GitHub
collab-evals
Run collab/multi-agent eval scenarios (symbolic RLM, large-context, pause/resume, multi-hour checkpoints) and capture manifest-backed evidence.
☆ 2查看技能
tools llm ai AI 技能
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。
分类目录: tools llm ai
tools llm ai 清除筛选
全部技能
GitHub
prompt-optimization
Expert prompt optimization for LLMs and AI systems. Use when building AI features, improving agent performance, crafting system prompts, or optimizing LLM interactions. Masters prompt patterns and techniques.
☆ 2查看技能
GitHub
analyzing-patterns
Automatically activated when user asks to "find patterns in...", "identify repeated code...", "analyze the architecture...", "what design patterns are used...", or needs to understand code organization, recurri...
☆ 2查看技能
GitHub
model-discovery
Fetch current model names from AI providers (Anthropic, OpenAI, Gemini, Ollama), classify them into tiers (fast/default/heavy), and detect new models. Use when needing up-to-date model IDs for API calls or when...
☆ 2查看技能
GitHub
meta-cognitive-reasoning
Meta-cognitive reasoning specialist for evidence-based analysis, hypothesis testing, and cognitive failure prevention. Use when conducting reviews, making assessments, debugging complex issues, or any task requ...
☆ 2查看技能
GitHub
meeting-insights-analyzer
Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss...
☆ 2查看技能
GitHub
researching-best-practices
Automatically activated when user asks "what's the best way to...", "how should I...", "what are best practices for...", or requests recommendations, industry standards, or proven approaches for implementing fe...
☆ 2查看技能
GitHub
analyzing-response-quality
Expert at analyzing the quality of Claude's responses and outputs. Use when evaluating response completeness, accuracy, clarity, or effectiveness. Auto-invokes during self-reflection or when quality assessment...
☆ 2查看技能
GitHub
eleanor
Roleplay companion skill for Eleanor - a brilliant 24-year-old researcher at a quiet café after leaving academia. Triggers when user selects Scholar character, requests academic research assistance, intellectua...
☆ 2查看技能
GitHub
writing-style
Core writing standards for all Skill Stack content. Invoke automatically for any writing task. Combines anti-AI patterns, voice principles, and prose style.
☆ 2查看技能
GitHub
decide-build-primitive
Analyze and decide the right Codex primitive (Skill, Custom Prompt, or Agent automation) for a capability. Use this when you need to plan how to package or automate a workflow.
☆ 2查看技能
GitHub
ui-spec-to-prompts
Translate a UI spec into build-order prompts for UI generator tools (v0, Bolt, Claude). Use when a UI spec already exists and you need sequenced, self-contained prompts.
☆ 2查看技能
GitHub
image-prompt-generator
Generate AI images using Gemini image generation API. Use this skill when content needs images - thumbnails, social posts, blog headers, or creative visuals. Follows an iterative workflow - brainstorm concepts,...
☆ 2查看技能
GitHub
prompt-testing
A/B testing and performance metrics for prompts
☆ 2查看技能
GitHub
article-illustrator
Smart article illustration skill. Analyzes article content and generates illustrations at positions requiring visual aids with multiple style options. Use when user asks to "add illustrations to article", "gene...
☆ 2查看技能
GitHub
agentsmd-generator
Generate project-level AGENTS.md guides that capture conventions, workflows, and required follow-up tasks. Use when a repository needs clear agent onboarding covering structure, tooling, testing, task flow, REA...
☆ 2查看技能
GitHub
ux-spec-to-prompts
Use when translating UX specifications into build-order prompts for UI generation tools. Triggers when user has a UX spec, PRD, or detailed feature doc and needs sequential, self-contained prompts for tools lik...
☆ 2查看技能
GitHub
guardrails
Security techniques and quality control for prompts and agents
☆ 2查看技能
GitHub
interview-me
Interactive, multiple-choice interview for requirements discovery and spec clarification; turns an underspecified idea (or draft spec) into an execution-ready spec with decisions, assumptions, acceptance criter...
☆ 2查看技能
GitHub
agent-design
Design AI agents with recommended patterns and architectures
☆ 2查看技能
GitHub
world-labs-text-prompt
Text-to-world generation best practices, prompt structure, style descriptors
☆ 2查看技能
GitHub
memecoin-narrative-engine
Build a meme narrative system: frames, symbols, story arcs, and content hooks tailored for Solana memecoins. Use for brand/story development.
☆ 2查看技能
GitHub
elicitation
Auto-review skill for expert agents. After coding, expert applies elicitation techniques to self-correct before sniper validation. Inspired by BMAD-METHOD.
☆ 2查看技能
GitHub
prompt-optimization
Analyze and improve existing prompts for better performance
☆ 2查看技能
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。