All authors
Claude Skills by majiayu000
github.com/majiayu00015,497 skills879 installs33,563 views
- Chanjing One Click Video Creation用户输入选题或工作流，自动生成完整短视频成片（文案、分镜、数字人口播与 AI 画面混剪）；调用 Chanjing Open API 与同仓库子技能脚本。Votes: 0GitHub stars: 666
- Chat Format Marshadgani Arshad AiFormat prompts for different LLM providers with chat templates and HNSW-powered context retrievalVotes: 0GitHub stars: 666
- ChatbotUse when a support or sales bot on a live website must behave: persona/system prompt, grounding so it cannot invent prices or policy, jailbreak and injection defense, the human handoff, launch metrics and kill switch. NOT the agent loop or RAG index under it (that is `building-agents`), NOT a human answering one ticket (that is `customer-support`).Votes: 0GitHub stars: 666
- Check ReportingUse when auditing a manuscript item by item against a reporting guideline or risk-of-bias tool. Covers 49 reporting guidelines and risk-of-bias tools (STROBE, CONSORT, STARD, TRIPOD+AI, PRISMA, QUADAS and more), marking each item PRESENT, PARTIAL or MISSING. Not a reviewer critique (/self-review).Votes: 0GitHub stars: 666
- CkPersistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.Votes: 0GitHub stars: 666
- Claude Ask Wonecosystem 2300 SkillsDeliberative consultation with another Claude model via Task tool. Opus consults Sonnet, Sonnet consults Opus. Ask, evaluate, critique, iterate until workable agreement.Votes: 0GitHub stars: 666
- Claude Mail Bridge InitUse when Claude Mail Bridge is installed (presence.json exists). Provides behavior guidelines for remote collaboration scenarios, including presence detection and MCP usage.Votes: 0GitHub stars: 666
- Claude Opus 4 6 Prompting Kastalien Research ThoughtboxComprehensive prompt engineering reference for Claude Opus 4.6. Use this skill whenever you are writing, reviewing, or optimizing prompts for Claude Opus 4.6 (or Sonnet 4.6 / Haiku 4.5). Covers foundational clarity principles, output formatting control, tool use, adaptive thinking, agentic system design, multi-context-window workflows, and migration guidance from earlier models. Trigger this skill for any task involving system prompt authorship, agent harness design, multi-step pipeline const...Votes: 0GitHub stars: 666
- Claude Opus 4 6 PromptingComprehensive prompt engineering reference for Codex Opus 4.6. Use this skill whenever you are writing, reviewing, or optimizing prompts for Codex Opus 4.6 (or Sonnet 4.6 / Haiku 4.5). Covers foundational clarity principles, output formatting control, tool use, adaptive thinking, agentic system design, multi-context-window workflows, and migration guidance from earlier models. Trigger this skill for any task involving system prompt authorship, agent harness design, multi-step pipeline constru...Votes: 0GitHub stars: 666
- Clawtributor Coralshades Acm AiCommunity incident reporting for AI agents. Contribute to collective security by reporting threats.Votes: 0GitHub stars: 666
- Clinical NlpExtracts medical entities (Diseases, Medications, Procedures) and patient outcome mentions with temporal anchoring from unstructured clinical text using regex and simple rules (or LLM wrappers).Votes: 0GitHub stars: 666
- CluelyReference system prompt and tool schemas for Cluely. Use when imitating, comparing, or analyzing Cluely's prompting style; designing prompts inspired by Cluely; or answering questions about how Cluely is prompted.Votes: 0GitHub stars: 666
- Cnb Docs查询 CNB 平台官方文档，覆盖代码托管、制品库、AI 助手、云原生构建等。Votes: 0GitHub stars: 666
- CodebuddyReference system prompt and tool schemas for CodeBuddy. Use when imitating, comparing, or analyzing CodeBuddy's prompting style; designing prompts inspired by CodeBuddy; or answering questions about how CodeBuddy is prompted.Votes: 0GitHub stars: 666
- Codex Ask Wonecosystem 2300 SkillsDeliberative consultation with Codex CLI. Ask, evaluate, critique, iterate until workable agreement.Votes: 0GitHub stars: 666
- Codex Subagent DesignerRoute Codex delegation design, subagent prompting, reusable catalog-asset design, and custom-agent template review.Votes: 0GitHub stars: 666
- Colang GenGenerates NeMo Guardrails Colang (.co) files and YAML config blocks from a plain-language description of a chatbot's purpose, allowed behaviors, and constraints. Use this skill whenever a user wants to build guardrails for a chatbot, define allowed intents for an LLM, create an AI firewall with NeMo Guardrails, generate Colang flow definitions, or configure a semantic allow-list for a bot. Trigger this skill even when the user just describes what their bot should and shouldn't do — generating...Votes: 0GitHub stars: 666
