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. 79 566 files from 1 758 authors, of which 61 913 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.

61 913
unique skills
out of 79 566 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
7 886
name collisions
two skills with one name cannot sit side by side

16 921–16 980 of 61 913

page 283 of 1 032
Limits Colimits
by vibeeval

Problem-solving strategies for limits colimits in category theory

490 tokens
Groups
by vibeeval

Problem-solving strategies for groups in abstract algebra

975 tokens
Natural Transformations
by vibeeval

Problem-solving strategies for natural transformations in category theory

483 tokens
Analytic Functions
by vibeeval

Problem-solving strategies for analytic functions in complex analysis

932 tokens
Contour Integrals
by vibeeval

Problem-solving strategies for contour integrals in complex analysis

921 tokens
Residues
by vibeeval

Problem-solving strategies for residues in complex analysis

996 tokens
Hilbert Spaces
by vibeeval

Problem-solving strategies for hilbert spaces in functional analysis

1k tokens
Banach Spaces
by vibeeval

Problem-solving strategies for banach spaces in functional analysis

908 tokens
Graph Algorithms
by vibeeval

Problem-solving strategies for graph algorithms in graph number theory

992 tokens
Operator Theory
by vibeeval

Problem-solving strategies for operator theory in functional analysis

898 tokens
Modular Arithmetic
by vibeeval

Problem-solving strategies for modular arithmetic in graph number theory

522 tokens
Prime Numbers
by vibeeval

Problem-solving strategies for prime numbers in graph number theory

422 tokens
Channel Capacity
by vibeeval

Problem-solving strategies for channel capacity in information theory

596 tokens
Entropy
by vibeeval

Problem-solving strategies for entropy in information theory

564 tokens
Source Coding
by vibeeval

Problem-solving strategies for source coding in information theory

801 tokens
Eigenvalues
by vibeeval

Problem-solving strategies for eigenvalues in linear algebra

317 tokens
Matrices
by vibeeval

Problem-solving strategies for matrices in linear algebra

328 tokens
Vector Spaces
by vibeeval

Problem-solving strategies for vector spaces in linear algebra

342 tokens
Math Model Selector
by vibeeval

Routes problems to appropriate mathematical frameworks using expert heuristics

871 tokens
Math Intuition Builder
by vibeeval

Develops mathematical understanding through examples, visualization, and analogy

961 tokens
Math Progress Monitor
by vibeeval

Metacognitive check-ins during problem solving - detects when to pivot or persist

976 tokens
Predicate Logic
by vibeeval

Problem-solving strategies for predicate logic in mathematical logic

456 tokens
Proof Theory
by vibeeval

Problem-solving strategies for proof theory in mathematical logic

468 tokens
Integration Theory
by vibeeval

Problem-solving strategies for integration theory in measure theory

948 tokens
Propositional Logic
by vibeeval

Problem-solving strategies for propositional logic in mathematical logic

425 tokens
Lebesgue Measure
by vibeeval

Problem-solving strategies for lebesgue measure in measure theory

844 tokens
Sigma Algebras
by vibeeval

Problem-solving strategies for sigma algebras in measure theory

802 tokens
Interpolation
by vibeeval

Problem-solving strategies for interpolation in numerical methods

1k tokens
Numerical Integration
by vibeeval

Problem-solving strategies for numerical integration in numerical methods

965 tokens
Root Finding
by vibeeval

Problem-solving strategies for root finding in numerical methods

907 tokens
Boundary Value Problems
by vibeeval

Problem-solving strategies for boundary value problems in odes pdes

1k tokens
First Order Odes
by vibeeval

Problem-solving strategies for first order odes in odes pdes

867 tokens
Constrained Optimization
by vibeeval

Problem-solving strategies for constrained optimization in optimization

947 tokens
Second Order Odes
by vibeeval

Problem-solving strategies for second order odes in odes pdes

848 tokens
Convex Optimization
by vibeeval

Problem-solving strategies for convex optimization in optimization

931 tokens
Gradient Methods
by vibeeval

Problem-solving strategies for gradient methods in optimization

1k tokens
Continuity
by vibeeval

Problem-solving strategies for continuity in real analysis

304 tokens
Convergence
by vibeeval

Problem-solving strategies for convergence in real analysis

329 tokens
Limits
by vibeeval

Problem-solving strategies for limits in real analysis

330 tokens
Rudin Real Complex Analysis
by vibeeval

Problem-solving with Rudin's Real and Complex Analysis textbook

663 tokens
Connectedness
by vibeeval

Problem-solving strategies for connectedness in topology

933 tokens
Compactness
by vibeeval

Problem-solving strategies for compactness in topology

753 tokens
Open Sets
by vibeeval

Problem-solving strategies for open sets in topology

817 tokens
MCP Chaining
by vibeeval

Research-to-implement pipeline chaining 5 MCP tools with graceful degradation

1k tokens
MCP Registry
by vibeeval

MCP server registry, auto-discovery, configuration, custom server development guide

1k tokens
MCP Scripts
by vibeeval

MCP Script Rules

210 tokens
Memory Palace
by vibeeval

Hierarchical memory organization for multi-session context retention. Wings (projects) > Rooms (domains) > Drawers (decisions). Semantic search across all memories with zero cloud dependency.

1k tokens
Migrate
by vibeeval

Migration workflow - research → analyze → plan → implement → review

2k tokens
Modular Code
by vibeeval

Modular Code Organization

754 tokens
Mongodb Patterns
by vibeeval

Document modeling, aggregation pipeline, indexing strategy, change streams, and multi-document transactions.

2k tokens
Morph Search
by vibeeval

Fast codebase search via WarpGrep (20x faster than grep)

425 tokens
Morph Apply
by vibeeval

Fast file editing via Morph Apply API (10,500 tokens/sec, 98% accuracy)

764 tokens
Mot
by vibeeval

System health check (MOT) for skills, agents, hooks, and memory

2k tokens
Mutation Testing
by vibeeval

Mutation testing ile test suite kalitesini olc. Stryker, mutmut, go-mutesting destegi.

2k tokens
N8n Workflows
by vibeeval

n8n otomasyon workflow'lari. Webhook, cron trigger, API entegrasyon, CI/CD otomasyon.

3k tokens
Nia Docs
by vibeeval

Search library documentation and code examples via Nia

454 tokens
No Polling Agents
by vibeeval

No Polling for Background Agents

314 tokens
No Task Output
by vibeeval

Never Use TaskOutput

188 tokens
Oauth Patterns
by vibeeval

OIDC flows, PKCE implementation, token refresh strategies, social login integration, and secure session management.

2k tokens
Observability
by vibeeval

Structured logging with Pino/Winston, OpenTelemetry tracing, metrics collection, Grafana dashboards, and alerting rules.

3k 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: 11 350 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 79 566 files found on GitHub, 61 913 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: 7 886 skills here share a name with another skill, and two of them cannot sit side by side.