mcpbeat Sign in

Claude Skills

The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.

Every Agent Skill we could find on GitHub, deduplicated by content. 79 600 files from 1 763 authors, of which 61 947 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.

61 947
unique skills
out of 79 600 files found on GitHub
17 653
are copies
same content, someone else's repository
1 739
tokens, median
what a typical skill costs you in context
7 890
name collisions
two skills with one name cannot sit side by side

21 181–21 240 of 61 947

page 354 of 1 033
Compare
by fcakyon

Same-epoch comparison of training runs across wandb, neptune, tensorboard, or mlflow. Aligns runs at the student's current step (never current-vs-final-of-baseline) and separates proxy metrics from downstream targets. Use when the user asks to compare runs, check if a run is improving, track lag against a baseline, rank experiments, or evaluate run-vs-run performance.

1k tokens
Latex Setup
by fcakyon

> Use when the user wants to set up or troubleshoot a LaTeX environment, choose between biber and bibtex, install packages for a specific venue template, or configure compilation. Triggers on phrases like "setup latex", "biber vs bibtex", "latex compilation error", "install latex packages", "venue template", or "texlive setup".

1k tokens
Debug
by fcakyon

Evidence-before-action diagnosis of failing ML experiments. Probes the system before guessing causes, process list, dmesg, GPU stats, log scrollback, checkpoint state, then states a hypothesis as a hypothesis and runs a smoke before claiming a root cause. Use when the user asks why a run is failing, diverging, OOMing, hanging, slow, producing weird metrics, has crashed, or asks to debug, diagnose, troubleshoot, or investigate a training issue.

1k tokens
Launch
by fcakyon

Pre-flight checklist for long-running ML training jobs covering config diff, run naming, path verification, monitoring setup, and restart-cleanup. Use when the user asks to launch, kick off, start, restart, or kill a training run, or mentions launching a multi-hour or multi-day GPU job (python train, accelerate launch, torchrun, deepspeed, sbatch, tmux training).

1k tokens
Paper Verification
by fcakyon

> Use when the user wants to verify paper claims against code or data, audit numerical accuracy, check formula-code alignment, or validate citation accuracy. Triggers on phrases like "verify claims", "check numbers", "do the numbers match", "formula vs code", "audit the paper", or "cross-check results".

1k tokens
Literature Research
by fcakyon

> Use when the user wants to find related work, survey a research area, identify literature gaps, or discover open-source implementations. Triggers on phrases like "find papers on", "related work", "literature review", "what papers exist", "open source implementation", or "papers with code".

1k tokens
Dataset Curation
by fcakyon

> Use when the user wants to analyze dataset bias, create stratified samples, evaluate fairness, or plan dataset collection. Triggers on phrases like "dataset bias", "stratified sample", "class imbalance", "data distribution", "fairness analysis", or "ethical review".

1k tokens
Reproduce
by fcakyon

End-to-end paper reproduction from arxiv URL through smoke runs to replication experiments. Handles missing or partial official code, missing training scripts, missing hyperparameters, and private datasets via similar-public-dataset substitution. Use when the user asks to reproduce, implement, replicate, or re-run a paper from scratch, or pastes an arxiv URL with reproduction intent.

9k tokens
Paper Writing
by fcakyon

> Use when the user wants to write, structure, or revise academic paper sections, improve notation consistency, or refine figures and tables. Triggers on phrases like "write the abstract", "structure the methods", "improve this section", "notation consistency", "figure refinement", or "paper structure".

1k tokens
Research Publishing
by fcakyon

> Use when the user wants to prepare code for open-source release, create reproducible research artifacts, or structure a repository for publication. Triggers on phrases like "publish code", "open source release", "reproducibility", "research repository", "code release", or "prepare for publication".