- Comet AssistantReference system prompt and tool schemas for Comet Assistant. Use when imitating, comparing, or analyzing Comet Assistant's prompting style; designing prompts inspired by Comet Assistant; or answering questions about how Comet Assistant is prompted.Votes: 0GitHub stars: 666
- Configure GrimoireUse when the user wants to view, edit, remove, or validate their grimoire settings — including reading current preferences, changing or deleting a setting, switching a named profile, or checking grimoire.toml for contradictions and expired entries.Votes: 0GitHub stars: 666
- Connect Chrome Kk20300113 Png My Claude SkillsLaunch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".Votes: 0GitHub stars: 666
- Connect Chrome Sadie100 Claude DotfilesLaunch GStack Browser — AI-controlled Chromium with the sidebar extension baked in.Votes: 0GitHub stars: 666
- Consolidate Then Review Ask QuestionsConsolidate answer to existing open questions (removing the open-ended questions section entirely), update a decision table, and assert if new questions need to be asked. Review the amended document: If new questions need to be asked, create a new section for open questions, and ask as many questions as possible, with options and recommended choice, following the template provided in the prompt.Votes: 0GitHub stars: 666
- Content Gen正文生成(四模式)Votes: 0GitHub stars: 666
- Context FundamentalsThis skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.Votes: 0GitHub stars: 666
- ContextUse when the user runs /context or asks for a briefing on his Personal OS — who he is, how he thinks, how he wants AI to interact with him, and where he is right now. Produces a self-contained system prompt about King that any future AI session can use to instantly understand him.Votes: 0GitHub stars: 666
- Conversation Flow当系统提示词需要定义 AI 如何分类用户意图、路由到不同处理流程、决定澄清策略和自主度级别时调用此 Skill。适用于多任务型 AI 助手、客服机器人、编程工具、研究助手等需要结构化对话管理的场景。不适用于：纯问答型系统（无任务执行）、单轮交互（无对话状态）、简单的 prompt 模板（无路由逻辑）。当需求仅涉及"输出什么格式"而非"如何决定输出什么"时，应该用 output-formatting 而非本 Skill。Votes: 0GitHub stars: 666
- Copilot Docs Hoodini Ai Agents Skills 2Configure GitHub Copilot with custom instructions. Use when setting up .github/copilot-instructions.md, customizing Copilot behavior, or creating repository-specific AI guidance. Triggers on Copilot instructions, copilot-instructions.md, GitHub Copilot config.Votes: 0GitHub stars: 666
- Cortex TelemetryExtracción, análisis e inspección de telemetría runtime y logs de transcripción (transcript.jsonl). Dispara con \"telemetría\", \"cortex telemetry\", \"transcript logs\", \"historial de prompts\", \"analizar transcripciones\".Votes: 0GitHub stars: 666
- Cost GuardPer-session cost and token budget tracking for AI coding agents. Monitors cumulative spend, warns at thresholds, and enforces limits with three modes: reject (stop work), alert (warn and continue), downgrade (suggest cheaper approach). Ported from the LOCO-Agent BudgetManager. Trigger phrases: "set a budget", "track my spend", "cost limit", "how much have I spent", "token budget", "spending cap".Votes: 0GitHub stars: 666
- Create AssistantCreate and configure Vapi voice AI assistants with models, voices, transcribers, tools, hooks, and advanced settings. Use when building voice agents, phone bots, customer support assistants, or any conversational AI that handles phone or web calls.Votes: 0GitHub stars: 666
- Create Control Manifest Hongyuanc Codex Game StudiosGenerate the programmer control manifest from accepted ADRs, technical preferences, and engine rules.Votes: 0GitHub stars: 666
- Create Control ManifestGenerate the programmer control manifest from accepted ADRs, technical preferences, and engine rules.Votes: 0GitHub stars: 666
- Create ScriptGenerate an AI script with emotion cues and dialogue formatting using Gemini 2.0 Flash for short-form video content.Votes: 0GitHub stars: 666
- Critique Builtin ToolAudit and critique builtin MCP tool implementations in LibrAgent. Use when auditing existing builtin MCP server implementations for compliance, reviewing pull requests that add or modify builtin tools, validating tool implementations against the Tool Design Manifesto v2.1, or identifying potential issues before they reach production.Votes: 0GitHub stars: 666
