All authors
Claude Skills by David-Li0406
github.com/David-Li04065,064 skills17 installs250 views
- Agent EvolutionMeta-skill for crystallizing tribal knowledge into systematic assets. Analyzes completed GUTTERS work to determine if new skills should be created or AGENTS.md updated. Use after complex tasks, module completions, or when patterns emerge.Votes: 0GitHub stars: 2
- Agent ExecutionAgent execution patterns including LLM calls and token handling. Use when implementing agent execution or multipart forms. Triggers: agent.Agent, VisionForm, ParseVisionForm, Token injection, constructAgent, ChatStream, VisionStream, multipart/form-data, base64, Provider.Options["token"], go-agents, ExecuteRequest, SetSecret, GetSecret. File patterns: internal/agents/*.goVotes: 0GitHub stars: 2
- Agent FeatureAgent 페이지 구현 스킬. SSE 토큰 스트리밍, 사이드바, 마크다운 렌더링, 메시지 액션을 포함한 AI 챗봇 인터페이스 구현 시 사용. React 19 + TypeScript + TailwindCSS 기반.Votes: 0GitHub stars: 2
- Agent InboxFile-based inter-agent messaging. Check inbox, send bugs/requests to other projects, acknowledge resolved issues. Use for cross-project agent communication.Votes: 0GitHub stars: 2
- Agent Instruction MaintenanceReview, update, and synchronize agent instructions and configs across Codex and Claude (and optionally VS Code/Copilot); use when creating or refactoring agent prompts, skills, or chatmodes (trigger keywords: agent instructions, prompt review, skill update, chatmode, subagent).Votes: 0GitHub stars: 2
- Agent JournalSearch past AI agent sessions, stored knowledge, and indexed content. Use for finding previous work, recalling conventions, storing learnings, and indexing documentation.Votes: 0GitHub stars: 2
- Agent LensAgent Lens: Real-time observability dashboard for multi-agent Claude Code sessions. Visualize agent interactions, tool usage, and session flows through a modern dual-pane interface. Track parent-child event relationships with hierarchical timeline visualization, HITL approvals, and comprehensive metrics. **Key Features:** - 👁️ Dual-pane layout (process timeline + results/metrics) - 🌳 Span hierarchy visualization with parent-child relationships - 🔴 Real-time event streaming via WebSocket ...Votes: 0GitHub stars: 2
- Agent Mail 1Coordinate with other AI agents via project-local Maildir messaging. Use when operating in tandem mode with Claude, Gemini, or other agents. Enables claiming tasks, reporting completion, handling blocks, and synchronizing work across terminals.Votes: 0GitHub stars: 2
- Agent Mail GuideGuide for installing and using MCP Agent Mail across heterogeneous agent tools/VMs.Votes: 0GitHub stars: 2
- Agent Memory 3Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check your notes', 'clean up memories'. Also use proactively when discovering valuable findings worth preserving.Votes: 0GitHub stars: 2
- Agent Memory 6Save and restore working memory across conversations. Triggers: "remember", "save this", "recall", "continue from last time". Store research findings, decisions, problem solutions, and work state.Votes: 0GitHub stars: 2
- Agent Memory SkillsSelf-improving agent architecture using ChromaDB for continuous learning, self-evaluation, and improvement storage. Agents maintain separate memory collections for learned patterns, performance metrics, and self-assessments without modifying their static .md configuration.Votes: 0GitHub stars: 2
- Agent Navigation SopGenerate AGENTS.md for AI agent navigation. Covers build/test commands, coding conventions, task routing, and codebase structure. Use for /init workflow or when creating agent-readable repository documentation. Examples: - user: "/init" → full AI navigation AGENTS.md + skill recommendations - user: "/init basic" → minimal AGENTS.md structure only - user: "Create AGENTS.md for this repo" → assess complexity, generate navigation doc - user: "Document codebase for AI agents" → structured AGENTS...Votes: 0GitHub stars: 2