1k tokens
Reviewer Defense
by fcakyon

> Use when the user wants to anticipate reviewer questions, select the strongest ablations to present, prepare rebuttals, or identify paper weaknesses before submission. Triggers on phrases like "reviewer questions", "anticipate reviewers", "rebuttal", "paper weaknesses", "defend the paper", or "strengthen the paper".

1k tokens
Academic Search
by claude-office-skills

Search and analyze academic literature. Find papers, understand research methodologies, and synthesize academic findings for research projects.

2k tokens
Applicant Screening
by claude-office-skills

Screen job applications against requirements and score candidates

2k tokens
AI Slides
by claude-office-skills

Generate complete presentations with AI - from outline to polished slides

1k tokens
Amazon Seller
by claude-office-skills

Automate Amazon seller operations including inventory, orders, pricing, and advertising management

3k tokens
Apple Shortcuts Integration
by claude-office-skills

Create and trigger Apple Shortcuts for iOS/macOS automation and cross-platform workflows

813 tokens
AI Agent Builder
by claude-office-skills

Build AI agents with tools, memory, and multi-step reasoning - ChatGPT, Claude, Gemini integration patterns

3k tokens
Ads Copywriter
by claude-office-skills

Multi-platform ad copy generation for Google Ads, Meta/Facebook, TikTok, LinkedIn with A/B testing variants

2k tokens
Airtable Automation
by claude-office-skills

Airtable database automation - views, automations, integrations, and workflow triggers

3k tokens
Brand Guidelines Generator
by claude-office-skills

Create and maintain brand style guides for consistent visual identity

2k tokens
Asana Automation
by claude-office-skills

Automate Asana project management workflows, task tracking, team collaboration, and reporting

3k tokens
Browser Automation
by claude-office-skills

Automate web browser interactions, scraping, testing, and workflow automation with Puppeteer/Playwright

907 tokens
Chart Designer
by claude-office-skills

Design effective data visualizations and charts. Generate chart configurations for ECharts, Chart.js, and other libraries. Create dashboards and reports.

2k tokens
Batch Convert
by claude-office-skills

Batch convert documents between multiple formats using a unified pipeline

4k tokens
Batch Processor
by claude-office-skills

Process multiple documents in bulk with parallel execution

1k tokens
Calendar Automation
by claude-office-skills

Google Calendar and Outlook automation - scheduling optimization, meeting workflows, time blocking, and Slack/Sheets integration

3k tokens
Changelog Generator
by claude-office-skills

Generate release notes from git commits, updates, or feature lists

2k tokens
Chat with PDF
by claude-office-skills

Answer questions about PDF content, summarize, and extract information

2k tokens
ClickUp Automation
by claude-office-skills

Automate ClickUp workspace management, task workflows, time tracking, and team productivity

3k tokens
Company Research
by claude-office-skills

Conduct comprehensive company research and due diligence. Analyze business model, competitive landscape, management, and market position.

2k tokens
Competitive Analysis
by claude-office-skills

Analyze competitors systematically. Compare products, features, pricing, positioning, and market strategies. Generate comprehensive competitive intelligence reports.

2k tokens
Contract Review
by claude-office-skills

Analyze contracts for risks, check completeness, and provide actionable recommendations. Supports employment contracts, NDAs, service agreements, and more.

4k tokens
Cover Letter
by claude-office-skills

>

3k tokens
Content Research Writer
by claude-office-skills

Research topics and write content like blog posts, articles, and copy

2k tokens
Crypto Report
by claude-office-skills

Analyze cryptocurrency projects with tokenomics, on-chain metrics, and market analysis. Generate comprehensive crypto research reports.

2k tokens
Cv Builder
by claude-office-skills

>

1k tokens
Data Analysis
by claude-office-skills

Analyze spreadsheet data, generate insights, create visualizations, and build reports from Excel/CSV data.