- Crun Educational ComicGenerate multi-panel educational comics, science explanatory cartoon strips, infographic storyboards, concept illustration strips, and step-by-step teaching comics using Crun AI image models and automated panel stitching. Use whenever the user asks for an educational comic, science/tech concept comic, explanatory cartoon, teaching storyboard, multi-panel knowledge strip, infographic illustration, or wants to turn any topic, concept, historical event, physics/math problem, coding logic, or sto...Votes: 0GitHub stars: 666
- Cue统一入口和智能路由中心，自动识别用户意图并路由到相应技能。基于 Cue 产品设计，提供专业化的深度研究体验。Votes: 0GitHub stars: 666
- CursorReference system prompt and tool schemas for Cursor. Use when imitating, comparing, or analyzing Cursor's prompting style; designing prompts inspired by Cursor; or answering questions about how Cursor is prompted.Votes: 0GitHub stars: 666
- Cyber Terminal Schematic把文章主题、AI/技术概念、Agent 工作流、数据判断编译成「赛博终端示意图」风格生图提示词：纯黑底 + 单一霓虹绿荧光，八族终端原生图面（节点拓扑 / 条形排行 / 时序折线 / 矩阵网格 / 层级堆叠 / 时间轴 / 巨型指标 / 左右对照）任选一族作主视觉，可配置 HUD 边框（角落数据面板、图例、标尺、系统状态行），等宽字巨型标题，节点标签支持短中文，外加一层可调强度的 CRT 屏幕质感（横向扫描线、荧光颗粒、辉光溢出、屏幕弧度、刷新条、烧屏残影）。用户提到终端风、赛博终端、HUD、拓扑图、节点图、schematic、示意图海报、排行图、时序图、数据面板、扫描线、CRT、显像管、老屏幕质感、荧光屏、绿色终端，或要按这个风格批量产文章封面和插图时使用。封面锁 5:2 横板，插图锁 16:9。先判封面/插图 + 图面族 + HUD 预设 + 质感强度档，再编译单条确定性提示词。要蓝底白线的工程图纸、三视图、爆炸图、标题栏那一套，用 engineering-blueprint-sheet，不用本 skill。Votes: 0GitHub stars: 666
- Daily Diegojcn Agent Skill PackDocumentation and capabilities reference for DailyVotes: 0GitHub stars: 666
- Daily Jantoniofc SkillsbankDocumentation and capabilities reference for DailyVotes: 0GitHub stars: 666
- Ddaigc对中文论文、摘要、课程作业、开题报告、实验报告、技术文档进行多轮降 AIGC / 去 AI 味改写。用户提到降AIGC、去AI味、降低AI痕迹、人性化改写、减少模板感和机器味、按顺序逐轮改写同一篇中文论文或技术文档时，必须使用本 skill；尤其当用户强调保留术语、数据、引用、段落结构、编号结构，或要求基于 origin/ 与 finish/aigc_records.json 在多个对话中继续下一轮时，应优先触发。本 skill 严格按 1-2-3 顺序依次使用 prompts/ddaigc1.md、prompts/ddaigc2.md、prompts/ddaigc3.md，每次调用只执行一轮，不得把三轮合并执行。不要把本 skill 用于普通润色、摘要压缩、翻译、查重降重、自由重写、逻辑审稿，或仅运行 scripts/run_aigc_round.py dry-run 这类脚本检查任务。Votes: 0GitHub stars: 666
- DecideExplores a problem, its context, and possible solutions before someone makes a significant decision. Use when the user invokes /decide, is uncertain about a direction, has not yet evaluated their options, or wants help thinking through a problem. This skill covers the exploration phase. To record a decision that is ready for review, or that the team already adopted, use /log-decision.Votes: 0GitHub stars: 666
- Design PromptUse when crafting or improving prompts for large language models — including system prompts, user-facing instructions, evaluation prompts, RAG query templates, agent tool descriptions, or any text that instructs an LLM to perform a task. Trigger when prompt outputs are inconsistent, too long, off-format, or incorrect.Votes: 0GitHub stars: 666
- DevinReference system prompt and tool schemas for Devin AI. Use when imitating, comparing, or analyzing Devin AI's prompting style; designing prompts inspired by Devin AI; or answering questions about how Devin AI is prompted.Votes: 0GitHub stars: 666
- DiaReference system prompt and tool schemas for Dia. Use when imitating, comparing, or analyzing Dia's prompting style; designing prompts inspired by Dia; or answering questions about how Dia is prompted.Votes: 0GitHub stars: 666
- Dispatching Parallel Agents Byannurcahyo SkillsUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesVotes: 0GitHub stars: 666
- Dispatching Parallel Agents Jamditis Claude Skills JournaUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesVotes: 0GitHub stars: 666
- Distill Shield SkillDistill Shield：为个人移交资料包生成 Canary 与可选加固策略，提高未授权蒸馏成本；仅适用于有权处置的数据。Votes: 0GitHub stars: 666
- DivertRecoding-Decoding applied to conversation. Access the tails of your own token distribution by generating through explicit priming and diversion. Use when asked to 'divert', 'access the tails', 'show me position 300', 'give me the non-modal answer', 'surprise yourself', 'what would you say if you weren't being careful', or any request for outputs that escape default/conventional/expected generation. Also triggers on: 'RD', 'recoding-decoding', 'divert mode', 'kick the wagon out of the rut', 'w...Votes: 0GitHub stars: 666
- Do UpskillGenerate project-specific implementation skills at docs/maverick/skills/<topic>/SKILL.md by scanning the codebase. Pass a topic name to generate one topic; omit arguments to process every topic.Votes: 0GitHub stars: 666