1. 2065Agent Orchestratorhuytran1120/vietnam-agentic-skillsMeta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management.9
  2. 2066Agentfoliohuytran1120/vietnam-agentic-skillsSkill for discovering and researching autonomous AI agents, tools, and ecosystems using the AgentFolio directory.9
  3. 2067Agentic Actions Auditorhuytran1120/vietnam-agentic-skillsAudits 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.9
  4. 2068AI Agent Developmenthuytran1120/vietnam-agentic-skillsAI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents.9
  5. 2069AI Analyzerhuytran1120/vietnam-agentic-skillsAI驱动的综合健康分析系统,整合多维度健康数据、识别异常模式、整理风险因素、提供一般性健康信息。支持智能问答和AI健康报告生成。9
  6. 2070AI Mlhuytran1120/vietnam-agentic-skillsAI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.9
  7. 2071AI Native CLIhuytran1120/vietnam-agentic-skillsDesign spec with 98 rules for building CLI tools that AI agents can safely use. Covers structured JSON output, error handling, input contracts, safety guardrails, exit codes, and agent self-description.9
  8. 2072AI SEOhuytran1120/vietnam-agentic-skillsOptimize content for AI search and LLM citations across AI Overviews, ChatGPT, Perplexity, Claude, Gemini, and similar systems. Use when improving AI visibility, answer engine optimization, or citation readiness.9
  9. 2073AI Studio Imagehuytran1120/vietnam-agentic-skillsGeracao de imagens humanizadas via Google AI Studio (Gemini). Fotos realistas estilo influencer ou educacional com iluminacao natural e imperfeicoes sutis.9
  10. 2074Akf Trust Metadatahuytran1120/vietnam-agentic-skillsThe AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing.9
  11. 2075App Builderhuytran1120/vietnam-agentic-skillsMain application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.9
  12. 2076Autonomous Agent Patternshuytran1120/vietnam-agentic-skillsDesign patterns for building autonomous coding agents, inspired by [Cline](https://github.com/cline/cline) and [OpenAI Codex](https://github.com/openai/codex).9
  13. 2077Frugal Subagentsikotelkin/claude-skillsOn Claude Fable 5.1 or Opus, subagents inherit the session's expensive model and can spawn more of themselves, so one research fan-out can burn the usage limit in minutes; this plugin's PreToolUse hook runs every subagent on a cheap model unless one is named explicitly, blocks nested spawns and caps spawns per session, and this skill says how to delegate well under those rules. Use whenever the session is about to delegate — spawning agents, running web scans or research passes in parallel, "fan out", "run a fleet of agents", "search across many sites", comparing listings/prices/flights/apartm3
  14. 2078Agent Teamsyasunori0418/skillsClaude Code の並列エージェント(agent teams・teammate)の後始末と無応答時の打ち切りルール。`name` を付けて Agent を起動するとき、TeamCreate でチームを組むとき、teammate から `idle_notification` が届いたとき、評価ループ等で次のイテレーションのエージェントを起動する前、エージェントの返信が届かないときに参照する。`name` を付けない通常のサブエージェント起動だけなら対象外。9
  15. 2079Project Sessionyasunori0418/skills指定したプロジェクト(ghq 管理下の部分一致キー、または直接パス)のディレクトリでブランチを変えずに claude を detached セッション(herdr 管理下なら workspace か専用 session、それ以外は tmux)として起動する。`/project-session` の明示実行専用。9
  16. 2080Response Formatyasunori0418/skillsファイル編集・コマンド実行・調査・複数ツール呼び出しを伴う作業の最終応答時に、指定の日本語Markdownテンプレ(タイトル/解釈の要約/対応内容/影響)で対応内容を報告する。複数ターンに分かれた作業の最終完了時、複数ファイル編集を含む実装完了時、調査・分析タスクの結果報告時、新規ファイル作成を伴う作業の完了時に必ず参照する。単発の質問への即答(ツール呼び出しなし、または1〜2回のRead/Bashのみ)は対象外。9
  17. 2081Session Insightsyasunori0418/skillsClaude Code の過去セッション(transcript JSONL)・設定・運用パターンを cclens と同梱スクリプトで収集し、指定された分析観点に沿って傾向分析と改善案を出す。/session-insights で明示起動されたときのみ使用する。キーワードマッチによる自動起動はしない。起動時に分析観点の指定が必須。9
  18. 2082AI Build Buy Partnertarunccet/pm-skillsEvaluate AI capability sourcing options across build, buy, fine-tune, and partner archetypes using a structured decision matrix. Use when deciding whether to build a custom model, use an LLM API, fine-tune a base model, or partner with an AI vendor.9
