Skip to content
alyn

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.

1747 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.

    Pack321k33MScore 97
    Details
  2. #2
    Matt Pocock

    Ask Matt

    Ask which skill or flow fits your situation. A router over the skills in this repo.

    Pack321k33MScore 95
    Details
  3. #3
    Matt Pocock

    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…

    Pack321k33MScore 95
    Details

  4. Jesse Vincent

    Superpowers

    #4
    Jesse Vincent

    Writing Skills

    Use when creating new skills, editing existing skills, or verifying skills work before deployment

    Pack316k3.9MScore 94
    Details

  5. Jesse Vincent

    Superpowers

    #5
    Jesse Vincent

    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…

    Pack316k3.9MScore 92
    Details

  6. Jesse Vincent

    Superpowers

    #6
    Jesse Vincent

    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…

    Pack316k3.9MScore 92
    Details
  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…

    Pack119k4.8MScore 90
    Details
  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…

    Pack301k1.7MScore 89
    Details
  9. #9
    affaan-m

    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…

    Pack301k1.7MScore 89
    Details
  10. #10
    affaan-m

    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…

    Pack301k1.7MScore 89
    Details

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 1747 coding skills.

Alyn ScoreInstallsStarsUpdated
47
Spielewoy

ap-implementer

Report the compatibility redirect to `ap-worker`; this retired role cannot perform new work.

Pack1.2k327Coding
47
Spielewoy

ap-intake

Report the compatibility redirect to `C0`; this retired role cannot perform new work.

Pack1.2k327Coding
47
Spielewoy

ap-janitor

Report the compatibility redirect to `C0`; this retired role cannot perform new work.

Pack1.2k327Coding
47
Spielewoy

ap-juror

Report the compatibility redirect to `ap-independent-checker`; this retired role cannot perform new work.

Pack1.2k327Coding
47
Spielewoy

ap-manager

Report the compatibility redirect to `ap-work-group-manager`; this retired role cannot perform new work.

Pack1.2k327Coding
47
Spielewoy

ap-planner

Report the compatibility redirect to `ap-roadmap-author`; this retired role cannot perform new work.

Pack1.2k327Productivity
47
Spielewoy

ap-preflight-probe

Report the compatibility redirect to `C0`; this retired role cannot perform new work.

Pack1.2k327Coding
47
Spielewoy

ap-re-anchor

Report the compatibility redirect to `C0`; this retired role cannot perform new work.

Pack1.2k327Coding
47
Spielewoy

ap-researcher

Report the compatibility redirect to `ap-worker`; this retired role cannot perform new work.

Pack1.2k327Research
47
Spielewoy

ap-reviewer

Report the compatibility redirect to `ap-independent-checker`; this retired role cannot perform new work.

Pack1.2k327Code review
47
mhattingpete

code-auditor

Performs comprehensive codebase analysis covering architecture, code quality, security, performance, testing, and maintainability. Use when user wants to audit code quality, identify…

Pack6946.3kCoding
47
mhattingpete

code-refactor

Perform bulk code refactoring operations like renaming variables/functions across files, replacing patterns, and updating API calls. Use when users request renaming identifiers, replacing…

Pack6946.3kCoding
47
mhattingpete

codebase-documenter

Generates comprehensive documentation explaining how a codebase works, including architecture, key components, data flow, and development guidelines. Use when user wants to understand…

Pack6946.3kCoding
47
qufei1993

dsh-doc

创建或维护工程文档、设计决策、事故复盘、归档提案或产品迁移指南时使用，保留事实依据、实际备选方案和准确状态。

Pack1.9k28Coding
47
qufei1993

dsh-error-handling

实现或审查错误传播、部分成功、结果未知、恢复、重试、取消或失败反馈时使用，明确状态保证和错误处理责任。

Pack1.9k28Coding
47
qufei1993

dsh-find-simplifications

用户明确要求审查或实施简化时使用，识别不必要的抽象、重复状态和兼容机制，并验证受支持行为得到保留。

Pack1.9k28Coding
47
qufei1993

dsh-pre-push-checks

在交付或推送前验证改动时使用，核实项目必需检查、当前构建产物和真实用户行为，区分通过、失败、未运行与环境阻塞。

Pack1.9k28Coding
47
qufei1993

dsh-speed-up-perf

调查性能问题或优化实际测量的用户路径时使用，建立优化前后对照，保留正确性、失败行为和真实运行证据。

Pack1.9k28Coding
47
Microsoft

edit-agent

Edit Copilot Studio agent settings, instructions, or configuration. Use when the user asks to change agent instructions, display name, conversation starters, AI settings, or generative…

