Best Claude skills for coding
Coding skills change how your agent works, not only what it writes: brainstorm before building, write a plan, test first, review its own diff, and finish branches cleanly. Packs like Superpowers, Matt Pocock's skills, Addy Osmani's agent skills and Garry Tan's gstack are the most starred skills on GitHub.
484 coding skills · ranked live · November 2026
The top 10. Ranked by the Alyn Score.
- 1#1
Matt Pocock
Diagnosing Bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
321k33MScore 97 - 2#2
Ask Matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
321k33MScore 95 - 3#3
Code Review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code…
321k33MScore 95 - 4#4
Jesse Vincent
Superpowers
Jesse Vincent
Writing Skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
316k3.9MScore 94 - 5#5
Jesse Vincent
Superpowers
Brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a…
316k3.9MScore 92 - 6#6
Jesse Vincent
Superpowers
Diagnosing Superpowers
Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why…
316k3.9MScore 92 - 7#7
JuliusBrussee
Caveman Learn
Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's…
119k4.8MScore 90 - 8#8
affaan-m
Agent Architecture Audit
Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering…
301k1.7MScore 89 - 9#9
Agent Sort
Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes…
301k1.7MScore 89 - 10#10
Android Clean Architecture
Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns. Use when structuring…
301k1.7MScore 89
What makes a great coding skill.
A workflow (plan, implement, verify) rather than a list of tips.
Explicit stop conditions so the agent asks instead of guessing.
Skills that compose: planning, testing and review that hand off to each other.
All 484 coding skills.
Vercel
Agent Skills
Vercelvercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks…
Jeffallan
Claude Skills
Jeffallanapi-designer
Use when designing REST or GraphQL APIs, creating OpenAPI specifications, or planning API architecture. Invoke for resource modeling, versioning strategies, pagination patterns, error…
gamedev-skillsaudio-design
Implement game audio practice — bus/mixer architecture and gain in decibels, ducking (sidechain), adaptive/dynamic music via layering and re-sequencing, SFX variation, and beat…
Jeffallan
Claude Skills
Jeffallanchaos-engineer
Designs chaos experiments, creates failure injection frameworks, and facilitates game day exercises for distributed systems — producing runbooks, experiment manifests, rollback procedures…
Jeffallan
Claude Skills
Jeffallancloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing…
phuryncreate-prd
Create a lean, decision-ready Product Requirements Document with an 8-section template: summary, contacts, background, objective, market segments, value propositions (6-part JTBD template)…
gamedev-skillsgodot-2d-movement
Implement 2D kinematic character movement in Godot 4.7 with CharacterBody2D and move_and_slide(): platformer run/jump with gravity, top-down 8-direction motion, slope handling, and reading…
Composiolangsmith-fetch
Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory…
davila7agent-management
Create, manage, and orchestrate AI agents using the AI Maestro CLI. Use when the user asks to "create agent", "list agents", "delete agent", "hibernate agent", "wake agent", "install…
tw93check
Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.
tw93health
Audits or prunes agent config, instruction drift, hooks or MCP, and AI maintainability. Use when Claude, Codex, or Pi setup looks wrong or guidance needs slimming. Not for application bugs…
KKKKhazix
Khazix Skills
KKKKhazixneat-freak
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so…
tw93read
Fetches URLs and PDFs, then summarizes or returns clean Markdown; can also search the web through DeepSeek when built-in search is thin. Use when asked to read, fetch, quote, cite, convert…
KKKKhazix
Khazix Skills
KKKKhazixstorage-analyzer
macOS / Windows / Linux 只读存储分析助手（自动识别系统）。扫描整机磁盘占用，找出 占空间大户，把每一项分成 🟢可自动清理 / 🟡需人工判断 / 🔴谨慎清理 三级并给出 可执行处置方案，生成排版精美、可折叠、命令可一键复制的交互式 HTML 报告，并可 起本地服务在网页上一键删除（移废纸篓/直接删）。扫描全程只读。务必在以下场景…
davila7docs-search
Search auto-generated codebase documentation for function signatures, API docs, class definitions, and code comments. Use when the user asks to "search docs", "find documentation", "look up…
wanshuiyin
Auto Claude Code Research In Sleep
wanshuiyinfigure-spec
Generate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG. Use when user says "架构图", "workflow 图"…
Composiochangelog-generator
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release…
Orchestra Research
AI Research SKILLs
Orchestra Researchdistributed-llm-pretraining-torchtitan
