AI & ML

khalilbenaz Skill

Design de systèmes human-in-the-loop pour agents IA avec approbation, correction et escalade. Se déclenche avec "human in the loop", "HITL", "approbation humaine", "validation humaine", "escalade agent", "agent supervisé", "intervention humaine", "approval workflow". Also triggers on "approval step for agent", "human review of agent output".

khalilbenaz Skill

Conception et modélisation de schémas de bases de données. Se déclenche avec "schéma base de données", "normalisation", "3NF", "database design", "modélisation relationnelle", "ERD. Also triggers on "design a database schema", "normalize my tables", "ER model".

khalilbenaz Skill

Conçoit des prompts avec raisonnement en chaîne pour des tâches complexes nécessitant de la logique multi-étapes. À utiliser pour analyse, résolution de problèmes, mathématiques, logique ou décisions complexes. Se déclenche aussi avec "chain of thought", "raisonnement étape par étape", "prompt logique", "tâche complexe", "décomposer le raisonnement", ou toute tâche nécessitant un raisonnement structuré. Also triggers on "chain of thought prompt", "step-by-step reasoning prompt", "make the model reason".

khalilbenaz Skill

Automatisation de navigateur via Playwright MCP — naviguer, cliquer, remplir des formulaires, prendre des captures d'écran et déboguer des pages web. À utiliser quand l'utilisateur veut interagir avec un navigateur, tester une interface ou automatiser des actions web. Se déclenche aussi avec "ouvre cette page", "teste le formulaire", "automatise le navigateur", "capture d'écran de la page", "remplis le formulaire". Also triggers on "Playwright automation", "automate a browser", "fill a form automatically".

khalilbenaz Skill

Automatisation de navigateur via Playwright MCP — naviguer, cliquer, remplir des formulaires, prendre des captures d'écran et déboguer des pages web. À utiliser quand l'utilisateur veut interagir avec un navigateur, tester une interface ou automatiser des actions web. Se déclenche aussi avec "ouvre cette page", "teste le formulaire", "automatise le navigateur", "capture d'écran de la page", "remplis le formulaire". Also triggers on "Playwright automation", "automate a browser", "fill a form automatically".

khalilbenaz Skill

Construction d'extensions et skills pour Claude Code — slash commands, hooks, intégration MCP et commandes personnalisées. Se déclenche avec "extension Claude Code", "skill Claude", "slash command", "Claude Code plugin", "custom command Claude". Also triggers on "build a Claude Code plugin", "custom slash command", "Claude Code hooks".

khalilbenaz Skill

Construction d'extensions et skills pour Claude Code — slash commands, hooks, intégration MCP et commandes personnalisées. Se déclenche avec "extension Claude Code", "skill Claude", "slash command", "Claude Code plugin", "custom command Claude". Also triggers on "build a Claude Code plugin", "custom slash command", "Claude Code hooks".

majiayu000 Bundle

Expert in Apache Ray distributed computing. Use when converting Python code to Ray workloads, debugging Ray applications, optimizing Ray performance, or working with Ray Core, Ray Data, Ray Train, Ray Serve, or Ray Tune. Automatically fetches relevant documentation from Ray, HuggingFace, PyTorch, and other ML/distributed frameworks based on code context.

majiayu000 Bundle

Handle blocked destructive commands. Use when dcg blocks rm -rf, git reset --hard, DROP DATABASE, kubectl delete, or when configuring agent safety guardrails.

majiayu000 Bundle

Cross Agent Session Resumer. Convert and resume sessions across Claude Code, Codex, Gemini, and other providers. Use when switching AI agent providers mid-session or migrating an active chat history to a new tool.

majiayu000 Bundle

Comprehensive guide for building AI agents using Google's Agent Development Kit (ADK). Use when building agentic systems, orchestrating multi-agent workflows, creating AI assistants with custom tools, implementing LLM-powered applications, or working with Google Gemini models. Covers agent types (LlmAgent, SequentialAgent, ParallelAgent, LoopAgent), tool integration (FunctionTool, built-in tools, MCP), session management, deployment strategies, and multi-agent coordination patterns.

majiayu000 Bundle

Installs and configures ktx, the open-source context layer for data agents — runs ktx setup non-interactively with hidden CLI flags, configures database connections and embeddings, installs agent integration, and verifies readiness. Use when the user asks an agent to add ktx to a project, connect data sources, install agent rules, ingest schema, or troubleshoot a local ktx install.

majiayu000 Bundle

Create a new skill via GitHub search, LLM generation, or both.

