Total 51,202 skills
Showing 12 of 51202 skills
创建结构正确、支持 progressive disclosure 并带 bundled resources 的新 agent skills。Use when user wants to create, write, or build a new skill.
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.
Use when adding Auth0 authentication to an iOS, macOS, tvOS, watchOS, or visionOS application — integrates the Auth0.swift SDK for native Apple platform authentication using Web Auth, CredentialsManager, and biometric protection.
Harness Engineering Phase 3: Establish cross-session state management to solve the problem of agents forgetting previous conversations. Create three files: tasks.json (task list), progress.md (progress record), and init.sh (environment initialization script). Use this skill immediately when the user says phrases like "establish task management", "make agent remember progress", "create tasks.json", "maintain state across sessions", "agent doesn't remember what was done last time", "create progress file", or "initialize state management". Prerequisites: harness-step1 and harness-step2 have been completed (the project has AGENTS.md and docs/ knowledge base).
A valid skill used for testing frontmatter validation. Do NOT use for production workflows.
Generate 10 YouTube title options from a topic description, then a keyword-optimized description for the chosen title
Draft and fill NVCA model documents — stock purchase agreement, certificate of incorporation, investors rights agreement, voting agreement, ROFR, co-sale, indemnification, management rights letter. Series A and venture financing templates. Produces signable DOCX files.
Track data lineage and provenance from source to consumption. Use when auditing data flows, debugging data quality issues, ensuring compliance (GDPR, SOX), or understanding data dependencies. Covers lineage tracking, impact analysis, data catalogs, and metadata management.
React to a message with an emoji. Works on Telegram, Discord, and Feishu.
SOLID principles for Ruby 3.3+ and Rails 8. Files < 100 lines, contracts separated, modular architecture. Modules MANDATORY.
Skill for Tauri 2.0 and Rust backend development in LocalCowork. Use when working on the Rust backend, Tauri IPC commands, frontend-backend communication, Tauri permissions/capabilities, the application shell, or the Agent Core modules (ConversationManager, ToolRouter, MCP Client, Inference Client, ContextWindowManager). MANDATORY TRIGGERS: "Tauri", "Rust backend", "IPC command", "tauri.conf.json", "Cargo.toml", "capabilities", "agent core", "tool router", "conversation manager", "inference client", "MCP client", "context window", or anything related to the desktop application shell or the Rust-side orchestration layer.
Prompt engineering and optimization for AI/LLMs. Capabilities: transform unclear prompts, reduce token usage, improve structure, add constraints, optimize for specific models, backward-compatible rewrites. Actions: improve, enhance, optimize, refactor, compress prompts. Keywords: prompt engineering, prompt optimization, token efficiency, LLM prompt, AI prompt, clarity, structure, system prompt, user prompt, few-shot, chain-of-thought, instruction tuning, prompt compression, token reduction, prompt rewrite, semantic preservation. Use when: improving unclear prompts, reducing token consumption, optimizing LLM outputs, restructuring verbose requests, creating system prompts, enhancing prompt clarity.