AG
Agent Agentic Payments
ruvnet · Expertise
Agent skill for agentic-payments - invoke with $agent-agentic-payments
$19
Details
Works with Claude Code
AD
Add a new Remotion package
remotion-dev · Workflow
See the writing-docs skill for details on writing documentation.
$35
Details
AD
Adversarial Review (General)
bmad-code-org · Workflow
Perform a Cynical Review and produce a findings report.
$15
Details
AG
AgentDB Vector Search
ruvnet · Workflow
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying.
$89
Details
BR
Brand Naming Strategies
mike-coulbourn · Output format
Provides brand naming frameworks, evaluation criteria, and templates for startup naming work.
$29
Details
CH
Checkpoint Review Workflow
bmad-code-org · Workflow
LLM-assisted human-in-the-loop review. Make sense of a change, focus attention where it matters, test. Use when the user says…
$39
Details
AG
Agent Browser
nexu-io · Workflow
Browser automation CLI for AI agents. Use when the user needs to inspect, test, or automate browser behavior: navigating pages, filling forms, clicking buttons, taking screenshots, extracting page…
$45
Details
GitHub CLI for issues, PRs, CI/check logs, comments, reviews, releases, repos, and gh api queries.
$99
Details
AR
Article Writing
affaan-m · Workflow
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied…
$45
Details
AV
Available make commands
streamlit · Workflow
Lists available make commands for Streamlit development.
$15
Details
Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.
$12
Details
AD
Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas…
$24
Details
AP
API and Interface Design
addyosmani · Workflow
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or…
$69
Details
BM
Bmad Market Research
bmad-code-org · Workflow
Conduct market research on competition and customers.
$12
Details
BO
Books and Records
JoelLewis · Workflow
Guide the design and maintenance of recordkeeping programs under SEC Rules 17a-3, 17a-4, and 204-2.
$12
Details
BR
Brand Positioning Theory Framework
mike-coulbourn · Output format
Provides brand positioning frameworks, the 22 Immutable Laws of Marketing, ZAG methodology, Onliness Statement formula, and positioning…
$89
Details
BR
Browser Extract
ruvnet · Output format
Extract structured data via stored browser-templates or one-shot DOM queries, with mandatory AIDefence PII + prompt-injection gates before…
$39
Details
BR
Browser Scrape (deprecated)
ruvnet · Output format
DEPRECATED in v0.2.0 -- use browser-extract instead; this is a thin shim for backward compatibility, removed in v0.3.0
$15
Details
CA
CAN/CAN-FD Communication
a5c-ai · Expertise
CAN bus design, analysis, and diagnostics expertise
$59
Details
CH
Checking Changes
streamlit · Guardrail
Validates all code changes before committing by running format, lint, type, and unit test checks.
$49
Details
CO
Code Quality Guide
tursodatabase · Workflow
General Correctness rules, Rust patterns, comments, avoiding over-engineering.
$24
Details
Agent skills on mcprush that work with Claude Code. Claude Code is a terminal agent, and working with it is a claim each publisher makes on their own listing — this shelf is every listing that makes it, and nothing else.
Every skill here says which kind it is, what it costs in context, what it needs beside it to work and the licence it is published under, next to the publisher it came from and whether that publisher has been verified. A skill is read by the client rather than routed to it, so what decides between two of them here is the context they cost and where their folder of instructions has to end up.
A skill is not connected to anything: there is no endpoint to authorise and nothing routed through the gateway. Installing one drops a folder of instructions into the client’s own skill folder, and uninstalling it is deleting that folder. The exact line for each client is on the skill’s own page, because it differs by client rather than by skill.