majiayu000 Bundle

Central authority for Claude Code permissions. Covers permission system (tiered model, read-only, bash, file modification), permission rules (allow, ask, deny), rule precedence, permission modes (default, acceptEdits, plan, bypassPermissions), tool-specific permission rules (Bash patterns, Read/Edit patterns, WebFetch domains, MCP tools), /permissions command, and additionalDirectories. Assists with configuring permission rules, understanding permission modes, and troubleshooting permission issues. Delegates 100% to docs-management skill for official documentation.

majiayu000 Bundle

Meta-skill for improving and optimizing prompts using Anthropic's prompt engineering best practices. Provides the 4-step improvement workflow (example identification, initial draft, chain of thought refinement, example enhancement), keyword registries for documentation lookup, and decision trees for improvement strategies. Use when improving prompts, optimizing for accuracy, adding chain of thought reasoning, structuring with XML tags, enhancing examples, or iterating on prompt quality. Delegates to docs-management skill for official prompt engineering documentation.

majiayu000 Bundle

Manage coordinator daemon tasks, approve/reject work, monitor autonomous agents. Use when user asks to delegate tasks, check task status, review agent work, manage the coordinator, or use GitHub-driven approval workflow.

majiayu000 Bundle

Apply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification. Use when complex questions require fact-checking, technical accuracy, or multi-step reasoning.

majiayu000 Bundle

Implement speech-to-text (ASR/automatic speech recognition) capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to transcribe audio files, convert speech to text, build voice input features, or process audio recordings. Supports base64 encoded audio files and returns accurate text transcriptions.

majiayu000 Bundle

Lisa - intelligent assistant for memory and tasks. Triggers on 'lisa', 'hey lisa', or addressing lisa directly.

majiayu000 Bundle

Mine past agent sessions for working prompts, decisions, and patterns. Use when "what did I ask?", "find that prompt", session archaeology, or agent history.

majiayu000 Bundle

Agent with selective Gemini safety settings for specific categories

majiayu000 Bundle

This sop guides you through the process of transforming a rough idea into a detailed design document with an implementation plan and todo list. It follows the Prompt-Driven Development methodology to systematically refine your idea, conduct necessary research, create a comprehensive design, and develop an actionable implementation plan. The process is designed to be iterative, allowing movement between requirements clarification and research as needed.

majiayu000 Bundle

Use when working with AI agent protocols, standards, and interoperability specifications. Covers MCP, A2A, ACP, Agent Skills, AGENTS.md, ADL, x402, AP2, MCP Apps, and cagent. USE FOR: agent protocol selection, comparing MCP vs A2A vs ACP, understanding agent standards ecosystem, choosing payment protocols DO NOT USE FOR: specific protocol implementation details (use the sub-skills: mcp, a2a, acp, x402, etc.)

majiayu000 Bundle

Multi-Agent Planner Skill

majiayu000 Bundle

Add a persistent wiki knowledge base to a NanoClaw group. Based on Karpathy's LLM Wiki pattern. Triggers on "add wiki", "wiki", "knowledge base", "llm wiki", "karpathy wiki".

majiayu000 Bundle

High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

majiayu000 Bundle

Validation agent that validates plan tech choices against current best practices

majiayu000 Bundle

Run a multi-agent review of changed files for reuse, quality, efficiency, and clarity issues followed by automated fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review efficiency", "simplify changes", "clean up code", "refactor changes", or "run simplify".

majiayu000 Bundle

Structure Python so LLMs can understand it in 50 lines.

majiayu000 Bundle

Guide creating Claude Code hooks with security-first design. Use for validation, logging, and policy enforcement.

majiayu000 Bundle

Unified Python interface to 40+ bioinformatics services. Use when querying multiple databases (UniProt, KEGG, ChEMBL, Reactome) in a single workflow with consistent API. Best for cross-database analysis, ID mapping across services. For quick single-database lookups use gget; for sequence/file manipulation use biopython.

majiayu000 Bundle

描述：生成全面的市场研究报告（50 页以上），风格参考顶级咨询公司（如 McKinsey、BCG、Gartner）。具备专业的 LaTeX 排版、大量基于科学示意图和图像生成的可视化内容、与 research-lookup 深度集成以进行数据收集，以及多框架战略分析能力，包括波特五力模型（Porter’s Five Forces）、PESTLE 分析、SWOT 分析、TAM/SAM/SOM 市场规模分析和 BCG 矩阵。

qhjqhj00 Skill

financial-llm-zero-shot-eval

qhjqhj00 Skill

llm-trustworthiness-benchmark-eval

qhjqhj00 Skill

Fletcher: Own All the Numbers

qhjqhj00 Skill

Referee 2: Systematic Audit & Replication Protocol