AI Agent
Skills Directory
Explore 250+ curated skills for Claude, Codex, and AI agents. Open-source, community-driven.
Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted training, optional repository analysis, and optional paper-gap resolution, enforces conservative patch rules, records evidence assumptions deviations and human decision points, and writes the standardized `repro_outputs/` bundle. Do not use for paper summary, generic environment setup, isolated repo scanning, standalone command execution, silent protocol changes, score chasing, or broad research assistance outside repository-grounded reproduction.
Rigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated branch or worktree to transplant modules, adapt a backbone, add LoRA or adapter layers, replace a head, or stitch together meaningful low-risk migration ideas with rollback-aware records in `explore_outputs/`. Do not use for end-to-end exploration orchestration on top of `current_research`, trusted baseline reproduction, conservative debugging, environment setup, verified contribution claims, or default repository analysis.
✨ Editor's Choice
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
obrareceiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
obrawriting-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
obradispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
obrafinishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
obra🆕 New Arrivals
View all →
paper-context-resolver
Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.
lllllllamaai-research-reproduction
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted training, optional repository analysis, and optional paper-gap resolution, enforces conservative patch rules, records evidence assumptions deviations and human decision points, and writes the standardized `repro_outputs/` bundle. Do not use for paper summary, generic environment setup, isolated repo scanning, standalone command execution, silent protocol changes, score chasing, or broad research assistance outside repository-grounded reproduction.
lllllllamaexplore-code
Rigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated branch or worktree to transplant modules, adapt a backbone, add LoRA or adapter layers, replace a head, or stitch together meaningful low-risk migration ideas with rollback-aware records in `explore_outputs/`. Do not use for end-to-end exploration orchestration on top of `current_research`, trusted baseline reproduction, conservative debugging, environment setup, verified contribution claims, or default repository analysis.
lllllllamaanalyze-project
Rigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrypoints, review configs and insertion points, or flag suspicious implementation patterns without modifying code or running heavy jobs. Do not use for active command execution, broad refactoring, speculative code adaptation, or automatic bug fixing.
lllllllama
defuddle
Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for URLs ending in .md — those are already markdown, use WebFetch directly.
kepano
make-interfaces-feel-better
Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, typography, micro-interactions, enter/exit animations, or any visual detail work. Triggers on UI polish, design details, "make it feel better", "feels off", stagger animations, border radius, optical alignment, font smoothing, tabular numbers, image outlines, box shadows.
jakubkreheljson-canvas
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.
kepano
self-improving-agent
A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.
charon-fan
What is an AI Agent Skill?
An AI Agent Skill (also known as Claude skills or AI skills) is a reusable capability you can add to an agent to automate tasks like writing, social posting, research, or development workflows.
Think of them as "plugins" for your AI. Browse our Claude skills marketplace to find Claude code templates and open-source GitHub repositories. Most come with a simple one-line installation command.
🔥 Trending This Week
View all →subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
obraverification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
obrareceiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
obrawriting-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
obradispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
obrafinishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
obrausing-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
obraexecuting-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
obrausing-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
obraBrowse by Category
View allAgent Workflows
Reusable agent workflows and orchestration patterns
Prompting & Reasoning
Prompt engineering, personas, and reasoning patterns
Research & Knowledge
Research, retrieval, summarization, and knowledge work
Browser & Web
Browser control, web automation, scraping, and crawling
Writing & Content
Writing, editing, publishing, and translation workflows
Design & UI
Interface design, visual systems, and product UI
Marketing & SEO
SEO, content marketing, campaigns, and growth workflows
Productivity
Task automation, office workflows, and personal productivity
Code Generation
Code generation, refactoring, and scaffolding
Frontend
Frontend frameworks, UI components, CSS, and web apps
Backend & API
Backend services, APIs, webhooks, and server-side tooling
Database
SQL, schema design, migrations, and database operations
Power your workflows
Discover specialized agents tailored to specific industries and tasks.
Content Creation
Generate blog posts, social media captions, and marketing copy effortlessly using specialized writing agents trained on high-converting frameworks.
Automation
Streamline repetitive tasks like file organization, data entry, and email sorting with intelligent automation scripts that run 24/7.
Data Analysis
Extract insights from large datasets, visualize trends, and generate comprehensive reports in seconds with data-centric agent skills.
Loved by Developers
"The Code Reviewer skill has completely transformed our PR process. It catches subtle bugs that even experienced humans miss. Absolutely essential tool."
"I built my entire marketing workflow using the Content Creation agents available here. It feels like I have a team of five working for me."
"Great for prototyping AI workflows. It helped me validate ideas in minutes instead of days."
"Saved hours on data cleaning scripts. The agents understand complex data structures surprisingly well."
"SEO tools are amazing for my blog. My organic traffic has doubled since I started using these skills."
"Helped me learn Python via code analysis. The explanations are clearer than my textbooks."
"Automated my deployments with ease. The infrastructure-as-code agents are spot on."
"Image generation prompts are top notch. It feels like having a creative director by my side."
"Research agent is a game changer. It summarizes hundreds of papers in minutes."
"Campaigns are easier to manage now. The copywriting skills capture our brand voice perfectly."
How to install a skill
2 minutesFind a skill
Browse our extensive catalog of verified skills. Filter by category, popularity, or rating to find the perfect tool for your specific needs.
Copy command
Every skill comes with a simple, one-line installation command. Just click the copy button on the skill's detail page to capture the unique identifier.
Paste & run
Built by the Community
Join thousands of developers contributing to the future of AI. All skills are open-source and vetted by the community.