Showing 6391–6420 of 10205 skills
Configure Codex user-level AGENTS.md when the user asks to install, adopt, or update these guidelines. Inspect the actual environment, relevant Codex configuration, and exposed models first; research public model facts, recommend a configuration, collect unresolved preferences together, and apply the authorized changes. Honor an explicit project-level target. Reviewing the repository or ordinary coding does not request installation.
Yuimi-chaya/codex-development-guidelines
用火山引擎 Podcast AI 模型生成中文双人对话播客。当用户要把文章、报告、话题文本转成播客音频、生成对话式音频内容时使用,需要环境具备火山引擎 APP_ID 和 ACCESS_KEY。支持 mp3/ogg_opus/pcm/aac、语速调节、自定义音色、断点续传。不用于:单人朗读式 TTS(用普通语音合成)、英文播客(模型主要优化中文)、播客文稿本身的撰写(先用写作类 skill 产出文本再来)。
staruhub/ClaudeSkills
用 ByteDance Seedream 4.0 API(经 Segmind)生成 AI 图像。当用户要从文字描述生成营销素材、海报、产品图、概念图、社交媒体配图等高质量图像,且环境配有 SEGMIND_API_KEY 时使用。支持 2K/4K、多比例、单次最多 15 张批量、最多 3 张参考图控风格。不用于:修改/编辑已有图片(用图像编辑类 skill)、视频生成、无 API 环境下的快速配图需求。
staruhub/ClaudeSkills
将天气要素(风速、能见度、降雨量等)单站预报系统的项目文档、模型、报告、评估结果整理成符合省级自然科学基金项目编写规范的专题研究报告。适用于:(1) 基于Claude Code + OpenSpec开发的气象预报系统结题报告编写,(2) 将技术文档转换为学术研究报告格式,(3) 生成符合省级自然科学基金规范的专题研究报告,(4) 整合项目代码、模型、评估指标等技术材料为规范化学术报告。触发关键词:"专题研究报告"、"结题报告"、"天气预报系统"、"基金项目报告"、"风速预报"、"能见度预报"、"降雨量预报"、"气象预测"、"单站预报"等。
staruhub/ClaudeSkills
胥克谦式AI-Native产品开发方法论。适用于:(1) 使用AI Agent(Claude Code、Codex、Cursor等)进行产品级软件开发,(2) 设计和优化Harness/Skill体系,(3) 文档驱动开发(SDD)流程,(4) 构建自动化质量门禁和eval机制,(5) Token成本优化与缓存策略,(6) 产品人转型开发者的AI编程实践。触发场景包括"帮我设计开发流程"、"怎么降低token成本"、"怎么提高AI编码质量"、"文档驱动"、"质量门禁"、"harness设计"、"单agent vs multi-agent"、"自动化迭代"、"AI产品开发"、"SDD"、"eval机制"等。即使用户只是说"帮我用AI写代码"或"怎么让agent干活更靠谱"也应触发。注意:如果产品是行为开放、用户输入不可穷举的AI-native类型,请改用 xuefeng-method skill。不用于:单个bug修复或小改动(无需方法论)、PRD需求文档写作(用product-manager)。
staruhub/ClaudeSkills
雪峰式AI-Native产品开发方法论。适用于:(1) 用户行为开放、不可穷举的AI-native产品(AI日历、AI助手、AI推荐、对话式产品等),(2) 强模型依赖型场景,AI驱动核心决策而非仅辅助,(3) 多专精Agent架构设计与分工,(4) 上线后快速校准、行为审计与漂移检测,(5) 模型选择和智能路由策略,(6) 概率性输出的质量评估。触发场景包括"AI-native产品怎么做"、"用户行为不可预测怎么办"、"多agent怎么分工"、"模型漂移怎么处理"、"校准到95%太难了"、"唯快不破"、"怎么选模型"、"agent并行分工"、"AI产品上线后怎么迭代"。注意:如果产品是场景明确、边界可定义的+AI类型,请改用 keqian-method skill。即使用户没有明确说"AI-native",但在讨论AI驱动决策、用户行为不可预测、概率性输出等话题时也应触发。
staruhub/ClaudeSkills
Light the current Unreal level as an outdoor scene (a sun, a sky atmosphere, a sky light and height fog) with UEAgent's MCP tools, then show the result in a screenshot. Use when the user asks to light a level, set up daylight or a sunset, or add a sky.
