Role
Best agent skills for developers, page 780
Skills for developers, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 37393 | Ankh 蛋白质语言模型昇腾 NPU 迁移 Skill,适用于 Ankh base/large、Ankh3 large/XL 以及同类基于 HuggingFace Transformers 与 PyTorch 的蛋白模型从 CUDA/GPU 到华为 Ascend NPU 的环境检查、代码适配、权重加载、验证脚本补齐与文档沉淀。 | ascend-ai-coding/ | 174 | — | ~2.1k | Automated safety check: Pass | No licence | yesterday |
| 37394 | 昇腾 TensorFlow Community 迁移适配 Skill,适用于将基于 TensorFlow 2.x 的模型原生部署到华为 Ascend NPU,而不经过 TF 到 PyTorch 转换,覆盖 aarch64 源码编译 TF 2.6.5、tfplugin 安装、自动迁移工具使用、手动适配与精度验证。 | ascend-ai-coding/ | 174 | — | ~2.1k | Automated safety check: Pass | No licence | yesterday |
| 37395 | 37395.AI For Science Boltzgen BoltzGen 昇腾 NPU 迁移与复现 Skill,适用于在华为 Ascend NPU 上部署 BoltzGen 生成式蛋白设计与逆折叠流程,覆盖环境准备、权重缓存、cuEquivariance 兼容、源码适配和端到端推理验证。 | ascend-ai-coding/ | 174 | — | ~3.8k | Automated safety check: Pass | No licence | yesterday |
| 37396 | 37396.AI For Science Deepfri DeepFRI 的 TensorFlow 到 PyTorch 转换与昇腾 NPU 迁移 Skill,适用于蛋白质功能预测场景下的 TF 模型分析、PyTorch 重写、权重逐层映射、NPU 推理与精度验证,尤其适合需要在 Ascend 上运行 DeepFRI CNN 或 GCN 路径时使用。 | ascend-ai-coding/ | 174 | — | ~2.4k | Automated safety check: Pass | No licence | yesterday |
| 37397 | DeepFRI TensorFlow 原生昇腾 NPU 迁移 Skill,适用于不做 TF 到 PyTorch 转换、而是直接使用 TensorFlow 2.6.5 与 npudevice 在华为 Ascend 上运行 DeepFRI 的场景,覆盖源码编译、tfplugin 安装、代码适配、推理与 CPU 对比验证。 | ascend-ai-coding/ | 174 | — | ~2.1k | Automated safety check: Pass | No licence | yesterday |
| 37398 | 37398.AI For Science Diffsbdd DiffSBDD 昇腾 NPU 迁移 Skill,适用于将基于等变扩散模型的结构化药物设计项目从 CUDA 迁移到华为 Ascend NPU,覆盖环境搭建、依赖安装、torchscatter 源码编译、代码适配以及 de novo 推理验证。 | ascend-ai-coding/ | 174 | — | ~898 | Automated safety check: Pass | No licence | yesterday |
| 37399 | 37399.AI For Science Generator GENERator DNA 序列生成模型的昇腾 NPU 迁移 Skill,适用于将基于 HuggingFace Transformers 的 Causal LM 从 CUDA 迁移到华为 Ascend NPU,覆盖环境搭建、依赖安装、代码适配、多进程处理和 sequence recovery 验证。 | ascend-ai-coding/ | 174 | — | ~827 | Automated safety check: Pass | No licence | yesterday |
| 37400 | OligoFormer 昇腾 NPU 迁移 Skill,适用于将基于 PyTorch Transformer 的 siRNA 效能预测模型迁移到华为 Ascend NPU,覆盖环境搭建、RNA-FM 依赖安装、代码适配、推理验证与可选训练流程。 | ascend-ai-coding/ | 174 | — | ~1.3k | Automated safety check: Pass | No licence | yesterday |
| 37401 | ProteinBERT 昇腾 NPU 部署与迁移 Skill,适用于将 TensorFlow 或 Keras 版 ProteinBERT 转成基于 PyTorch 与 torchnpu 的实现,覆盖权重转换、embedding 提取、微调训练、注意力可视化和 GPU 与 NPU 精度验证。 | ascend-ai-coding/ | 174 | — | ~1.9k | Automated safety check: Pass | No licence | yesterday |
| 37402 | TensorFlow 或 Keras 模型改写到 PyTorch 的通用 Skill,适用于在华为 Ascend NPU 或其他依赖 PyTorch 生态的平台上完成层级映射、权重转换、逐层数值验证和端到端精度对比,尤其适合 ProteinBERT、DeepFRI 这类科学模型的跨框架迁移。 | ascend-ai-coding/ | 174 | — | ~3.4k | Automated safety check: Pass | No licence | yesterday |
| 37403 | HuggingFace Diffusers 环境配置指南,用于华为昇腾 NPU。覆盖 CANN 版本检测、PyTorch + torchnpu 安装、Diffusers 库安装及环境验证。当用户需要在昇腾 NPU 上配置 Diffusers 环境时使用。 | ascend-ai-coding/ | 174 | — | ~566 | Automated safety check: Pass | No licence | yesterday |
| 37404 | 从用户 PyTorch/Python 代码中提取算子实现,构建为算子任务格式的标准化 任务文件。支持两种模式:单 case(单一自包含 .py,getinputs 返回单组)和 多 case(.py + 同名 .json 配对,getinputgroups 返回多组)。 | ascend-ai-coding/ | 174 | — | ~1.4k | Automated safety check: Pass | No licence | yesterday |
| 37405 | 能完成昇腾NPU驱动和固件安装部署,实现安装包正则匹配提取、按需添加可执行权限、Python+Shell双重包校验、系统依赖先验后装、适配CentOS/RHEL/Ubuntu/Debian系统,适用于昇腾NPU驱动和固件安装部署。 | ascend-ai-coding/ | 174 | — | ~663 | Automated safety check: Notes | No licence | yesterday |
