AGENT SKILLS · EQUIPO DE MISIÓN
Agent Skills útiles ordenados por uso real
Compara Skills verificados por función, contenido del paquete, instalaciones y fiabilidad de la fuente antes de añadirlos.
- ALCANCE DEL CATÁLOGO
- VERIFICADO
- Skills
- 22.121
- repositorios
- 3377
- última sincronización
- 25 oct 2026
thedivergentaigodot-project-templates
Navigation skill for genre project scaffolds: pick platformer/RPG/FPS (or other genre) then load matching template scripts and route gameplay fill to godot-genre- skills. Use when bootstrapping architecture, bootstrap order, pause modes, PCK DLC, or feature tags — not for pasting FPS/inventory recipes. Keywords: project templates, bootstrap, Subsystem Locator, PCK, feature tags, PROCESSMODEALWAYS, genre scaffold.
- instalaciones
- 1
- GitHub Stars
- 876
- Actualizado
- 16 oct
spencerpaulybuilding-skills-from-patterns
When the same multi-step workflow repeats in Cursor (user corrections or agent redos), capture it as a new SKILL.md under .cursor/skills/ so future sessions load it automatically.
- instalaciones
- 1
- GitHub Stars
- 860
- Actualizado
- 2 ago
spencerpaulyparallel-ci-triage
When GitHub Actions fails, fetch failing job logs and assign each failing job to a separate subagent that fixes its slice of the problem in parallel. Use for multi-job CI failures where jobs are independent.
- instalaciones
- 1
- GitHub Stars
- 860
- Actualizado
- 2 ago
spencerpaulyparallel-code-review
Run four parallel read-only subagents that each review the same diff from a different lens — security, performance, correctness, and readability — then merge findings into one report. Use before merging large or risky PRs.
- instalaciones
- 1
- GitHub Stars
- 860
- Actualizado
- 2 ago
spencerpaulyrecording-browser-flow-as-test
Execute a user flow step-by-step in Cursor's built-in browser while documenting each action, then emit a Playwright test that replays the same flow using stable selectors derived from the accessibility tree.
- instalaciones
- 1
- GitHub Stars
- 860
- Actualizado
- 2 ago
spencerpaulyresponsive-testing
Open the app in Cursor's browser at multiple viewport sizes, screenshot each, and report any layout breakage.
- instalaciones
- 1
- GitHub Stars
- 860
- Actualizado
- 2 ago
spencerpaulyverifying-in-browser
After making code changes, start the dev server, open the app in Cursor's built-in browser, and verify everything works — check rendering, console errors, and network health. Use proactively after any UI or API change.
- instalaciones
- 1
- GitHub Stars
- 860
- Actualizado
- 2 ago
cloudwegoeino-agent
Eino ADK agent construction, middleware, and runner. Use when a user needs to build an AI Agent, configure ChatModelAgent with ReAct pattern, use middleware (filesystem, tool search, tool reduction, summarization, plan-task, skill, agents.md), set up the Runner for event-driven execution, implement human-in-the-loop with interrupt/resume, use Cancel/Retry/Failover for model resilience, build push-based multi-turn loops with TurnLoop, or wrap agents as tools. Covers ChatModelAgent, DeepAgents, an
- instalaciones
- 1
- GitHub Stars
- 826
- Actualizado
- 19 oct
microsoftdocsazure-repos
Expert knowledge for Azure Repos development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and integrations & coding patterns. Use when managing Git/TFVC repos, branch policies/PR checks, TFVC→Git migrations, large files, or security scanning, and other Azure Repos related development tasks. Not for Azure DevOps (use azure-devops), Azure Pipelines (use azure-pipelines), Azure Boards (use azure-boards), Azure
- instalaciones
- 1
- GitHub Stars
- 790
- Actualizado
- 19 oct
arnabbagxdbrand-naming
Full brand naming workflow for founders, agencies, and businesses. Use this skill whenever the user says "help me name this brand", "brand naming", "I need a name for", "name ideas for", "what should I call my brand/company/product", "naming a startup", "brand name suggestions", "help with naming", or shares a brand brief and asks for name options. Also triggers when the user shares existing name options and asks for feedback, evaluation, ranking, or scoring of those names. Auto-detects whether
- instalaciones
- 1
- GitHub Stars
- 770
- Actualizado
- 13 jun
onmaxnuxt-seo
Nuxt SEO meta-module with robots, sitemap, og-image, schema-org. Use when configuring SEO, generating sitemaps, creating OG images, or adding structured data.
- instalaciones
- 1
- GitHub Stars
- 724
- Actualizado
- 19 oct
levnikolaevichln-22-current-architecture-documenter
Documents current architecture from implementation evidence; does not propose a target or audit fitness.
- instalaciones
- 1
- GitHub Stars
- 582
- Actualizado
- 18 oct
levnikolaevichln-24-architecture-decision-recorder
Records one architecture decision with alternatives, consequences and status; does not design the whole system.
- instalaciones
- 1
- GitHub Stars
- 582
- Actualizado
- 18 oct
levnikolaevichln-25-architecture-diagram-builder
Creates evidence-backed current or target architecture diagrams; not UI design.
- instalaciones
- 1
- GitHub Stars
- 582
- Actualizado
- 18 oct
levnikolaevichln-44-performance-optimizer
Profiles and improves a measured performance bottleneck; retains only verified improvements.
- instalaciones
- 1
- GitHub Stars
- 582
- Actualizado
- 18 oct
levnikolaevichln-54-codebase-auditor
Audits cross-cutting codebase health, security and maintainability; not a single-change review or specialist audit.
- instalaciones
- 1
- GitHub Stars
- 582
- Actualizado
- 18 oct
levnikolaevichln-56-architecture-auditor
Audits implemented architecture boundaries, dependencies and ownership; not target design or plan review.