- Agent ObservabilitySelf-report agent issues by logging user corrections for later review. Use when a user says "don’t do that", "stop doing X", "always do Y", or requests self-correction.Votes: 0GitHub stars: 2
- Agent Ops Code Review ComprehensiveA senior code-review agent that produces critical, thorough, constructive, and evidence-based reviews. Works as a sub-agent or through direct invocation. ---Votes: 0GitHub stars: 2
- Agent Ops Git WorktreeManage git worktrees for isolated development. Create, list, remove, and work in worktrees.Votes: 0GitHub stars: 2
- Agent OptimizationAnalyze and improve the AI agent workforce system, ensuring compatibility across environments (CLI, IDE, GitHub) and leveraging emerging technologies.Votes: 0GitHub stars: 2
- Agent Orchestration 1Agent orchestration protocol and coordination patternsVotes: 0GitHub stars: 2
- Agent Orchestration Improve AgentSystematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.Votes: 0GitHub stars: 2
- Agent Orchestration Multi Agent OptimizeUse when working with agent orchestration multi agent optimizeVotes: 0GitHub stars: 2
- Agent PlatformsGuide for multi-platform skill compatibility across Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, and other AI coding agents.Votes: 0GitHub stars: 2
- Agent ReadyScan repositories for AI agent readiness using the Factory.ai 9 Pillars / 5 Levels model. Use this skill when users ask to check repository maturity, agent readiness, evaluate codebase quality for AI agents, or run agent-ready scans. Triggers on phrases like "check agent readiness", "scan for readiness", "evaluate repo maturity", "how ready is this repo for AI agents", or "/agent-ready".Votes: 0GitHub stars: 2
- Agent Recorder FixturesRecord real OpenAI/Anthropic HTTP back-and-forth (requests + responses, including streaming text/event-stream) and print paste-ready Swift fixtures for SwiftAgent unit tests (ReplayHTTPClient) using the AgentRecorder CLI or HTTPReplayRecorder. Use when adding/updating any provider adapter tests (text, streaming, structured outputs, tool calls), when payload formats change, or when debugging agent loop mismatches by inspecting recorded JSON/SSE payloads.Votes: 0GitHub stars: 2
- Agent ScaffolderUse when user says 'agent を作りたい', 'create agent', 'scaffold agent', '新しい agent', 'agent 作成', or discusses creating a new climpt agent. Generates .agent/{name}/ directory with all required files including agent.json, steps_registry.json, schemas, and prompts.Votes: 0GitHub stars: 2
- Agent Sdk DevA comprehensive plugin for creating and verifying Claude Agent SDK applications in Python and TypeScript.Votes: 0GitHub stars: 2
- Agent SdkGuide for Claude Agent SDK - build custom AI agents powered by Claude. Covers installation, authentication providers, tool permissions, file-based configuration, TypeScript/Python code examples, and project scaffolding templates.Votes: 0GitHub stars: 2
- ClaudeExample skill that triggers on specific keywords.Votes: 0GitHub stars: 2
- Agent SelectAnalyze tasks and recommend optimal sub-agent(s) for executionVotes: 0GitHub stars: 2
- Agent Skill WritingGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends an agent's capabilities with specialized knowledge, workflows, or tool integrations.Votes: 0GitHub stars: 2
- Agent Skills 2Author and improve Agent Skills following the agentskills.io specification. Use when creating new SKILL.md files, modifying existing skills, reviewing skill quality, or organizing skill directories with proper naming, descriptions, and progressive disclosure.Votes: 0GitHub stars: 2
- Agent Skills 3Learn about Agent Skills - how AI agents use skills, create new skills, and understand skill discovery in real-time. Use when user asks about skills, wants to create a skill, or wants to understand how Claude uses skills.Votes: 0GitHub stars: 2
- TemplatesWHAT_IT_DOES. Use when TRIGGER_PHRASES. Handles CAPABILITIES.Votes: 0GitHub stars: 2
- TemplatesGuides users through PROCESS interactively. Use when USER_INTENT.Votes: 0GitHub stars: 2