| 37406 | 根据设计文档生成 AscendC 算子完整代码实现并完成框架适配。TRIGGER when: 设计文档已完成,需要生成 ophost/opkernel 代码、注册到 PyTorch 框架、编译测试。关键词:代码生成、ophost、opkernel、tiling、kernel、框架适配、算子注册。 | ascend-ai-coding/ | 174 | — | ~2k | Automated safety check: Pass | No licence | yesterday |
| 37407 | Ascend C 算子 mssanitizer 内存检测分析技能。用于检测和分析算子内存问题:非法内存访问、非法释放、内存泄漏、UB地址越界,生成问题报告。自动识别算子工程类型(ops算子仓用GE IR模式,自定义算子用Python模式)。触发关键词:mssanitizer、内存检测、内存泄漏、非法访问、illegal free、内存错误。 | ascend-ai-coding/ | 174 | — | ~3.4k | Automated safety check: Pass | No licence | yesterday |
| 37408 | 昇腾 NPU 平台 vLLM 大模型推理服务一键部署。触发:用户说'部署 模型名'、'NPU 部署模型'、'vllm serve'。流程:SSH检查 → NPU检查 → 配置发现(必须验证) → 用户确认 → 部署 → cron监控 → 验证。约束:(1) 配置必须从官方文档验证,禁止猜测;(2) 后台启动必须用cron监控,禁止手动轮询。支持… | ascend-ai-coding/ | 174 | — | ~1.2k | Automated safety check: Pass | No licence | yesterday |
| 37409 | 面向 Ascend PyTorch Profiler / msprof DB(如 ascendpytorchprofiler.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。 | ascend-ai-coding/ | 174 | — | ~1.4k | Automated safety check: Pass | No licence | yesterday |
| 37410 | 用于审查 GitCode PR,并结合 PR metadata、diff 与整个代码仓上下文生成深度审查结论或发布逐行评论。当用户希望 review GitCode PR、检查某个 GitCode PR 链接、分析变更风险、或将审查意见发布到 GitCode PR 时使用。典型触发方式包括“review this PR”“检视这个 PR”“检查 PR”,或直接提供 GitCode PR… | ascend-ai-coding/ | 174 | — | ~1.7k | Automated safety check: Pass | MIT | yesterday |
| 37411 | 37411.GitHub Issue Rca GitHub Issue root cause analysis skill. An agent skill from ascend-ai-coding/awesome-ascend-skills. | ascend-ai-coding/ | 174 | — | ~4.2k | Automated safety check: Pass | No licence | yesterday |
| 37412 | 模型层 Tensor 打点与精度对比工具。用于在模型 forward 过程中捕获模型各层中间 tensor,实现 GPU/NPU 精度对比调试。支持 vLLM、SGLang 推理框架。When to use: When you need to debug precision issues between GPU and NPU,or validate layer-wise tensor… | ascend-ai-coding/ | 174 | — | ~2.4k | Automated safety check: Pass | No licence | yesterday |
| 37413 | 37413.Mindspeed Mm Env Setup MindSpeed-MM multimodal model suite environment setup guide for Huawei Ascend NPU. | ascend-ai-coding/ | 174 | — | ~3.1k | Automated safety check: Pass | No licence | yesterday |
| 37414 | 37414.Mindspeed Mm Vlm Universal VLM (vision-language understanding model) training guide for Huawei Ascend NPU using MindSpeed-MM. | ascend-ai-coding/ | 174 | — | ~5.2k | Automated safety check: Pass | No licence | yesterday |
| 37415 | 37415.Npu Docker Launcher Directly launch Docker containers on Ascend NPU servers for users. | ascend-ai-coding/ | 174 | — | ~2.4k | Automated safety check: Notes | No licence | yesterday |
| 37416 | 37416.Tech Docs Guard 评估 CANN 算子仓的「进阶教程 / 开发指南」类文档质量——通读文档 + 对照算子代码静态查证(默认不跑),按五轴(找得到/信得过/学得会/可操作/读得懂)找出 漏讲/讲不清/过时/对不上代码/概念讲错,产出带证据与改进建议的体检报告(MD + HTML)。涉及「评进阶教程 / 开发指南文档质量 / 文档对不对得上代码 / 教程审稿 / tutorial 体检 /… | ascend-ai-coding/ | 174 | — | ~2.7k | Automated safety check: Pass | No licence | yesterday |
| 37417 | 37417.Verl Quickstart Generates an executable, end-to-end VERL reinforcement learning quickstart runbook for Ascend/NPU (docker image, dataset preprocessing, model setup, mainppo training, and examples/run.sh flow). | ascend-ai-coding/ | 174 | — | ~592 | Automated safety check: Pass | No licence | yesterday |
| 37418 | 37418.Vllm Ascend Server Deploy vLLM inference services on Ascend NPU servers with automatic model detection and optimized configuration. | ascend-ai-coding/ | 174 | — | ~2.7k | Automated safety check: Pass | No licence | yesterday |
