antigravity CLI as a partner. It may break Google's terms on a consumer plan, so the user agrees first. | Stars: 646 | Updated | Claude CodeCodex | Unverified | Install |
| nan-overflow-detectionkali20gakki/msAgent多卡分布式训练中的 loss/gnorm 精度溢出检测与根因追溯。基于 MSProbe dump 数据,先跨 rank 定位首次出现 NaN 的源卡,再在源卡上追溯具体的溢出根因算子。 当用户需要:(1) 多卡分布式训练场景下的 NaN/Inf 溢出检测 (2) 找出首先出现 NaN 的源卡 (3) 追溯根因计算算子 (4) loss/gnorm NaN 问题定位 时使用此 skill。 | Stars: 32 | Updated | Claude CodeCodex | Verified | Install |
| rl-consistency-dump-analysiskali20gakki/msAgent通用训推一致性(prefill)的 dump 数据分析 skill。分析**已采集**的训推两侧 dump:探查 dump 结构 → 语义边界映射(不要求算子同名)→ 逐边界精确门禁比对 → 定位首差异 → ULP 量化区分舍入/逻辑级 → 追放大链 → 差异点隔离验证(打桩迭代:输出打桩指令给采集侧,等它用 msprobe `load` 覆盖边界再采后比下游,枚举所有独立差异点)→ 排除根因假设 → 输出整体结论 → 产出分析报告。与具体框架/硬件解耦,适用 msprobe PrecisionDebugger 或等价工具采的任何 dump。触发词:训推一致性分析、dump 数据分析、dump 已采好帮我分析、首差异定位、所有差异点、差异点隔离、打桩指令、对齐报告、训推不一致结论、比较两侧 tensor。采集与打桩再采由 rl-prefill-consistency-dump 负责,本 skill 只消费已落盘 dump、输出打桩指令驱动再采。 | Stars: 32 | Updated | Claude CodeCodex | Verified | Install |
| rl-prefill-consistency-dumpkali20gakki/msAgent训推一致性(prefill)采集侧:为训练/推理两侧采集可比的 prefill dump(输入对齐 PROMPTS_ONLY → 参数对齐校验(dump 前前置:校验两侧 config 超参/结构/权重,不一致输出参数不一致点并对齐)→ msprobe 接入采集 → 采集验证 → 恢复代码)。按用户需求判断用法:① 仅采集 dump——用户只要 dump 数据,走采集主流程(0→7→9),直接产出两侧可比 dump;② 配合分析——用户要求找所有独立差异点/差异点隔离验证/配合 rl-consistency-dump-analysis 分析时,才按分析侧打桩指令用 msprobe `load` 覆盖边界二次采集(阶段 8)再恢复代码。差异分析、首差异定位、打桩指令、整体结论由 rl-consistency-dump-analysis 承担。触发词:训推一致、训推一致性、prefill 比对、msprobe dump/采集、精度比对数据采集、打桩二次采集、参数对齐校验、参数不一致点、mHC 配置不一致、权重不同步、清卡验环境后采数据;已采 dump 的分析转 rl-consistency-dump-analysis。 | Stars: 32 | Updated | Claude CodeCodex | Verified | Install |
| train-infer-op-diff-scannerkali20gakki/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: 32 | Updated | Claude CodeCodex | Verified | Install |
| aisbench-dataset-compression-herdingkali20gakki/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: 32 | Updated | Claude CodeCodex | Verified | Install |
| ascend-computation-analysiskali20gakki/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: 32 | Updated | Claude CodeCodex | Verified | Install |
| ascend-fusion-op-replacekali20gakki/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: 32 | Updated | Claude CodeCodex | Verified | Install |
| ascend-profiler-collect-adaptionkali20gakki/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: 32 | Updated | Claude CodeCodex | Verified | Install |
| quant-tuning-infer-ditkali20gakki/msAgent在 W8A8 动态量化后,用 MindIE-SD 冒烟测试 DiT 量化权重是否可加载(可选 skill)。与 `quant-tuning-evaluate`(DiT 扩展节)的区别:本 skill 仅做"能跑通 + 权重可用"的轻量验证(4~16 条 prompt,几分钟出结果),不算分;后者产出视频集交 `quant-tuning-score-dit`(AISBench-VBench 16 维度)评分,是调优回路一环。不引入 vLLM-Ascend、不做精度指标评估(FID/CLIP-score 等)。 | Stars: 32 | Updated | Claude CodeCodex | Verified | Install |
| quantization-expert-experience-tuning-ruleskali20gakki/msAgent量化专家经验调优库:按「L1 通用专家调优意见 → L2 结构化专家调优意见 → L3 模型专属专家调优意见」三级递进, 输出量化精度调优的完整手段(离群值抑制 / 量化方法·粒度·对称性选型 / 校准集调整 / 敏感层回退 / 模型专属策略), 每条结论附专家原因分析与专家意见可信度等级。 本 Skill 是专家经验库,负责说明可选离群值抑制算法并询问用户选择哪些算法,以及回答「怎么调、哪些层需要回退及为什么」;不运行离群值抑制 processor,不修改 YAML、不执行量化、不做 EP 检查 / 服务化 / 任务评测。 | Stars: 32 | Updated | Claude CodeCodex | Verified | Install |
| smart-ralphtzachbon/smart-ralphThis skill should be used when the user asks about "ralph arguments", "quick mode", "commit spec", "max iterations", "ralph state file", "prototype overlay", "execution modes", "ralph loop", "coordinator behavior", "delegate to subagent", or needs guidance on Ralph plugin arguments, state management, delegation patterns, or execution loop behavior. Core behavioral skill for all Ralph Specum operations. | Stars: 566 | Updated | Claude CodeCodex | Verified | Install |
| metarossoctl/rossoctlSkills for improving and maintaining skills | Stars: 305 | Updated | Claude CodeCodex | Verified | Install |
| herdr-operationsespennilsen/piUse when inspecting or operating Herdr sessions, workspaces, tabs, panes, agents, terminal output, agent messaging, or waits. | Stars: 122 | Updated | Claude CodeCodex | Verified | Install |