  19. 2083AI Data Strategytarunccet/pm-skillsDefine a data strategy for AI products covering training data requirements, data quality, labeling strategy, feedback loops, and continuous retraining. Use when assessing data readiness for an AI feature, designing a data flywheel, or planning an ML data pipeline.9
  20. 2084AI Feature Definitiontarunccet/pm-skillsWrite a complete AI feature specification that defines desired model behaviour, input/output examples, confidence thresholds, fallback logic, and non-functional requirements. Use when defining requirements for an AI-powered feature, writing an AI PRD, or bridging the gap between PM intent and ML team implementation.9
  21. 2085AI Incident Responsetarunccet/pm-skillsHandle AI model failures, quality regressions, bias incidents, and safety issues with a structured response runbook. Use when an AI feature produces harmful outputs, when model quality degrades in production, or when preparing an incident response plan for an AI system.9
  22. 2086AI Model Evaluationtarunccet/pm-skillsEvaluate and compare LLMs, ML APIs, and fine-tuned models for product fit across quality, latency, cost, compliance, and vendor risk dimensions. Use when selecting an AI model or vendor, comparing foundation model options, or making build-vs-API decisions for a product use case.9
  23. 2087AI Test Workflow Toolboxruhedanghaoyigexuesheng/claude-skills-portfolioAI 测试工作流工具箱:整合 Bug 分析、日志排查、SQL 分析、回归测试、Prompt 测试五类助手,含统一入口、风险等级与人工复核规则,支持多助手联动实战。当用户提及 AI 测试工具箱、测试工作流工具箱、Bug+日志+SQL 联动分析、综合测试助手时使用。5
  24. 2088AI User Researchtarunccet/pm-skillsResearch user expectations, mental models, trust calibration, and interaction patterns for AI-powered features. Use when planning user research for an AI feature, evaluating user trust and satisfaction with AI outputs, or designing feedback collection for a machine learning system.9
  25. 2089Cf Promptecorkran/context-forgeGet or list Context Forge prompt templates. Use when the user asks for a cf prompt by phase name or wants the list of available prompts.5
  26. 2090Learn AI Pmtarunccet/pm-skillsInteractive Socratic learning module on AI product management: model evaluation, responsible AI, prompt engineering, AI metrics, and managing AI features in production.9
  27. 2091Monetization Modelstarunccet/pm-skillsBrainstorm 3-5 monetization strategies with audience fit, risks, and validation experiments. Use when exploring revenue models, evaluating pricing strategies, or deciding how to monetize a product.9
  28. 2092Proactive Agentwangyendt/wayne-skills让 AI 助手从「等待任务」变成「主动预见」的架构设计。包含 WAL 协议、Working Buffer、自动定时任务等经过实战验证的模式。9
  29. 2093Product Metricstarunccet/pm-skillsDefine a complete product metrics framework: North Star metric selection, input metrics, dashboard design, alert thresholds, and — for AI products — a four-layer AI metrics stack (model quality, operational, product-level, business). Use when setting up metrics for a new product, choosing a North Star, designing a dashboard, or defining KPIs for an AI feature.9
  30. 2094Prompt Engineeringtarunccet/pm-skillsCraft, evaluate, and manage production-quality prompts including system prompts, few-shot examples, chain-of-thought instructions, and guardrails. Use when designing prompts for a product feature, improving output quality, reducing hallucinations, or building a prompt versioning strategy.9
  31. 2095Prompt Test Workflowruhedanghaoyigexuesheng/claude-skills-portfolioPrompt 测试工作流:对用例生成、Bug 分析等 Prompt 执行稳定性、边界、错误输入、多轮一致性与幻觉风险验证,输出结构化测试报告。当用户提及 Prompt 测试、Prompt 质量验证、测试工作流设计、Prompt 稳定性、幻觉测试时使用。5
  32. 2096Prototype Plantarunccet/pm-skillsPlan an AI-assisted prototyping session: scope the MVP, pick the right AI coding tool, define the build sequence, and estimate effort for a solo PM-builder.9
  33. 2097Pywayne CV Camera Modelwangyendt/wayne-skillsCamera model wrapper for camera_models C++ library via pybind11. Use when working with pywayne.cv.camera_model module to load camera models from YAML configuration files, access camera properties (model type, image size, parameters), perform projection operations (lift_projective, space_to_plane), and export camera parameters as dictionaries.9
