Loading…
Showing 6331–6360 of 10177 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| llm-eval-and-prompt-injection-fortressimMamdouhaboammar/anti-slop-engineeringReview how agents handle untrusted text, authorize tool requests, and protect private outputs. Use for retrieval, tool connectors, agent permissions, or evaluation of coding agents. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| skill-evolutionCarlo1911/skill-evolutionAutonomous skill improvement — analyze agent sessions, generate structured improvement proposals, and optionally auto-apply high-confidence changes to your skills. Host-agnostic (Hermes, Claude Code, and any HostAdapter) | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| podcast-generatorstaruhub/ClaudeSkills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)。 | Stars: 741 | Updated | Claude CodeCodex | Verified | Install |
| seedream-imagegenstaruhub/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。 | Stars: 741 | Updated | Claude CodeCodex | Verified | Install |
| weather-forecast-reportstaruhub/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。 | Stars: 741 | Updated | Claude CodeCodex | Verified | Install |
| keqian-methodstaruhub/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)。 | Stars: 741 | Updated | Claude CodeCodex | Verified | Install |
| xuefeng-methodstaruhub/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。 | Stars: 741 | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersosrim/niksiUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| niksiosrim/niksiInstall, update, and inspect agent skills with nik, which scans every file before it writes. Use when asked to install, update, or list skills. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| agent-turn-reviewdimagi-internal/aceInternal ACE turn step — ACE's pre-send review: one inline §A–§F pass before every outbound reply, deliverable or PR. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| oss-find-issuechiruu12/OSS-SkillsFind 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. | Stars: 62 | Updated | Claude CodeCodex | Verified | Install |
| subagent-delegationshinpr/codex-subagent-playbookGuides parents in subagent model selection and delegation through completion. Use when assigning work to subagents, assessing their progress or results, or intervening in delegated work. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| oss-bootstrapnicholyx/ai-skills把一个新项目(或只有代码的裸仓库)落实为符合主流规范的开源项目——CI、治理文件、Issue/PR 模板、仓库自动化、文档体系、看板与发布流程。当用户说「新建开源项目」「给项目加上 CI / 规范」「给这个项目加上开源规范」「按热门开源项目的标准搭基建」时使用。基建就位后的日常迭代请改用 maintain-loop skill。 | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| skills-doctornicholyx/ai-skills诊断「技能装了却没反应」—— 检查技能装在哪个目录、软链有没有断、SKILL.md 能不能被加载、有没有被别的目录顶掉。当用户说「技能装了但用不了,帮我看看」「技能没反应」「我说了触发词什么都不发生」「检查一下技能装好没有」「skills 怎么不生效」时使用。 | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| update-claude-codenicholyx/ai-skills当用户提到"更新 claude"、"升级 claude code"、"检查 claude 版本"、"claude code 最新版本"时使用此技能。 | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| review-planfeO2x/guided-codingReview a completed Guided Coding plan draft against the codebase before its Planning Phase ends. Run only when explicitly requested by the user or by another Guided Coding skill. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| write-planfeO2x/guided-codingWrite a Guided Coding plan or follow-up plan after its approach has been discussed. Run only when explicitly requested by the user or by another Guided Coding skill. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| agent-quality-gradingever-just/agentskillsGrade AI-agent performance qualitatively — every user↔agent conversation on four axes (did it do the task / respond fast / use the right tools / message quality), plus the generated assets (PDFs, images, videos) and the prompts/configs — using writing-quality skills as the message-quality rubric. Produces per-channel grades, per-agent report cards, asset grades, and prompt grades, each with verbatim evidence. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| codexTayhlow8/Caixa-D-gua-website-2026OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ autistic developer" second opinion. Use when asked to "codex review", "codex challenge", "ask codex", "second opinion", or "consult codex". (gstack) | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| context-restoreTayhlow8/Caixa-D-gua-website-2026Restore working context saved earlier by /context-save. Loads the most recent saved state (across all branches by default) so you can pick up where you left off — even across Conductor workspace handoffs. Use when asked to "resume", "restore context", "where was I", or "pick up where I left off". Pair with /context-save. Formerly /checkpoint resume — renamed because Claude Code treats /checkpoint as a native rewind