CarlxsMG/UEAgent
Turn an Unreal Editor workflow into a reusable skill built on UEAgent's MCP tools. It finds the tools the task needs, rehearses the task once in the editor, checks the result, and writes a SKILL.md with the tool sequence and the pitfalls it met. Use when the user asks to make, capture or automate an Unreal workflow as a skill, or to repeat a task they just did with the tools.
CarlxsMG/UEAgent
Discover, identify, inspect, and compare Relewise Datasets. Use when a user asks which Datasets they can access, wants details or Agent Gateway capabilities for a Dataset, or needs Dataset context resolved before another Relewise task.
Relewise/relewise-agent-plugins
Set up, verify, or repair Relewise Agent Gateway authentication. Use when a user wants to connect Relewise, sign in or reconnect with OAuth, diagnose MCP connectivity, configure a Personal Access Token, resolve missing Dataset access or Agent Gateway configuration, or check whether Relewise is already connected.
Relewise/relewise-agent-plugins
Convert a spec, roadmap item, or rough plan into independently implementable issue slices with scope, dependencies, acceptance criteria, and validation. Use when the user asks to split work into GitHub issues, local markdown tasks, or agent-ready implementation chunks.
stark-ai-de/agent-skills
Triage repository issues through a maintainer decision tree. Use when the user asks to classify issues, apply labels, identify missing information, mark ready-for-agent work, split vague reports, or clean up an issue inbox.
stark-ai-de/agent-skills
Author a new or successor public Architecture Compass target-repository ADR and its local adoption in stark-ai-de/agent-skills. Use when a maintainer supplies a decision idea or rough requirements and wants generic requirements, paired Short/Long/Guide triplets, conflict reporting, release synchronization, validation, and a GitHub pull request. Do not use for internal or skill-runtime ADRs or adoption in unrelated repositories.
stark-ai-de/agent-skills
Help install, list, update, remove, or troubleshoot Agent Skills using the Vercel skills CLI. Use when the user asks about npx skills add, installing a whole repo, installing one skill, global vs project installs, symlink vs copy, or Codex/Claude/Cursor agent targets.
stark-ai-de/agent-skills
Turn ambiguous coding requests into verified Claude Code implementation specs. Use when the user wants requirements, an implementation plan, or a spec before coding; include source checks, needed ADRs, and agreed delivery. Do not use for already specified direct implementation or memory cleanup.
stark-ai-de/agent-skills
Turn ambiguous coding requests into verified Cursor Agent implementation specs. Use when the user wants requirements, an implementation plan, or a spec before coding; include source checks, needed ADRs, and agreed delivery. Do not use for already specified direct implementation or memory cleanup.
stark-ai-de/agent-skills
Delegates coding tasks from Codex to local Claude Code in print mode while preserving Claude's normal runtime customizations by default. Use when: (1) You want Codex to call Claude Code locally, (2) You need Claude-side skills, plugins, MCP servers, custom commands, CLAUDE.md rules, or workspace settings to stay active, (3) You want resumable Claude sessions from Codex via SESSION_ID, (4) You need thin `claude mcp` / `claude plugin` passthrough from the same bridge.
Dianel555/DSkills
Use when an approved non-trivial plan from nobrainer-tech-flow needs an installed-capability inventory, bounded worker assignments, task-local specialist briefs or native parallel execution; do not use to elicit requirements, invent the plan, schedule work, or create sessions. Aliases: nb-team, nobrainer-skill-browser.
nobrainer-tech/nobrainer-tech-flow
Recommend focused improvements to agent instructions and workflows.
porada/domfiles
Use when preparing, performing, or coordinating an independent review through native subagents, top-level reviewer threads, or provider sessions. Own initial reviewer assignments, findings reports, disputes, corrections, follow-ups, replacement handoffs, and completion within that review. Also use when creating or maintaining reusable prompts for coordinated reviews. Exclude a main agent’s standalone review and independently supplied findings or status reports outside an active review workflow.