- TemplatesOrchestrates WORKFLOW by coordinating multiple sub-skills. Use when COMPREHENSIVE_TASK.Votes: 0GitHub stars: 2
- TemplatesAutomates WORKFLOW. Use when TRIGGERS. Handles STEPS_INVOLVED.Votes: 0GitHub stars: 2
- Agent Skills 4Manage and discover skills for AI coding assistants. Register skills, sync to CLIs, scan for candidates.Votes: 0GitHub stars: 2
- DocsThis guide explains how to enable AI coding agents (Codex CLI, Claude Code, Cursor, etc.) to view and interact with local/LAN web pages they normally cannot access.Votes: 0GitHub stars: 2
- Agent Skills ArchitectureFoundational "High-Density" standard for token-optimized agent instructions and CLI-based automated activation.Votes: 0GitHub stars: 2
- Agent Skills ExpertExpert for creating and managing Claude Code Agent Skills. Create skills with git submodule + sparse-checkout for source references, write SKILL.md with proper frontmatter, and follow best practices. Use when creating new skills, adding source references to skills, or managing skill configurations.Votes: 0GitHub stars: 2
- Agent Stealth BrowserStealth 模式的浏览器自动化 MCP 工具，能够绕过反爬检测（如 Cloudflare、reCAPTCHA 等）。完全兼容 agent-browser API。当需要操作有反爬保护的网站时使用此工具，包括：(1) 访问受保护页面 (2) 自动登录需要验证的网站 (3) 表单填写和提交 (4) 截图和数据提取 (5) 持久化登录状态Votes: 0GitHub stars: 2
- Agent Studio ChatWork on Agent Studio chat (UI + streaming) and the /api/chat route. Use for tasks like message rendering, reasoning display, editing/regenerate, Zustand chat stores, model/settings UI, and OpenRouter or Vercel AI SDK integration. 聊天功能开发/排障：流式输出、Reasoning 展示、消息编辑与重新生成、模型与参数设置。Votes: 0GitHub stars: 2
- Agent Studio PlaygroundWork on Game Playground (frontend /playground and backend game API). Use for adding/debugging games, render modes (scene vs frame), session lifecycle, controls/keyboard, and backend environments (Gymnasium, Snake, Tetris). 游戏游乐场开发：新增/排查游戏、前后端协议、渲染模式(scene/frame)、会话管理、键盘与控制面板。Votes: 0GitHub stars: 2
- Agent StudioDevelop, run, and debug the AGENT-Studio repo (Next.js frontend + FastAPI backend). Use for repo onboarding, starting/stopping services (restart.sh, ports 3115/8000), env vars, logs, and common dev workflows. 本仓库开发/排障：启动前后端、端口/日志、环境变量、lint/build、定位关键目录。Votes: 0GitHub stars: 2
- Agent Survey CorpusDownload a small corpus of open-access arXiv survey/review PDFs about LLM agents and extract text for style learning. **Trigger**: agent survey corpus, ref corpus, download surveys, 学习综述写法, 下载 survey. **Use when**: you want to study how real agent surveys structure sections (6–8 H2), size subsections, and write evidence-backed comparisons. **Skip if**: you cannot download PDFs (no network) or you don't want local PDF files. **Network**: required. **Guardrail**: only download arXiv PDFs; store...Votes: 0GitHub stars: 2
- Agent TemplateCreate new GitHub Copilot agents with proper structure and frontmatter. Use when asked to create a skill, make a new agent, or scaffold agent files.Votes: 0GitHub stars: 2
- Agent Workflow 1Design principles for multi-agent workflows with validation gates using the Ralph Wiggum technique. Use when orchestrating multiple AI agents (Opus/Sonnet/Gemini/Codex) for complex autonomous development tasks with skill stacking, extended thinking, and iterative improvement loops.Votes: 0GitHub stars: 2
- Agent WorkflowsCore Kyora Agent OS workflows for task routing, delegation, handoffs, and recovery. Use when: routing a new task through the OS, delegating work between agents, creating handoff packets at phase boundaries, recovering/resuming work in a new session. Keywords: route, delegate, handoff, packet, recovery, resume, continue, task, phase.Votes: 0GitHub stars: 2
- AgentShow information about the connected Vocal Bridge voice agent including name, mode, phone number, and deployment status.Votes: 0GitHub stars: 2
- Agentdb Advanced FeaturesMaster advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.Votes: 0GitHub stars: 2
- Agentdb Performance OptimizationOptimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors.Votes: 0GitHub stars: 2