alias in current environments. (gstack) | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| context-saveTayhlow8/Caixa-D-gua-website-2026Save working context. Captures git state, decisions made, and remaining work so any future session can pick up without losing a beat. Use when asked to "save progress", "save state", "context save", or "save my work". Pair with /context-restore to resume later. Formerly /checkpoint — renamed because Claude Code treats /checkpoint as a native rewind alias in current environments, which was shadowing this skill. (gstack) | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| deep-researchPyroxin/opinionated-claude-skillsDeprecated name; the skill formerly here is now opinionated-research:interactive-research. Retained as a context-level notice because Claude Code now ships a built-in deep-research workflow that runs one-shot, non-interactive fan-out research (no conversation after the report). interactive-research instead runs a persistent agent team you can keep questioning after the report is delivered. Guidance for Claude: when the user makes a research request, ask whether they want the interactive team (interactive-research) or the built-in non-interactive deep-research workflow before starting. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| Add multimodal lifelong memory to MCP and Python agents with SimpleMemagentskillexchange/skillsUse SimpleMem to store, compress, index, and retrieve text or multimodal memories for agents through MCP or Python integrations. | Stars: 65 | Updated | Claude CodeCodex | Verified | Install |
| ultimate-ai-media-generator-skillZeroLu/Ultimate-AI-Media-Generator-SkillGenerate and monitor CyberBara Public API v1 image, video, audio, and music tasks end-to-end. Use when work involves CyberBara `/api/v1` endpoints for listing models, uploading reference media, quoting credits, creating generation tasks, polling task status, checking credits balance and usage, or saving final media outputs. | Stars: 115 | Updated | Claude CodeCodex | Verified | Install |
| activecampaign-automationSHAH-SHLOK13/Sentinel---AML-and-KYC-compliance-platform-Automate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation enrollment, and tasks. Always search tools first for current schemas. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| amplitude-automationSHAH-SHLOK13/Sentinel---AML-and-KYC-compliance-platform-Automate Amplitude tasks via Rube MCP (Composio): events, user activity, cohorts, user identification. Always search tools first for current schemas. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| asana-automationSHAH-SHLOK13/Sentinel---AML-and-KYC-compliance-platform-Automate Asana tasks via Rube MCP (Composio): tasks, projects, sections, teams, workspaces. Always search tools first for current schemas. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| h3-prompt-writingWeeexiao/skillsWrite MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal requests into H3 prompt structures, composing integrated_multimodal_description, overall_soundscape, and non_diegetic_music, aligning keyframes, or defining reference labels for images, videos, and audio. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| prd-firstAbhillashjadhav/AI-PM-essential-skillsForces a written PRD before any code generation. Use this skill when the user says "build", "create app", "make me a", "vibe code", "let's build", "I want an app that", "spin up a", "prototype a", "ship a", or any phrasing that signals they want code generated from a high-level idea. Also use when the user references an existing project but the conversation has no PRD context (no /prds/ file referenced, no clear success metric). The skill blocks code generation until a 5-field PRD exists as a markdown file in the repo. Do NOT use when the user is asking factual questions, debugging existing code, editing a specific file they've named, or working in a repo where a PRD for this feature already exists at /prds/. Skip when user explicitly says "skip the PRD" or "just code it" — but flag the risk once before proceeding. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| create-rulemgiovani/ai-arsenalCreate a new memory/instruction rule for whatever AI coding tool a project actually uses, a CLAUDE.md entry or .claude/rules/*.md file for Claude Code, an AGENTS.md entry for Codex/Cursor/Copilot/Gemini-CLI-style tools, or a .cursor/rules/*.mdc file for Cursor. Use when the user runs /create-rule or asks to add a project rule, user/personal rule, coding standard, style guide entry, or workflow instruction to memory, AGENTS.md, or CLAUDE.md. Not for creating skills or slash commands (use create-skill). Not for discovering or installing existing third-party skills (use find-skills). | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |