AI & ML

jr2804 Bundle

MCP server integration for vstash document memory. Use when configuring Claude Desktop or other MCP-compatible AI assistants with persistent document memory, setting up vstash MCP tools for semantic search and Q&A, or integrating vstash with AI assistant workflows via Model Context Protocol.

jr2804 Bundle

ITU-T patent policy, IPR disclosure, and licensing declarations for standardization contributors. Covers the Common Patent Policy for ITU-T/ITU-R/ISO/IEC (2022), the three licensing options (RF, RAND, refusal), Patent Statement and Licensing Declaration Forms (individual and general), disclosure obligations at meetings and after approval, the ITU Patent Information database, cover sheet notification text, and ITU neutrality principles. Use when the agent needs to understand patent disclosure requirements, fill in declaration forms, add patent notices to Recommendation drafts, or handle SEP-related procedures during ITU-T standards development.

jr2804 Skill

Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.

jr2804 Bundle

MCP server integration for CytoScnPy code metrics analysis. Use when configuring CytoScnPy MCP server for AI assistants (Claude, Cursor, Copilot), setting up VS Code extension integration, or exposing code quality tools via MCP. Triggers on: mcp-cytosnpy, cytoscnpy mcp-server, MCP server setup, AI assistant code analysis integration, VS Code extension configuration.

tachyon-beep Bundle

Use when training, debugging, or selecting a deep-RL algorithm — value-based (DQN/Rainbow/BBF), policy-gradient (PPO/GRPO), actor-critic (SAC/TD3/REDQ), model-based (DreamerV3/TD-MPC2), offline (CQL/IQL/Decision Transformer), multi-agent (MAPPO/IPPO), exploration, reward shaping, or counterfactual credit assignment. Routes to the matching specialist sheet by problem type and algorithm family.

tachyon-beep Bundle

Use when creating, analyzing, repairing, or iterating a game concept, mechanic, ruleset, core loop, session arc, economy, balance model, prototype, or playtest; translating a desired kind of fun, learning outcome, or player experience into tangible mechanics; diagnosing locally interesting ideas that combine into a globally boring game; or challenging design assumptions with player behavior and evidence. Covers digital games, board and card games, tabletop roleplaying, LARP and live/embodied play, physical and social games, educational and training games, asynchronous games, and hybrids. Routes to 15 specialist reference sheets. For emergence-forward systemic design use /systems-as-experience; for in-engine simulation implementation use /simulation-tactics; for game UI use /ux-designer.

moonpay Skill

Set up MoonPay as an MCP server for Claude Desktop or Claude Code. Provides all MoonPay CLI tools via the Model Context Protocol.

buzzbysolcex Bundle

Smart LLM routing for cost optimization. Routes tasks to the cheapest capable model: free models (OpenRouter Llama 70B, AkashML Qwen 30B) for simple tasks like token scanning and data fetching, MiniMax M2.5 for complex reasoning, scoring, and outreach drafting.

buzzbysolcex Skill

On-chain verified trading signals for Buzz BD Agent. Publish scan results with TX hash proof for credibility. Source: https://github.com/BankrBot/openclaw-skills/tree/main/bankr/bankr-signals NOTE: Replace this placeholder with actual skill from BankrBot repo.

buzzbysolcex Skill

4-layer token data validation cascade for Buzz BD Agent. Ensures every piece of data touching a business decision is verified by 2+ independent sources. DexScreener primary, with Helius, Bankr, and GeckoTerminal as fallbacks. Valid data = long-term business.

buzzbysolcex Skill

Crypto-native security scanner for Claude Code agent configurations. Scans for exposed private keys, insecure RPC endpoints, contract addresses in public repos, unprotected wallet operations, and agent config vulnerabilities. Extends AgentShield concept with 47 crypto-specific detection rules. Run via /security-scan command.

buzzbysolcex Skill

Score any crypto token using Buzz's 11-rule scoring engine. Zero LLM cost — pure rule-based analysis across liquidity, volume, security, deployer identity, and market dynamics. Pulls from DexScreener API + on-chain data. Returns 0-100 score with COLD/WARM/HOT classification and actionable breakdown.

damilola-elegbede-org Bundle

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

damilola-elegbede-org Skill

Build any deliverable to a stated quality bar by fanning out a builder sub-agent per aspect, looping each through a fresh harsh critic against a rubric derived from a required concrete reference, then gating completion on a final unanimous blind side-by-side panel that must prefer the build. Use when D explicitly invokes it, or says "gauntlet this", "don't stop until it's perfect, blind-compare it against [X]", or hands over a build with an explicit, comparable quality bar and asks for AAA-level rigor. Requires the Workflow tool.

jr2804 Skill

Skill family for agent-assisted software development workflows. Includes workspace isolation (git-worktrees), parallel debugging (dispatching-parallel-agents), structured multi-task development (subagent-driven-development), and lightweight code review (requesting-code-review). Install individual skills based on workflow needs.

jr2804 Bundle

Review existing skills and suggest improvements. Use when asked to review, audit, or improve a skill — validates against Agent Skills spec and best practices. Also triggers when drafting or creating a new skill. Run `uvx skills-ref validate` to check spec compliance.

jr2804 Bundle

Bootstrap and maintain an agent-based document drafting project for any SDO. Use when starting a new standards contribution, setting up project structure (PLAN.md, AGENTS.md, directory layout), syncing metadata between PLAN.md and .docx properties, or detecting whether a project is new vs. ongoing. Provides common project infrastructure; SDO-specific templates and header structures live in the per-SDO drafting skill.

