LLM & Agents

Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process: (1) create section outlines with key points using research-lookup, (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.

Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.

Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.

Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key.

Analyzes Claude Code usage patterns and provides comprehensive recommendations. Runs usage analysis, discovers GitHub community resources, suggests CLAUDE.md improvements, and fetches latest docs on-demand. Use when user wants to optimize their Claude Code workflow, create configurations (agents/skills/commands), or set up project documentation.

This skill should be used when the user asks to "use Metasploit for penetration testing", "exploit vulnerabilities with msfconsole", "create payloads with msfvenom", "perform post-exploitation", "use auxiliary modules for scanning", or "develop custom exploits". It provides comprehensive guidance for leveraging the Metasploit Framework in security assessments.

This skill should be used when the user asks to "test for SQL injection vulnerabilities", "perform SQLi attacks", "bypass authentication using SQL injection", "extract database information through injection", "detect SQL injection flaws", or "exploit database query vulnerabilities". It provides comprehensive techniques for identifying, exploiting, and understanding SQL injection attack vectors across different database systems.

This skill should be used when the user asks to "escalate privileges on Windows," "find Windows privesc vectors," "enumerate Windows for privilege escalation," "exploit Windows misconfigurations," or "perform post-exploitation privilege escalation." It provides comprehensive guidance for discovering and exploiting privilege escalation vulnerabilities in Windows environments.

This skill should be used when the user asks to "escalate privileges on Linux", "find privesc vectors on Linux systems", "exploit sudo misconfigurations", "abuse SUID binaries", "exploit cron jobs for root access", "enumerate Linux systems for privilege escalation", or "gain root access from low-privilege shell". It provides comprehensive techniques for identifying and exploiting privilege escalation paths on Linux systems.

Update template catalogs and UI prompts after adding new infographic templates (src/templates/*.ts), including SKILL.md template list, site gallery template mappings, and the AIPlayground prompt list.

Orchestrate OpenAI Codex CLI for parallel task execution. As orchestrator, analyze tasks, inject context, manage sessions, and coordinate parallel instances. Use when delegating coding tasks to Codex or running multi-agent workflows. (user)

This skill should be used when working with DSPy.rb, a Ruby framework for building type-safe, composable LLM applications. Use this when implementing predictable AI features, creating LLM signatures and modules, configuring language model providers (OpenAI, Anthropic, Gemini, Ollama), building agent systems with tools, optimizing prompts, or testing LLM-powered functionality in Ruby applications.

Expert guidance for creating, writing, building, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

This skill should be used when users need to generate detailed, structured prompts for creating UI/UX prototypes. Trigger when users request help with "create a prototype prompt", "design a mobile app", "generate UI specifications", or need comprehensive design documentation for web/mobile applications. Works with multiple design systems including WeChat Work, iOS Native, Material Design, and Ant Design Mobile.

Execute codeagent-wrapper for multi-backend AI code tasks. Supports Codex, Claude, and Gemini backends with file references (@syntax) and structured output.

This skill should be used when the user asks to "demonstrate skills", "show skill format", "create a skill template", or discusses skill development patterns. Provides a reference template for creating Claude Code plugin skills.

Consult official Claude Code documentation from docs.claude.com using selective fetching. Use this skill when working on Claude Code hooks, skills, subagents, MCP servers, or any Claude Code feature that requires referencing official documentation for accurate implementation. Fetches only the specific documentation needed rather than loading all docs upfront.

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dependencies, and rust-documentation skills.

Use RepoPrompt CLI for token-efficient codebase exploration

Analyze Claude Code sessions via Braintrust