  34. 2098Pywayne LLM Chat Botwangyendt/wayne-skillsLLM chat interface using OpenAI-compatible APIs with streaming support and session management. Use when working with pywayne.llm.chat_bot module for creating LLM chat instances with custom configuration, managing multi-turn conversations with history, handling streaming responses, or managing multiple chat sessions with ChatManager9
  35. 2099Pywayne LLM Chat Ollama Gradiowangyendt/wayne-skillsGradio-based chat interface for Ollama with multi-session management. Use when working with pywayne.llm.chat_ollama_gradio module to create a web-based chat UI that connects to Ollama models, supports multiple chat sessions, model selection, and streaming responses. Integrates with ChatManager for session management.9
  36. 2100Pywayne LLM Chat Windowwangyendt/wayne-skillsPyQt5-based GUI chat window for LLM conversations with streaming responses and stop functionality. Use when working with pywayne.llm.chat_window module to create desktop chat applications with customizable window configuration, system message management, and real-time streaming display.9
  37. 2101Responsible AItarunccet/pm-skillsAssess an AI feature or product for ethical risks, bias, safety issues, fairness gaps, and regulatory compliance. Use when reviewing an AI feature before launch, conducting a responsible AI audit, or responding to a bias or safety concern.9
  38. 2102User Segmentationtarunccet/pm-skillsUnified segmentation skill with three modes: market segmentation (identify 3-5 opportunity segments with JTBD and fit analysis), user segmentation (cluster existing users from feedback data by behavior and needs), or beachhead selection (evaluate candidate segments against burning pain, WTP, winnability, and referral potential to pick the best launch segment). Use when exploring market opportunities, building a segmentation model from user data, or choosing where to focus first.9
  39. 2103A4ahuytran1120/vietnam-agentic-skillsConnect your AI agent to the A4A end-to-end encrypted agent-to-agent messaging network via local MCP tools or Python SDK.9
  40. 2104Aas Compose Stackhuytran1120/vietnam-agentic-skillsPreserve the coding agent's explicit AAS skill selection as a validated stack and optional evidence.9
  41. 2105Advanced Evaluationhuytran1120/vietnam-agentic-skillsDesign LLM-as-judge rubrics, direct scores and pairwise comparisons. Use for judge models, evals, position bias and calibration against human labels.9
  42. 2106Aegisops AIhuytran1120/vietnam-agentic-skillsAutonomous DevSecOps & FinOps Guardrails. Guide to reviewing Linux kernel patches, Terraform cost changes and Kubernetes policy with a separately reviewed upstream tool and configured model.9
  43. 2107Agent Creatorhuytran1120/vietnam-agentic-skillsCreate custom AI subagents with proper plugin structure, persona generation, and companion routing skills.9
  44. 2108Agent Evalshuytran1120/vietnam-agentic-skillsBuild automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates. Use when shipping agent features, validating prompt changes, or gating deployments on quality.9
  45. 2109Agent Evaluationhuytran1120/vietnam-agentic-skillsEvaluate agent behavior with versioned cases and explicit verifiers. Use when comparing agent or prompt changes, reproducing failures, or running agent regression tests.9
  46. 2110Agent Evaluation Reportinghuytran1120/vietnam-agentic-skillsUse when summarizing agent evaluations where autonomous, assisted, failed, timed-out, or invalid outcomes must remain distinct and comparable.9
  47. 2111Agent Harness Fault Injectionhuytran1120/vietnam-agentic-skillsUse when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.9
  48. 2112Agent Manager Skillhuytran1120/vietnam-agentic-skillsManage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) in an explicitly authorized workspace.9