jr2804 Bundle

ITU-T contribution and TDoc submission procedures, deadlines, liaison statement format, and IPR requirements. Use when the agent needs to understand how to submit, format, or process ITU-T contributions (C-series documents), TDocs (Temporary Documents), or liaison statements. Covers submission deadlines, translation rules, patent/copyright declarations, and electronic posting. Sources: Rec. ITU-T A.1 (09/2019) clause 3.

jr2804 Bundle

Language-agnostic behavioral guidelines to reduce common LLM coding mistakes. Use for ANY coding task (all languages) to avoid overcomplication, make surgical changes, surface assumptions before coding, and define verifiable success criteria. Applies behavioral rigor—separate from language-specific technical standards.

dyoshikawa Skill

Form an Agent Team of Implementer and Reviewer subagents to tackle the given task, looping implementation and review until the Reviewer reports zero high-or-above findings and no more than three mid findings.

khw1031 Bundle

Claude Code Agent를 생성합니다. 에이전트 생성, AGENT.md 작성, 새 에이전트 만들기 요청 시 활성화.

khw1031 Bundle

사용자 요구사항을 분석하여 Skill 또는 Agent 중 적절한 유형을 결정하고 생성을 위임합니다. 도구 만들기, 스킬 vs 에이전트, 어떤 걸 만들어야 할지, 도구 유형 선택 요청 시 활성화.

khw1031 Bundle

프로젝트 컨텍스트를 파악한 뒤 전문가 관점으로 코드 리뷰하고, 사용자 승인 후 Agent Team SPAWN으로 병렬 개선 작업을 수행합니다. 트리거: 코드리뷰, 코드 리뷰, code review, 리뷰해줘, 리팩토링, 코드검토, PR 리뷰, 변경사항 검토.

khw1031 Bundle

기능 구현을 5단계(Requirements → Design → Task → Implementation → Review) 워크플로우로 체계적으로 진행합니다. Agent Team 기반 병렬 구현을 지원합니다. 워크플로우, 기능 구현, 기능 개발, 작업 재개, TASK-ID 패턴, .ai/tasks 요청 시 활성화.

tachyon-beep Skill

Mandatory protocol for all SME (Subject Matter Expert) agents. Defines fact-finding requirements, output contracts, confidence/risk assessment, and qualification of advice.

tachyon-beep Bundle

Use when working on LLM applications — chat / instruct prompting, reasoning models (o-series / Claude extended thinking / DeepSeek-R1 / Gemini thinking / Qwen QwQ), agentic patterns + MCP, RAG, fine-tuning (SFT / DPO / IPO / KTO / SimPO / ORPO / GRPO + LoRA family), context engineering and prompt caching, inference optimization (vLLM / SGLang / TensorRT-LLM), evaluation (incl. LLM-as-judge bias controls and capability suites), or safety (OWASP LLM Top 10, 2025 + 2026 renumbering). Calibrated to 2026-05 with capability-tier vocabulary (frontier-reasoning / frontier-general / fast-cheap / on-device) instead of hardcoded model IDs. Routes to the right specialist sheet.

jr2804 Bundle

ITU-T Recommendation structure, approval processes, amendment/corrigendum procedures, and ITU-T | ISO/IEC common text conventions. Use when the agent needs to understand how ITU-T Recommendations are structured (clause order, element types, annex conventions), approved (TAP/AAP), amended, or how joint ITU-T/ISO/IEC texts work. Sources: Rec. ITU-T A.1 (09/2019) + Rules for presentation of ITU-T | ISO/IEC common text (2014).

jr2804 Skill

File system operations, process management, terminal interaction, and workspace exploration

jr2804 Skill

A detailed tool for dynamic and reflective problem-solving through thoughts that can adapt and evolve

dyoshikawa Skill

Run the `review-full-pr` skill on another model (github-copilot/gpt-5.4) via opencode, then thoroughly investigate and vet the resulting findings, and present only the valid ones to the user.

toilahuongg Skill

Guide for conducting thorough and synthesized research, focusing on verification, multi-source analysis, and RAG patterns.

toilahuongg Bundle

Guide for creating, configuring, and refining AI Agents. Use this skill when users want to define a new agent persona, generate a system prompt, or assemble a specific set of skills/workflows for a specialized agent (e.g., "Create a QA Agent" or "Design a Security Auditor Agent").

toilahuongg Bundle

Rigorous reasoning using philosophical theories and scientific methods. Use this skill when analyzing logic, evaluating arguments, constructing proofs, critiquing opinions, or solving complex problems requiring critical thinking. Triggers - debate, proof, critique, logical analysis, argument evaluation, fallacy detection, inference, argumentation, logical fallacy, critical thinking.

aztr0nutzs Bundle

Use ClawHub CLI to search, install, update, and publish agent skills from clawhub.ai with advanced caching and compression. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with optimized performance.

khw1031 Bundle

LLM 컨텍스트 윈도우를 효율적으로 사용하는 3단계 정보 로드 원칙. Skills, Agents, Prompts 작성 시 참조. SKILL.md, AGENT.md 작성, 프롬프트 설계, 컨텍스트 최적화 시 활성화.

khw1031 Bundle

AI 도구(Skill, Agent) 추가/변경 후 모든 README.md를 재귀적으로 업데이트하고 CHANGELOG에 반영합니다. update-ai-tools, README 업데이트, 도구 문서 갱신, 문서 동기화 요청 시 사용.