2k tokens
Data Pipeline
by claude-office-skills

Data pipeline and ETL automation - extract, transform, load workflows for data integration and analytics

2k tokens
Data Extractor
by claude-office-skills

>

4k tokens
Dcf Valuation
by claude-office-skills

Build Discounted Cash Flow (DCF) valuation models. Calculate intrinsic value with customizable assumptions. Generate professional valuation reports.

2k tokens
Database Sync
by claude-office-skills

Automate database synchronization, replication, migration, and cross-platform data integration

3k tokens
Dev Slides
by claude-office-skills

>

1k tokens
Deep Research
by claude-office-skills

Conduct comprehensive research on any topic. Synthesize information from multiple angles, provide structured analysis, and generate detailed research reports.

2k tokens
Diagram Creator
by claude-office-skills

Create professional diagrams using Mermaid, PlantUML, and other text-based diagram tools. Generate flowcharts, sequence diagrams, architecture diagrams, and more.

2k tokens
Discord Bot
by claude-office-skills

Discord bot development - community management, moderation, notifications, and AI integration

3k tokens
Devops Automation
by claude-office-skills

DevOps and IT Ops automation - CI/CD, monitoring, incident management, and infrastructure workflows

3k tokens
Doc Pipeline
by claude-office-skills

Chain document operations into reusable pipelines

1k tokens
Doc Parser
by claude-office-skills

>

4k tokens
DocuSign Automation
by claude-office-skills

Automate document signing workflows, envelope management, and e-signature processes

3k tokens
Email Classifier
by claude-office-skills

Automatically categorize emails by type, priority, and required action

2k tokens
Email Drafter
by claude-office-skills

>

2k tokens
DOCX Manipulation
by claude-office-skills

Create, edit, and manipulate Word documents programmatically using python-docx

2k tokens
Excel Automation
by claude-office-skills

>

3k tokens
Expense Report
by claude-office-skills

>

3k tokens
Expense Tracker
by claude-office-skills

Automate expense tracking, receipt processing, approval workflows, and reimbursement management

2k tokens
File Organizer
by claude-office-skills

Organize and rename files based on content analysis

2k tokens
Meta Ads
by claude-office-skills

Automate Facebook and Instagram advertising campaigns, audience targeting, and performance optimization

3k tokens
Gmail Workflows
by claude-office-skills

Automate Gmail with intelligent workflows - attachment management, email organization, auto-archiving, and Google Drive integration

3k tokens
Financial Modeling
by claude-office-skills

Build integrated financial models with 3-statement projections. Create income statement, balance sheet, and cash flow models with proper linkages.

2k tokens
Form Builder
by claude-office-skills

Build interactive document forms and questionnaires using docassemble

1k tokens

Claude Skills — questions

Answers built from the skills we actually parsed.

What is a Claude Skill?
A folder with a SKILL.md file: instructions that teach an agent to do one thing well, optionally with scripts and reference files alongside. The format is open and called Agent Skills — Claude Code, Codex and other agents read the same files. It is not a program you run; it is knowledge the agent loads when the task calls for it.
How is a skill different from an MCP server?
A server gives the agent new abilities — it connects to something and exposes tools. A skill gives the agent knowledge: how to use what it already has. They combine, and often literally: 11 352 of the skills here declare which MCP servers they need to work.
Why are there fewer skills here than in other catalogues?
Because we deduplicate by content. Of 79 600 files found on GitHub, 61 947 are unique — the rest is the same skill copied into someone else's repository, word for word. Catalogues that count files rather than skills show every copy as a separate entry.
What does the token count mean?
A skill is loaded into the model's context when it is used, so its size is a running cost on every request that touches it. We measure the whole folder, not just SKILL.md: one official skill is 377 tokens, another drags 83 files of fonts behind it.
How do I install a skill?
Copy the skill folder into ~/.claude/skills for personal use, or into .claude/skills inside a project. The agent picks it up by the name in the SKILL.md header — which is worth checking: 7 890 skills here share a name with another skill, and two of them cannot sit side by side.