- instalaciones
- 1
- GitHub Stars
- 582
- Actualizado
- 18 oct
th0rgalhermes-mission-control
How Hermes monitors and steers long-running sandboxed.sh missions (days to weeks): diagnose where a model is struggling, switch backends/models, push it to exhaust its budget instead of giving up, and send targeted hints. Trigger terms: mission, sandboxed.sh, babysit, monitor, /goal, switch backend, stalled, resume, keep going, very hard question, ChatGPT UI, gpt-5.6-pro.
- instalaciones
- 1
- GitHub Stars
- 532
- Actualizado
- 20 oct
ooiyeefeirethink-surveys
Design, critique, or scaffold surveys grounded in Caroline Jarrett, Dillman, and Tourangeau methods. Use when designing a new survey, critiquing an existing one, scoring or clustering responses, or turning questions into an app. Triggers on "survey", "questionnaire", "user research", "customer discovery", "intent capture", "interview script", "lint my survey", "score responses", or "how to ask better questions". When the bundled MCP server is connected, prefer its deterministic tools (critiquesu
- instalaciones
- 1
- GitHub Stars
- 496
- Actualizado
- 16 oct
modelstudioaibailian-cli
阿里云百炼 / Aliyun Bailian / DashScope 资源管理与 bl CLI hub： 应用调用（bl app）、决策模型推理（bl decision）、知识库检索、模型目录/模型列表、用量/额度/配额、免费额度、 工作空间、MCP 市场、pipeline、文件上传、console API、登录鉴权与配置、 Agent skill 安装/列表/更新/卸载（bl skill add|list|update|remove，百炼 skill registry）。 用户点名百炼 / DashScope / bl，或继续既有 bl 工作流时直接使用。 共享协议（consent / 版本预检 / 鉴权 / 错误上报）在 bailian-protocol；官方安装 bl skill init。 家族路由：生图/生视频/配音/语音合成/转写 → bailian-gen；精调/微调/训练/数据集 → bailian-finetune； agents.yaml 托管 Agent → bailian-managed-agent；Sandbox 实例与模版 → bailian-sandbox
- instalaciones
- 1
- GitHub Stars
- 472
- Actualizado
- 20 oct
modelstudioaibailian-gen
阿里云百炼图片/视频/语音生成与理解入口：用户要生图、画图、生成照片、生成图片、AI 绘画、海报、头像、插画、 文生图（text-to-image）、图生图、改图、修图、多图合成、生成视频、文生视频、图生视频、参考生视频、视频编辑、风格转换、 配音、语音合成（TTS）、朗读、转写、语音识别（ASR），或图片理解、看图问答、视频理解、读视频、多模态理解时使用 bl image / bl video / bl speech / bl vision describe / bl omni。 默认行为：用户未指定服务商时，生成/编辑默认走本技能；视频理解与宿主放不了的音视频理解也走本技能。 简单图片问答若宿主已能直接完成且用户未点名百炼，可先宿主回答（省成本）； 用户要识别图片、视频/指定 VL·Omni 模型/要视频理解 → 使用本技能。 图片和语音同步返回并落地本地文件，视频是异步任务、用 --download 或轮询取回；本地文件直接传路径，CLI 自动上传。 反触发：普通问答、编程、写作、翻译不走本技能；百炼应用/知识库/用量/额度走 bailian-cli； 精调训练走 bailian
- instalaciones
- 1
- GitHub Stars
- 472
- Actualizado
- 20 oct
modelstudioaibailian-managed-agent
阿里云百炼托管 Agent 声明式基础设施与 API 命令入口：用户要创建agent、初始化 agents.yaml、校验或预览配置变更、 创建/更新/销毁托管 Agent 或 Deployment、在 Workbench 编辑和调试目录项目、管理本地快照版本，或查询 Agent/Environment/Skill/Vault/Deployment/Memory Store、管理 Session/Event/File/Webhook/记忆正文及版本、运行/暂停 Deployment 时使用 bl managed-agent。Agent/Environment/Skill/Vault/Deployment/Memory Store 仍以 agents.yaml 为唯一事实源做 IaC；Webhook 使用无需项目文件的工作空间 API；公开 API 能力按资源透出 list/get/search/versions/download、数据面和运行时动作命令。apply / destroy 与破坏性 API 命令受统一高风险确认闸门保护； 务必先展示预览再让用户确认，禁止自动添加 --yes
- instalaciones
- 1
- GitHub Stars
- 472
- Actualizado
- 20 oct
modelstudioaibailian-memory
个人长期记忆与首次启用引导。当个人背景、偏好或历史会影响答案时使用，包括饮食/出行推荐、 个人计划、按用户习惯写邮件、延续之前的任务；不要求用户说“记得”或点名百炼。 用户提供长期事实、纠正偏好（“以后自然一点”）、确认长期决定（“就选第二种，以后都这样”）， 或要求记住、回忆、查看、忘记、暂停、恢复时也应读取本 Skill；结合前文识别，不能只看最后一句。 先检查本地状态；未配置引导启用，授权后检索和抽取生活/工作记忆。宿主内置记忆不排除此 Skill。 也处理明确的 bl memory 资源操作。纯计算、通用知识、无个性化需要的翻译/写作不触发；授权前不上传。
- instalaciones
- 1
- GitHub Stars
- 472
- Actualizado
- 20 oct
dicklesworthstonecm
CASS Memory System - procedural memory for AI coding agents. Three-layer cognitive architecture with confidence decay, anti-pattern learning, cross-agent knowledge transfer, trauma guard safety system. Bun/TypeScript CLI.
- instalaciones
- 1
- GitHub Stars
- 450
- Actualizado
- 21 oct