Agent Skills Directory

Browse production-ready skills for Claude Code, Cursor, Codex, Gemini CLI, and more. Install in seconds to supercharge your AI coding assistant.

145 skills21 categories
Works with
Claude Code
Cursor
Windsurf
GitHub Copilot
Codex
Gemini CLI
OperationsEngineeringFinanceGemini CLIClaude Code145 results

Vercel React Native Skills

Vercel React Native Skills skill.

20
vercel-labs
#skills

Architecture

Create or evaluate an architecture decision record (ADR). Use when choosing between technologies (e.g., Kafka vs SQS), documenting a design decision with trade-offs and consequences, reviewing a system design proposal, or designing a new component from requirements and constraints.

20
anthropics
#engineering

Code Review

Review code changes for security, performance, and correctness. Trigger with a PR URL or diff, "review this before I merge", "is this code safe?", or when checking a change for N+1 queries, injection risks, missing edge cases, or error handling gaps.

20
anthropics
#engineering

Variance Analysis

Decompose financial variances into drivers with narrative explanations and waterfall analysis. Use when analyzing budget vs. actual, period-over-period changes, revenue or expense variances, or preparing variance commentary for leadership.

20
anthropics
#finance

Process Optimization

Analyze and improve business processes. Trigger with "this process is slow", "how can we improve", "streamline this workflow", "too many steps", "bottleneck", or when the user describes an inefficient process they want to fix.

20
anthropics
#operations

CI CD Pipeline Builder

CI/CD Pipeline Builder

20
Alireza Rezvani
#engineering

API Design Reviewer

API Design Reviewer

20
Alireza Rezvani
#engineering

Agent Workflow Designer

Agent Workflow Designer

20
Alireza Rezvani
#engineering

API Test Suite Builder

API Test Suite Builder

20
Alireza Rezvani
#engineering

Autoresearch Agent

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

20
Alireza Rezvani
#engineering

Run

Run a single experiment iteration. Edit the target file, evaluate, keep or discard.

20
Alireza Rezvani
#engineering#autoresearch-agent

CTO Advisor

Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Use when assessing technical debt, scaling engineering teams, evaluating technologies, making architecture decisions, establishing engineering metrics, or when user mentions CTO, tech debt, technical debt, team scaling, architecture decisions, technology evaluation, engineering metrics, DORA metrics, or technology strategy.

20
Alireza Rezvani
#c-level#c-level advisor