Pack490331Coding
47
mhattingpete

git-pushing

Stage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also…

Pack6946.3kCoding

badlogic

Pi Skills

47
badlogic

gmcli

Gmail CLI for searching emails, reading threads, sending messages, managing drafts, and handling labels/attachments.

Pack2.7k4.2kCoding
47
Prat011

raffle-winner-picker

Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.

Pack1.9k987Coding
47
mhattingpete

review-implementing

Process and implement code review feedback systematically. Use when user provides reviewer comments, PR feedback, code review notes, or asks to implement suggestions from reviews.

Pack6946.3kCoding

arpitg1304

Robotics Agent Skills

47
arpitg1304

robotics-software-principles

Foundational software design principles applied specifically to robotics module development. Use this skill when designing robot software modules, structuring codebases, making architecture…

Pack4012.1kCoding

arpitg1304

Robotics Agent Skills

47
arpitg1304

ros1

Best practices, design patterns, and common pitfalls for ROS1 (Robot Operating System 1) development. Use this skill when building ROS1 nodes, packages, launch files, or debugging ROS1…

Pack4012.1kDesign

arpitg1304

Robotics Agent Skills

47
arpitg1304

ros2

Comprehensive best practices, design patterns, and common pitfalls for ROS2 (Robot Operating System 2) development. Use this skill when building ROS2 nodes, packages, launch files…

Pack4012.1kDesign

Jesse Vincent

Superpowers Skills

47
Jesse Vincent

Systematic Debugging

Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions.

Pack76017kCoding

Jesse Vincent

Superpowers Skills

47
Jesse Vincent

Test-Driven Development (TDD)

Write the test first, watch it fail, write minimal code to pass

Pack76017kTesting
47
mhattingpete

test-fixing

Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or…

Pack6946.3kTesting

Jesse Vincent

Superpowers Skills

47
Jesse Vincent

Using Git Worktrees

Create isolated git worktrees with smart directory selection and safety verification

Pack76017kCoding
46
Prat011

changelog-generator

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release…

Pack1.9k987Automation
46
Microsoft

chat-sdk

Send a message to a Copilot Studio agent via the Copilot Studio Client SDK (M365). Use for agents with integrated auth (Entra ID SSO). Requires an App Registration Client ID.

Pack490331Coding
46
Microsoft

directline-chat

DEPRECATED: Use /copilot-studio:chat-with-agent instead — it auto-detects DirectLine vs M365 mode. This skill is kept for backwards compatibility only.

Pack490331Coding
46
mhattingpete

file-operations

Analyze files and get detailed metadata including size, line counts, modification times, and content statistics. Use when users request file information, statistics, or analysis without…

Pack6946.3kCoding

staruhub

ClaudeSkills

46
staruhub

pair-programming

结对编程搭档。当用户要求"边写边审"、"结对编程"、"写完自己 review 一遍"、"高可靠地实现"，或明确希望代码交付时附带自我审查意见时使用。交付代码的同时输出结构化审查（正确性/安全/性能/可读性/健壮性五维度），重点捕捉 AI 生成代码的特有缺陷。不用于：对已有 PR 的正式评审（用 code review 流程）、安全专项扫描（用…

Pack7361.4kCoding

Jesse Vincent

Superpowers Skills

46
Jesse Vincent

Preserving Productive Tensions

Recognize when disagreements reveal valuable context, preserve multiple valid approaches instead of forcing premature resolution

Pack76017kCoding

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

Best frontend skills Best web development skills Best backend skills Best code review skills Best testing skills Best devops skills Best security skills Best ai engineering skills Best mcp skills Best mobile skills Best game development skills

Coding skills for your agent

Claude CodeClaudeCursorCodexGemini CLIGitHub CopilotWindsurf

Built a coding skill? Get it ranked.

Submit a skill