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8…
Orchestra Research
AI Research SKILLs
Orchestra Researchimplementing-llms-litgpt
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational…
Orchestra Research
AI Research SKILLs
Orchestra Researchmamba-architecture
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and…
phuryncode-review
Moved to phuryn/product-engineering, where it is maintained in the ai-shipping plugin; this copy says where it went and how to install it. Use when asked to review changes, find bugs, audit…
Cloudflare
Skills
Cloudflareworkers-development
Run, inspect, and debug Cloudflare Workers during local development with cf dev, wrangler dev, or the Cloudflare Vite plugin, using Local Explorer to read and seed binding data and query…
wondelai
Skills
wondelaiarchitecture-optimization
Guided journey from a working codebase grown slow and tangled to one measurably fast, cleanly bounded, and readable. Orchestrates eight skills phase by phase - working-with-legacy-code…
wondelai
Skills
wondelaiclean-architecture
Structure software around the Dependency Rule: source code dependencies point inward from frameworks to use cases to entities. Use when the user mentions "architecture layers", "dependency…
wondelai
Skills
wondelaiclean-code
Write readable, maintainable code through disciplined naming, small functions, and clean error handling. Use when the user mentions "clean up this code", "this function is too long", "code…
JCodesMoreclone-website
Rebuild existing web pages as working local code, matching their real content, assets, responsive layout, and interactions. Use for website cloning, replication, or reverse engineering…
Google Labs
Stitch Skills
Google Labsstitch::extract-design-md
Extract a comprehensive design system (DESIGN.md) directly from frontend source code — React, Vue, Svelte, Angular, plain HTML/CSS, or any web framework. Analyzes component files…
amElnagdy
Delegate Skills
amElnagdyagy-delegate
Delegate a coding task to the Google Antigravity CLI (`agy`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation…
amElnagdy
Delegate Skills
amElnagdyaider-delegate
Delegate a coding task to Aider (`aider`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Aider -…
amElnagdy
Delegate Skills
amElnagdyclaude-delegate
Delegate a coding task to a separate Claude Code CLI process or another Claude session as an implementer, then review its diff and land it yourself. Use only when the user explicitly asks…
deanpeters
Product Manager Skills
deanpeterscontext-engineering-advisor
Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably.
ljagiello
Ctf Skills
ljagielloctf-pwn
Provides binary exploitation techniques for CTF challenges. Use when you already have a vulnerable native target or service and need to turn memory corruption or low-level primitives into…
ljagiello
Ctf Skills
ljagielloctf-web
Provides web exploitation techniques for CTF challenges. Use when the target is primarily an HTTP application, API, browser client, template engine, identity flow, or smart-contract…
KKKKhazix
Khazix Skills
KKKKhazixleader
把一句话的想法拆成 AI agent 能独立跑完的目标任务书。用户说「帮我给 agent 写个目标」「帮我详细拆一下这个目标」「写个任务书/brief 给 agent」「写个 goal 提示词」「让 agent 自己跑这个项目」「把活分给几个 agent 并行」时使用。先进代码库实测、必要时联网调研，再一次性提问（≤5 个），产出一份 ≤4000 字符、直接粘进 /goal…
Google Labs
Stitch Skills
Google Labsstitch::manage-design-system
Manage design systems in Stitch using MCP tools. Includes retrieval of assets, creating/updating design systems in Stitch, and applying them to screens.
ljagiello
Ctf Skills
ljagielloctf-reverse
Provides reverse engineering techniques for CTF challenges. Use when the main job is to understand how a compiled, obfuscated, packed, or virtualized target works before exploiting or…
Coding skills, explained.
Also searched as: claude code skills, best claude code skills, software engineering skills, superpowers.
What are the best Claude skills for coding?
Right now the top-ranked coding skills on Alyn are Diagnosing Bugs (Matt Pocock), Ask Matt (Matt Pocock), Code Review (Matt Pocock). Rankings combine GitHub stars, installs, freshness and depth, and update live.
What are the best Claude Code skills?
By stars and installs: Superpowers (obra), Matt Pocock's skills, Addy Osmani's agent-skills, gstack (Garry Tan) and Caveman. Alyn ranks them live.
How many skills should I install?
Start with one workflow pack and two or three task skills. Each skill only costs about 100 tokens until it is used, but overlapping skills can confuse which one runs.
How do I install a coding skill?
Run npx skills add owner/repo in your project, or copy the folder with SKILL.md into ~/.claude/skills. Every skill on this page has a ready-to-copy command.
More in Build
Coding skills for your agent