vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-15 00:13
Coding & development
41,136 results
peach-intake
A gate skill that receives and classifies PeachSolution development requests or PRDs before implementation and determines the necessary next skill path. "Which skill to start with", "request analysis", "PRD analysis", "development path determination", "determining whether Spec/DB/proto is needed", "determining task scale",…
plan-review-criteria
Plan review criteria — the six review axes, severity rubric, approval standard, and output format for reviewing implementation plans. Loaded by the reviewer…
review-code
Code review flow — review a diff, PR, or code change, delegating the review to a subagent that follows the code-review-criteria skill. Use it when the user…
review-plan
Plan review flow — evaluate an implementation plan before it is executed, delegating the review to a subagent that follows the plan-review-criteria skill. Use…
discord-expert
Expert in Discord bot development using discord.js and discord.py, slash commands, embeds, voice channels, moderation, and bot deployment. Use when the user…
shape-up
Guided Shape Up workflow for taking projects from idea to working software. Orchestrates the /shaping and /breadboarding skills through a structured process:…
react-component-dev
Build React components with proper patterns, accessibility, and composition. Use when creating new components, refactoring existing ones, or reviewing…
gis-platform-engineering
Use when implementing GIS maps, spatial data services, maps integrations, geocoding, spatial APIs, or PostGIS-backed geospatial platforms. Load absorbed GIS…
graphql-patterns
Use when designing, building, or operating GraphQL APIs with Apollo Server + TypeScript — covers schema-first SDL design, resolver architecture, DataLoader,…
microservices-architecture
Use when designing, reviewing, or refactoring microservice boundaries, communication, service ownership, deployment independence, resilience, and distributed…
kiro-specs
Create a Kiro spec for a feature in .kiro/specs create/update feature spec/PRD/RFC—requirements, design doc, and implementation tasks checklist.Trigger on…
serpapi
Search the web and e-commerce platforms using the SerpApi API. Use when the user wants to search Google, Google Shopping, Google Jobs, eBay, or Amazon via…
pflow-agents
Creates or rewrites a minimal AGENTS.md for the current project and syncs it to CLAUDE.md. Audits the repo, asks the user only for facts that cannot be derived…
pflow-task-implement
Implements the saved plan for the current active task, step by step. Does not plan, commit, or close the task. Invoked manually only.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent,…
crypto-gains
Calculate capital gains with FIFO, wash sale detection, term classification, and Form 8949 outputs.
guardrail
Generate custom lint rules from architectural patterns. ESLint local plugins (JS/TS) or ast-grep YAML rules (Python/Go/Rust/any). Invoke when: codifying an…
pr-polish
Elevate a working PR: hindsight review, refactor, simplify, test audit, docs, quality gates. Composes: hindsight-reviewer agent, /refactor, /simplify,…
remotion-render
Render videos from React/Remotion component code via inference.sh. Pass TSX code, get MP4. Supports all Remotion APIs: useCurrentFrame, useVideoConfig, spring,…
retro
Implementation feedback capture. Appends effort accuracy, scope changes, and blockers to {repo}/.groom/retro.md. Read by /groom for planning. Invoked by /done…
review-branch
Orchestrate comprehensive code review across ~12 AI reviewers. 5 persona reviewers (Grug, Carmack, Ousterhout, Beck, Fowler) via Moonbridge, 4 domain…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code