| 37419 | Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. | nicknisi/ | 114 | — | ~3.4k | Automated safety check: Pass | MIT | 2 mo ago |
| 37420 | 37420.Delegate Run parallel or isolated subagents for independent subtasks (research, parallel analysis, one-shot transforms) to avoid bloating the main context. | av/ | 102 | — | ~599 | Automated safety check: Pass | No licence | 15 days ago |
| 37421 | 37421.Explore Answer "how does X work", "where is X defined", or "trace through Y" questions about a codebase using parallel subagent searches with cited summaries. | av/ | 102 | — | ~958 | Automated safety check: Pass | No licence | 15 days ago |
| 37422 | 37422.TDD Add new behavior test-first (write failing test → make it pass → refactor). | av/ | 102 | — | ~972 | Automated safety check: Pass | No licence | 15 days ago |
| 37423 | A skill your agent uses when reducing context cost in an agent skill by deciding what belongs in metadata, SKILL.md body, references, scripts, assets, or validation files; trigger when SKILL.md is… | BingHanOfUESTC/ | 106 | — | ~366 | Automated safety check: Pass | MIT | 3 mo ago |
| 37424 | 37424.Revision Workflow Versioned fiction revision workflow. An agent skill from BingHanOfUESTC/open_agent_team. | BingHanOfUESTC/ | 106 | — | ~264 | Automated safety check: Pass | MIT | 3 mo ago |
| 37425 | A skill your agent uses when designing the structure of a new agent skill, choosing skill name, folder layout, freedom level, references/scripts/assets split, dependencies, validation plan, and… | BingHanOfUESTC/ | 106 | — | ~317 | Automated safety check: Pass | MIT | 3 mo ago |
| 37426 | 37426.Skill Authoring Workflow A skill your agent uses when writing or updating SKILL.md for an agent skill, including model-facing frontmatter description, concise body instructions, workflow steps, resource navigation, gotchas… | BingHanOfUESTC/ | 106 | — | ~301 | Automated safety check: Pass | MIT | 3 mo ago |
| 37427 | A skill your agent uses when reviewing or maintaining an agent skill after creation, especially to add gotchas from failures, check over-triggering or under-triggering, assess action-at-a-distance… | BingHanOfUESTC/ | 106 | — | ~294 | Automated safety check: Pass | MIT | 3 mo ago |
| 37428 | A skill your agent uses when creating a new agent skill from a user problem, repeated workflow, expected output, examples, or failure cases; extract trigger conditions, reusable capability, inputs… | BingHanOfUESTC/ | 106 | — | ~339 | Automated safety check: Pass | MIT | 3 mo ago |
| 37429 | 37429.Playwright E2E Comprehensive end-to-end testing skill using Playwright for web applications, covering page objects, selectors, assertions, waits, fixtures, and test organization. | PramodDutta/ | 235 | — | ~3.7k | Automated safety check: Pass | MIT | 7 days ago |
| 37430 | A robust methodology for LLM-based requirements gathering and high-fidelity artifact generation. | GoogleCloudPlatform/ | 107 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 37431 | 37431.Cometchat Entry point for any CometChat task on any platform. An agent skill from cometchat/cometchat-skills. | cometchat/ | 132 | — | ~2.9k | Automated safety check: Pass | MIT | 6 days ago |
