Loading...
Loading...
Found 8,761 Skills
Enforces a 'Document-then-Execute' workflow. Use when an agent needs to run shell commands, execute tests, build projects, or perform any task that should favor established task runners (Makefile, npm run) and be logged to .cmds-by-agents/ for auditability.
Git conventions and workflow best practices including Conventional Commits, branch naming, and commit message guidelines. Use when user needs guidance on git standards, commit formats, or workflow patterns.
Create (or update) and validate Agent SOPs (Standard Operating Procedures) - markdown-based workflows that guide AI agents through complex, multi-step tasks with RFC 2119 constraints.
Interactive model selection workflow with paginated navigation. Use when users want to select a model interactively - guides them through provider selection then model selection using the question tool with pagination support for large lists.
Expert guidance for building production-grade AI agents and workflows using Pydantic AI (the `pydantic_ai` Python library). Use this skill whenever the user is: writing, debugging, or reviewing any Pydantic AI code; asking how to build AI agents in Python with Pydantic; asking about Agent, RunContext, tools, dependencies, structured outputs, streaming, multi-agent patterns, MCP integration, or testing with Pydantic AI; or migrating from LangChain/LlamaIndex to Pydantic AI. Trigger even for vague requests like "help me build an AI agent in Python" or "how do I add tools to my LLM app" — Pydantic AI is very likely what they need.
Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to "串起来", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.
Microsoft Teams integration. Manage communication data, records, and workflows. Use when the user wants to interact with Microsoft Teams data.
Validate-then-fix workflow for PR review comments: Fetch, Validate, Plan, Fix, Commit. Use when user wants to address PR feedback, fix review comments, or resolve reviewer requests. Use for "fix PR comments", "address review", "pr-fix", or "resolve feedback". Do NOT use for creating PRs, reviewing code without fixing, or general debugging unrelated to PR comments.
Comprehensive skill for Adobe Substance 3D Painter texturing and material creation workflow. Use this skill when creating PBR materials, exporting textures for web/game engines, optimizing 3D assets for real-time rendering, or automating texture workflows. Triggers on tasks involving Substance 3D Painter, PBR texturing, material creation, texture export for Three.js, Babylon.js, Unity, Unreal, glTF optimization, or Python API automation. Creates optimized textures for threejs-webgl, react-three-fiber, and babylonjs-engine materials.
High-quality article translation skill, adopting a four-step professional translation workflow: **Analysis → Initial Translation → Review → Final Draft**. Only supports Chinese ↔ English, Chinese ↔ Japanese translation. Triggered when users explicitly request translation using terms such as "翻译", "translate", "精翻", "翻訳", "翻译文章", "translate to Chinese/English/Japanese", "改成中文", "改成英文", "改成日文", "翻成中文", "翻成日文", "翻成英文", "英译中", "中译英", "中译日", "日译中", "日本語に翻訳", "中国語に翻訳", "英語に翻訳", "これを翻訳して", "put this in Chinese", "put this in English", "put this in Japanese", "convert to Chinese", "convert to English", "convert to Japanese", "帮我翻一下", "本地化", "localize", "这篇文章翻译一下", or provide a URL/file/text body and explicitly request a final draft in the target language. Not applicable to requests for only summarization, explanation, comprehension, or organization. If the input is a URL, prioritize using `curl -L` to request `r.jina.ai` to fetch the body content in Markdown; if fetching fails or the content is incomplete, you must stop immediately and ask the user to provide the full text themselves.
Used when user requests involve dataset queries, SQL creation, and BFF development for the Lovrabet/Yuntoo platform. Trigger words: dataset, data table, custom SQL, filter, sql.execute, bff.execute, get_dataset_detail, validate_sql_content, save_or_update_custom_sql, save_or_update_bff_script, @lovrabet/sdk, MCP SQL workflow, multi-table association, lovrabet development.
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches. AI agents running in CI/CD pipelines.