Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
solution-scoping
Prioritize features and define MVP boundaries based on problem framing and user models. Use when a user has validated their problem and understands their users but needs to decide what to build first. Outputs feature priorities, MVP scope, and explicit cuts that feed into PRD generation.
Abhsin/DesignSkills 4
-
prd-generation
Generate lean, actionable Product Requirements Documents from upstream design thinking artifacts or raw input. Use when a user needs to define what they're building with enough structure to guide development but without enterprise bloat. Outputs a PRD that feeds directly into UX specs and development prompts.
Abhsin/DesignSkills 4
-
problem-framing
Extract and structure fuzzy product ideas into validated problem statements, target users, and jobs-to-be-done. Use when a user has a raw idea, concept, or solution in mind but hasn't clearly articulated the problem, target user, or assumptions. This skill helps users communicate context to coding agents more effectively, reducing iteration cycles and "that's not what I meant" moments.
Abhsin/DesignSkills 4
-
ux-specification
Translate PRDs into detailed UX specifications including user flows, screen descriptions, components, and interaction patterns. Use when a user has a PRD and needs to define the concrete UI/UX before generating development prompts. Bridges product requirements to implementation details.
Abhsin/DesignSkills 4
-
user-modeling
Create lightweight user personas and usage scenarios from problem framing or raw research. Use when a user needs to clarify who they're building for beyond a basic target user description. Outputs practical personas and scenarios that inform feature priorities and UX decisions—not marketing fluff.
Abhsin/DesignSkills 4
-
create-plan
Create detailed implementation plans with thorough research and iteration. Use when the user asks to build a feature, create a plan, or specifically invokes this skill.
ferueda/agent-skills
-
summarize-work
Summarize work done in a spec/plan document.
ferueda/agent-skills
-
review-spec
Review a spec document against codebase reality, identifying gaps and ensuring sound, robust implementations.
ferueda/agent-skills
-
ask-questions
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
ferueda/agent-skills
-
research-codebase
Research codebase comprehensively using parallel sub-agents. Use when the user asks to "research the codebase", "understand how X works", or "investigate Y".
ferueda/agent-skills
-
implement-plan
Implement a spec document phase-by-phase, writing robust idiomatic code that follows codebase patterns.
ferueda/agent-skills
-
logging-best-practices
Use before implementing logs in a medium to large scale production system.
nbbaier/agent-skills 9
-
react-effect-patterns
Guidelines for proper React useEffect usage and avoiding unnecessary Effects. Use when writing, reviewing, or refactoring React components that use useEffect, useState, or handle side effects. Triggers on tasks involving React Effects, derived state, event handlers, data fetching, or component synchronization.
nbbaier/agent-skills 9
-
implementation-guide
Generate comprehensive implementation guides for coding tasks instead of writing code directly. Use when the user requests detailed implementation documentation, step-by-step development guides, or when they want to implement features themselves using tools like Cursor. Creates exhaustive guides with background context, architecture decisions, milestones with verification points, and rationale for a "build-it-yourself" workflow.
nbbaier/agent-skills 9
-
ideation
Guides structured ideation through Socratic questioning to explore problems, opportunities, and solutions. Use when brainstorming features, exploring use cases, or thinking through new ideas.
nbbaier/agent-skills 9
-
html-tools
Build single-file HTML tools — self-contained HTML+JS+CSS applications that solve a specific problem without a build step. Use this skill whenever the user asks to build a utility, converter, viewer, debugger, or any small interactive web tool. Also trigger when the user says "build me a tool that...", "make a quick app for...", "I need a single-file HTML page that...", or wants to create something that could be hosted as a static file. This skill is specifically for practical, utility-focused tools (not landing pages, portfolios, or marketing sites — use frontend-design for those).
nbbaier/agent-skills 9
-
val-town-cli
Manage Val Town projects using the vt CLI. Use when working with Vals (Val Town serverless functions), syncing code to Val Town, creating HTTP endpoints, streaming logs, or managing Val Town branches. Triggers on tasks involving Val Town development, val creation/editing, or when user mentions "vt", "val town", or "vals".
nbbaier/agent-skills 9
-
sand-table
Design, scaffold, extract, and validate Sand Table simulations and event streams across domains. Meta skill that knows the protocol and all existing implementations.
leegonzales/AISkills 25
-
artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
leegonzales/AISkills 25
-
concept-forge
Transform nebulous ideas into sharp, testable frameworks through multi-perspective dialectical interrogation. Use when developing vague intuitions, pressure-testing concepts, structuring half-formed frameworks, or distinguishing new ideas from existing concepts. Triggers include "explore this idea," "think through X," or "challenge my thinking."
leegonzales/AISkills 25
-
command-center-builder
Build a personalized AI command center as a Claude project with MCP integrations, custom voice print, and tailored workflows. Use when setting up a new command center, configuring a Claude project for executive productivity, or when someone says "build my command center."
leegonzales/AISkills 25
-
presentation-partner
Collaborative presentation authoring that transforms ideas, outlines, or existing slides into Talk Track v5 format through structured interview, thread tracking, and voice calibration.
leegonzales/AISkills 25
-
writing-partner
Collaborative essay writing that preserves authenticity through structured interview, thread tracking, and voice calibration. Transforms AI from text generator into intellectual prosthesis. Use when writing essays, blog posts, or any content where voice matters more than speed.
leegonzales/AISkills 25
-
pr-review-loop
Manage PR review feedback loops with Gemini Code Assist. Use when pushing changes to a PR, iterating on review feedback, or monitoring CI/review status. Automatically falls back to Claude when Gemini is rate-limited.
leegonzales/AISkills 25