| 37432 | 37432.Cometchat Analytics See what your chat is doing — pull usage & message metrics via REST, stream real-time events to your data/observability stack via webhooks, monitor client-side errors & the init/login path, and read… | cometchat/ | 132 | — | ~1.5k | Automated safety check: Pass | MIT | 6 days ago |
| 37433 | Add or enable a specific CometChat feature in an Android v6 app — receipts, typing, reactions, mentions, threads, search, polls, stickers, translation, link previews, AI smart replies / conversation… | cometchat/ | 132 | — | ~2.4k | Automated safety check: Pass | MIT | 6 days ago |
| 37434 | Diagnose a broken CometChat Android v6 integration — dependency and version conflicts, init/login failures, blank or stuck screens, empty lists, missing realtime updates, keyboard/inset layout bugs… | cometchat/ | 132 | — | ~2.7k | Automated safety check: Pass | MIT | 6 days ago |
| 37435 | Web push notifications for a CometChat Angular app — the Notifications product, FCM registration, the service worker, and token lifecycle. | cometchat/ | 132 | — | ~1.1k | Automated safety check: Pass | MIT | 6 days ago |
| 37436 | Project wiring for the Flutter v6 UI Kit — navigation (Navigator / gorouter / autoroute), state management (bloc / riverpod / provider / getx), config & secrets, platform setup, and web/desktop… | cometchat/ | 132 | — | ~1.4k | Automated safety check: Pass | MIT | 6 days ago |
| 37437 | Diagnose a broken CometChat Flutter integration — blank screens, unbounded-height crashes, lists that don't fill, login and Region failures, calls that never ring, push that never arrives, and v5… | cometchat/ | 132 | — | ~1.6k | Automated safety check: Pass | MIT | 6 days ago |
| 37438 | 37438.Cometchat iOS Push Add push notifications to an iOS CometChat app — APNs registration, token handoff, tap-to-open, badge counts and VoIP call pushes. | cometchat/ | 132 | — | ~1k | Automated safety check: Pass | MIT | 6 days ago |
| 37439 | Diagnose a broken CometChat iOS (Swift) integration — a screen that never populates, credentials read as the literal $(...), login that silently fails, empty lists, no messages, or a version/SDK… | cometchat/ | 132 | — | ~1.2k | Automated safety check: Pass | MIT | 6 days ago |
| 37440 | Diagnose a broken CometChat React v7 integration — blank panes, a collapsed/0-height surface, empty lists, no messages, the kit's error state, events that never fire, or a versionconflict. | cometchat/ | 132 | — | ~1.4k | Automated safety check: Pass | MIT | 6 days ago |
Explore related skills
Categories for developers
Popular topics
- MCP servers2,044
- Pull requests1,954
- Deployment1,269
- Debugging1,175
- Changelog and release notes1,169
- Refactoring1,142
- Code review1,046
- Subagents1,016
- Technical documentation1,009
- CI/CD974
- Backend development935
- Unit testing875
- Linting and formatting858
- Git workflow817
- Diagrams811
- End-to-end testing791
- REST APIs786
- Project scaffolding746
- Agent instruction files743
- Containers734
- Webhooks688
- Browser testing673
- Authentication647
- Observability631
Products these skills work with
Other roles
- Frontend Developers7,075
- DevOps and SRE Engineers6,607
- Data Scientists5,833
- Designers4,873
- Marketers5,420
- SEO Specialists1,401
- Writers and Editors5,851
- Product Managers2,029
- Founders and Solopreneurs6,359
- Researchers6,553
- Students and Educators1,988
- Lawyers and Compliance Teams1,330
- Accountants and Finance Teams2,470