Every Hermes skill, in one place

185 official skills from the Hermes Agent repository plus 101,376 community entries. Community index checked 2026-11-20 (UTC). Read community skills at their original sources.

Open baoyu-article-illustrator in the official library

Community index generated 2026-11-20 (UTC), checked 2026-11-20 (UTC).

Skill results

52 official + 12,194 community matches. Page 326 of 511.

Official skills first, then community.

Best match / quality.

当需要测试 iOS/Android 原生 App、H5 页面或小程序的移动端专项场景时使用此技能。移动端的坑主要不在功能逻辑上; ; 中断(电话/通知/低电量)、弱网/断网/网络切换、前后台切换、系统权限管理、多机型适配和各种系统版本兼容才是重灾区。不要只测功能流程,移动端的 Bug 有一半以上是中断和兼容性相关的。输出按中断/网络/权限/兼容/性能分类的测试要点清单。 触发场景:移动测试、App测试、Android测试、iOS测试、手机上测、H5测试、小程序测试、移动端中断

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/qa-mobile-testing
Coding & developer toolsSource (opens in a new tab)

AI在生成测试用例时存在六大系统性盲区:时序依赖、并发冲突、资源竞争、状态累积、数据一致性、第三方集成差异。评审完AI生成的用例之后,必须用此技能做盲区补盲; ; 因为AI几乎一定会漏掉这些。如果你心里觉得"好像还差点什么但说不上来",这就是答案。每个盲区维度至少补2-3个场景,总补盲数12-18个。 触发场景:还有什么没测到、AI漏了什么、补盲、全面覆盖、是不是不够、哪还没测、盲区分析、遗漏场景、时。 Use when the user asks about: compen

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/qa-ai-blindspot-compensation
Coding & developer toolsSource (opens in a new tab)

当一个迭代结束、一个项目完成、或者发生线上事故需要事后分析时使用此技能。通过系统性的回顾会议和数据复盘,把个人和团队的经验教训转化为可复用的组织资产。不要沦为"说说好话走个形式"; ; 有效的复盘需要有数据支撑(缺陷趋势/漏测分析/效率数据)、有根因分析(为什么出问题)和有 action items(下次怎么做不一样)。输出复盘报告和改进项追踪表。 触发场景:测试复盘、迭代复盘、项目复盘、经验沉淀、漏测分析、回顾总结、事后分析、反复出现同类问题需要根因改进时。 Use whe

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/qa-retrospective
Coding & developer toolsSource (opens in a new tab)

将模糊的需求描述系统化拆分为输入、操作、状态、输出、规则五个可测试维度,同时挖掘显性需求之外的那些"没写出来但必须满足"的隐性需求和衍生需求。当用户的需求描述只有一两句话、或者看起来功能很简单但你可能遗漏了什么的时候,一定要用此技能做深度解构。适用于任何测试任务的第二步骤; ; 无论需求文档有多详细,解构之后总能发现盲区。每条需求带唯一 ID(REQ-{模块缩写}-{序号})。 触发场景:分析这个需求、需求解构、挖掘隐含需求、需求挖掘、需求分析、拆解需求、业务规则提取、需求模

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/qa-req-deconstruction
Coding & developer toolsSource (opens in a new tab)

当需要告诉开发"这个 Bug 必须修"、跟产品经理沟通需求变更的影响、或者向管理层汇报质量风险时使用此技能。不同角色关注的事情不同; ; 开发要的是复现步骤和定位信息,产品要的是影响范围和优先级建议,管理层要的是风险判断和决策依据。此技能提供针对开发/产品/管理层的沟通模板和策略。产出根据不同角色定制的沟通话术和汇报材料模板。 触发场景:怎么沟通、跟开发说、跟PM说、跟领导说、沟通策略、向上汇报、干系人沟通、推动问题解决需要有效沟通时。 Use when the user a

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/qa-stakeholder-communication
Coding & developer toolsSource (opens in a new tab)

根据不同的测试目标和上下文,选择最佳的提示词模式来驱动AI生成高质量的测试用例。当AI输出的测试用例质量不够好、太泛泛、或者深度不够时,问题往往不在AI而在提示词。此技能提供结构化提示词模板,注入前面步骤产出的分析结果,输出包含角色定义、输出格式规范和约束条件的优化提示词。⚠️ 作为工作流的必过步骤,不得跳过。 触发场景:怎么问AI、AI回答不好、换个方式问、提示词、提问模板、提示词优化、角色扮演、AI输出太浅需要更深时。 Use when the user asks abo

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/qa-ai-prompt-strategy
Coding & developer toolsSource (opens in a new tab)

当管理层问"质量到底怎么样"、需要量化质量数据来做决策、或者想建立质量看板来跟踪趋势时使用此技能。从过程质量(需求评审通过率/用例覆盖度)、结果质量(Bug 密度/线上事故数)、效率(测试周期/回归耗时)和健康度(自动化通过率/环境稳定性)四个维度设计度量指标。⚠️ 度量的目的不是打分,是发现问题趋势; ; 如果只报喜不报忧,度量就没用了。 触发场景:质量度量、质量指标、怎么量化质量、质量看板、质量数据、趋势分析、向管理层展示质量数据时。 Use when the user

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/qa-quality-metrics
Coding & developer tools · Everyday life & funSource (opens in a new tab)

Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format. Do NOT use for: bug fixes, test fixes, dependency bumps, refactoring, CI/CD changes, performance tuning, or any task that does not involve writing or

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/nemo-rl-docs
Coding & developer tools · Work & businessSource (opens in a new tab)

