发现 tools llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
Produce natural, high-quality human-like text. Avoids common AI markers (repetitive patterns, fluff words, false neutrality) in favor of specificity, directness, and genuine voice. Use this skill when the user...
Guide for adding AI presenter avatars to demos using HeyGen. Use when you want to make demos look like they were recorded by a human presenter (Loom-style).
Convert academic research papers into engaging, SEO-optimized blog posts. Use when asked to (1) create a blog post from a research paper/preprint, (2) summarize research for general audiences, (3) promote publi...
Use this skill when advising on post structure, timing, media selection, and account health to align with the HeavyRanker's scoring weights and anti-spam heuristics.
Generate optimized prompts for AI image and video generation. Triggers on "generate a prompt for", "write me a prompt", "create an image prompt", "create a video prompt", "optimize this prompt".
Write documents in a natural, human style. Use when writing essays, papers, documentation, reports, articles, or any prose content. Avoids common AI writing patterns.
Use when transcribing audio/video to text with timestamps, speaker labels, and chapters. Supports YouTube URLs and local files. Produces structured markdown output.
This skill should be used when needs to search for unknown information, verify understanding, or avoid hallucination. or when detects knowledge gaps during task execution. Also trigger when the user asks to "se...
Review AI output critically before accepting it. Use when the user invokes /verify or wants to check AI-generated content for errors, assumptions, and claims requiring validation.
Adversarial fact-checking and verification of LLM output against uploaded attachments using DeepCitation. Use when you need to verify claims, find contradictions, or perform devil's advocate analysis on AI-gene...
Use this skill to decode the "DNA" of the recommendation engine. These signals are the foundational data structures used to retrieve candidates (before ranking) and as features for the Heavy Ranker (during rank...
Use when writing or editing novels, short stories, or any fiction manuscript. Trigger on: 'write fiction', 'edit my novel', 'developmental edit', 'line edit', 'character voice', 'plot hole', 'brainstorm', or fi...
Turn ideas into fully formed designs through collaborative dialogue - one question at a time.
Guide users through writing effective task definitions for plan-forge. Use when user wants help writing a task, needs a task template, is preparing input for plan-forge, or asks "how do I write a good task for...
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends an agent's capabilities with specialized knowledge, workflows, or...
Use when starting a Claude Code session, feeling overwhelmed by context, or needing workflow tips. Triggers on "how do I manage sessions", "context getting long", "remind me".
Unified management for Claude Code artifacts - extensions (agents, commands, skills, plugins, hooks) and configuration files (CLAUDE.md) using templates and a two-phase API.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool cal...
Activates when the user asks about Agent Skills, wants to find reusable AI capabilities, needs to install skills, or mentions skills for Claude. Use for discovering, retrieving, and installing skills.
Use this skill when reasoning about the distributed system design, service orchestration, or request lifecycle of the X recommendation engine. It is essential for tasks involving the "For You" timeline construc...
Opinionated constraints for building better interfaces with agents. Combines UI Skills and Vercel Web Interface Guidelines. Use when building UI components, reviewing frontend code, or implementing interactions...
This skill should be used when the user asks to "create bash scripts", "automate Linux tasks", "monitor system resources", "backup files", "manage users", or "write production shell scripts". It provides ready-...
Challenge assumptions and sharpen the prompt before implementing. Use when the user invokes /challenge or asks to critique their approach before starting work.
Automate creation, versioning, deployment, and synchronization of Mapache Skills across Desktop, Code CLI, and API environments. Manages skill lifecycle from scaffolding to deployment.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。