porada/domfiles
Run and drive an Expo / React Native app on the iOS Simulator. Pick an execution mode (Expo Go, dev client, Storybook-mobile, web-on-mobile), build and install a dev client, and clear the recurring Expo/RN prompts that block automation: the push-token alert that stacks until the overlay darkens the screen, the "Open in app?" deep-link dialog, the dev menu, and the element-inspector trap. Sits ON TOP of ios-simulator; failures route to ios-simulator-triage. Project-agnostic; discovers bundle id and scheme from the app config. Use for "run my Expo app on the simulator", "load a dev client", or "drive Storybook on iOS".
simiancraft/simiancraft-skills
Capture proof of a driven iOS-simulator flow: vision-verifiable screenshots, video (mp4), and a manifest tying steps to artifacts, plus an honest list of what a simulator cannot do (deliver a push, use a real camera, place a call, fully observe the network). Produces artifacts to a contract that a separate GitHub-presentation skill consumes; this skill owns extraction, not publishing. Sits beside ios-simulator; project-agnostic. Use for "capture evidence of an iOS flow" or "record the simulator".
simiancraft/simiancraft-skills
pzfreo/draftwright-python
bee.lua 运行时库指南——Lua 5.4/5.5 上的跨平台系统级绑定(异步 I/O、网络、子进程、线程、文件系统、文件监控、崩溃 dump)。当需要在本项目里编写、修改或排查使用 `require "bee.*"` 的 Lua 代码,涉及 socket/select/epoll/async、thread/channel/serialization、subprocess、filesystem/filewatch、time/sys/crash/debugging/windows,或需要按平台差异处理行为时,使用本 skill。即使用户没有明确提到 bee.lua,只要上下文是在调用 `bee` 命名空间下的模块,也应使用。不要用于纯 Lua 语言/标准库问题、与 bee 无关的第三方 C 模块,或本项目 C++ 层 `bee/`、`binding/` 的实现细节(那些看源码)。
actboy168/bee.lua
Find unclaimed open source issues that match the user's skills and experience level. Searches for issues created by maintainers/org admins, checks contribution eligibility, and ranks by learning value. Use when looking for an issue to contribute to, starting OSS contributions, or finding GSoC-friendly issues. Not for finding problems that nobody has filed an issue for yet. Use oss-find-real-issues for that.
chiruu12/OSS-Skills
当用户希望找回长对话中没有被看见、确认或明确取舍的信息点时使用。包括四类情况:用户提了但 AI 没答、AI 提了但用户没接住、AI 替用户做了选择,以及 AI 本该提问却自行决定。用户说「对账」 「建清单」「哪些没闭环」「open loops」,或抱怨对话跑偏、旧问题消失、AI 替自己做主时触发。 长项目进行到一半才开始审计,也属于正常入口。用户明确启用后,在该项目或任务中持续逐轮运行, 直到用户明确暂停或停止,不要求每轮重新点名。不要用于单轮编号问答、普通任务进度追踪,或用户 已经明确看见但暂缓执行的事项。仅检查、调试、修改或发布 Open Loops 本身的轮次属于维护通道: 可以使用本 skill 排障,但不得写进业务项目的原文存档或未闭环清单。
haorantang97/LabKit
Publish a prepared AI skill or rule repository to GitHub, or repair an existing publication, using available CLI, API or browser tools. Use when the user asks to upload, push, create a GitHub repository or make it live. Covers repository metadata and verification of the published result. Use the authoring modules for unfinished content and submit-to-directories for community listings.
haorantang97/LabKit
Unified Kanban lifecycle — task generation, lint validation, META bundling, completion archiving, and flat-to-V6 migration in one meta skill.
mokhtarabadi/cognitive-lead-hq
Use this skill when handling PII, personal data, privacy regulations, data subject requests, consent management, data breach response, or any GDPR/CCPA/HIPAA compliance task. Provides structured privacy compliance workflows based on regulatory frameworks.
JPeetz/agent-skills
Use this skill when producing local videos on the 16GB M5 executor.
JPeetz/agent-skills