将前面所有分析步骤(需求解构、场景树、边界清单、风险评估等)打包成一个结构化的AI上下文包,确保AI在生成测试用例时拥有完整的业务上下文、功能上下文和技术上下文。当已经完成了需求分析、场景构建和深度设计,即将进入提示词生成阶段时,必须经过此步骤。上下文包的完整度直接决定了AI生成用例的质量; ; 输入垃圾,输出也是垃圾。当上游分析缺失时,本技能会读取用户上传的需求文件或fetch用户提供的URL以补充上下文,并对原始描述做结构化解析后并入上下文包,但不会替代上游分析步骤; ;

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/qa-ai-context-engineering
Coding & developer tools · AI models & providersSource (opens in a new tab)

WE PUT YOUR AD LINE WHERE THE AI SPINNER SITS. Verified wait-state ads. Start earn money now while waiting your agents! One short sponsored line appears while developers wait on AI coding tools. Advertisers buy visible impressions. Develope

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/waitspin
Coding & developer tools · Automation & multi-agentSource (opens in a new tab)

当项目还在需求阶段或者开发正在写代码时使用此技能; ; 这时候介入能花最小的成本避免最多的缺陷。从需求可测试性评审(需求模糊/矛盾/不可测)、开发阶段测试设计(单元测试/接口契约/测试桩)和技术方案评审(影响面分析/风险识别)三个维度提前发现缺陷。越早发现 Bug 修复成本越低; ; 需求阶段的 Bug 修复成本是线上阶段的 1/100。输出左移检查清单和阶段性介入记录。 触发场景:测试左移、左移、提前测试、需求可测试性(左移阶段)、需求评审(左移介入)、开发阶段测、项目早期

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/qa-shift-left
Coding & developer tools · Images, video, music & 3DSource (opens in a new tab)

当开发提了 PR、代码变更需要确定测试范围、或者想通过分析代码来预测可能出 Bug 的区域时使用此技能。从测试视角分析代码变更的影响范围、识别高危模式和典型风险区域。不要看完整代码逻辑; ; 你只需要关注变更类型(新增/修改/删除/重构)、影响范围(接口定义/数据库字段/业务逻辑)和相关依赖,据此确定最小回归测试范围。输出代码变更影响分析报告。 触发场景:代码评审、CR、测试视角、看代码、代码变更、Diff、代码变更后需要确定测试范围时。 Use when the user

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/qa-code-review-for-test
Coding & developer toolsSource (opens in a new tab)

对AI生成的测试用例进行八维评审(完整性、正确性、可执行性、风险覆盖、规范性、一致性、追溯性、冗余度),是AI生成用例后的第一个质量门禁。当AI刚刚生成了一大批测试用例、你需要确保这些用例真的有价值而不是"看起来不错"时,应当使用此技能。不要假设AI输出的都是对的; ; AI经常生成语义正确但实际操作不了的用例。每个维度评分低于7分的必须标注问题并使用MISSING/WRONG/VAGUE等规范格式标记。无上游场景树/风险清单时降级为六维评审(跳过追溯性、简化完整性)。 触发

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/qa-ai-output-critique
Coding & developer tools · Cost, speed & monitoringSource (opens in a new tab)

Start or patch Dynamo router modes and run router endpoint smoke checks. Use for round-robin, KV-aware, least-loaded, or device-aware routing setup; use recipe-runner for recipe deployment and troubleshoot for failure diagnosis.

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/dynamo-router-starter
Coding & developer toolsSource (opens in a new tab)

当 AI 生成的测试用例已经过输出评审和盲区补盲、准备终审上线时使用此技能。由资深测试对 AI 输出的用例做人工抽样校验,从业务有效性、场景完整性、可执行性三个维度做最后把关。⚠️ 如果发现系统性问题(比如遗漏了某个关键模块),需要回退修正并记录到 Prompt 优化反馈库。专家评审不是走形式; ; 发现的问题必须闭环。 触发场景:专家评审、用例审查、校正反馈、评审用例、检查用例、终审、用例上线前需要终审时。 Use when the user asks about: fin

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/qa-expert-review
Coding & developer toolsSource (opens in a new tab)

当测试新人不知道执行时应该关注什么、或者有经验的测试发现"执行完了但好像什么都没发现"时使用此技能。测试执行不是"按步骤操作看结果"; ; 你需要同时关注功能表现、接口响应、日志报错、UI 渲染、数据一致性、性能指标六路信号。大多数的 Bug 是被"不小心看到"的而非被测出来的。每轮执行后输出观察记录,在 9 列设计用例上回填「实际结果」与「结论」完成执行闭环,标注异常信号与待跟进问题。⚠️ 本技能示例可能调用外部监控/截图工具,请在受控环境执行。 触发场景:执行观察、观察日

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/qa-execution-observation
Coding & developer toolsSource (opens in a new tab)

Diagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use recipe-runner/router-starter before this for normal bring-up.

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/dynamo-troubleshoot
Coding & developer tools · AI models & providersSource (opens in a new tab)

Find Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference code, downloading data, or installation.

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/earth2studio-discover
Coding & developer tools · AI models & providersSource (opens in a new tab)

Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments.

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/dynamo-recipe-runner
Coding & developer tools · AI models & providersSource (opens in a new tab)

Call the Kimi API (kimi-k3, kimi-k2.7-code, kimi-k2.6, kimi-k2.5) through RunAPI using OpenAI-compatible Chat Completions. Use for Kimi text chat, streaming, or an existing compatibility client that needs the conditional reference.

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/runapi-kimi
Coding & developer tools · Chat apps & voiceSource (opens in a new tab)

Guide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment. Do NOT use for writing inference code, choosing models, or PhysicsNeMo questions.

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install clawhub/earth2studio-install
Coding & developer tools · AI models & providersSource (opens in a new tab)

Entries with unclear source links are withheld. Some restricted-license records have source links only. Full skill instructions stay at the original source.