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.
Matt Pocockdiagnosing-bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
Matt Pocockask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
Matt Pocockcode-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…
Jesse Vincent
Superpowers
Jesse Vincentwriting-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Jesse Vincent
Superpowers
Jesse Vincentbrainstorming
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…
Jesse Vincent
Superpowers
Jesse Vincentdiagnosing-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…
JuliusBrusseecaveman-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…
affaan-magent-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…
affaan-magent-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…
affaan-mandroid-clean-architecture
Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns. Use when structuring…
JuliusBrusseecaveman-compress
Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Sends the file's text to the configured model provider. Trigger…
Addy Osmaniconstraint-driven-development
Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they…
nextlevelbuilderdesign-system
Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic…
Anthropic
Skills
Anthropicdiscernment-nudge
After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or…
JuliusBrusseecaveman-setup
Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.
Corey Haines
Marketingskills
Corey Hainesfree-tools
When the user wants to plan or build a free tool as marketing, or asks whether a tool idea is worth building or which one to pick: calculators, graders, generators, and other interactive…
GitHub
Awesome Copilot
GitHubacquire-codebase-knowledge
Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me…
Addy Osmaniidea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before…
Addy Osmaniperformance-optimization
Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals…
Anthropic
Skills
Anthropictheme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any…
GitHub
Awesome Copilot
GitHubagent-architecture
Design AI agent architectures through requirements discovery, or audit and diagnose architectural flaws in existing agents. Architecture only; excludes implementation and general code…
tt-a1iarchify
Create validated architecture, workflow, sequence, data-flow, lifecycle/state, ERD, class, tree, timeline, and waterfall diagrams as explorable standalone HTML with dark/light themes…
tt-a1iarchify-tuning
Improve Archify diagram accuracy, visual quality and complete authoring speed with fewer repairs. Use for generation experiments or evaluating changes to layout, routing, diagnostics…
wshobson
Agents
wshobsonarchitecture-patterns
Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use this skill when designing clean architecture for a new…
GitHub
Awesome Copilot
GitHubarize-prompt-optimization
Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven…
wshobson
Agents
wshobsonnft-standards
Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or…
Shubhamsabooproject-graveyard
Scans the developer's machine for dead side projects, autopsies each one from its git history (died at the payments wall, killed by a newer project, finished but never shipped), surfaces…
morlutorea-analysis-optimization
Optimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query…
morlutorea-ci-tests-audit
Audit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary…
morlutoreverse-engineer-anything
Reverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live…
wshobson
Agents
wshobsonteam-communication-protocols
Structured messaging protocols for agent team communication including message type selection, plan approval, shutdown procedures, and anti-patterns to avoid. Use this skill when…
Shubhamsaboocommit-archaeologist
Reconstructs why code exists from local git history, including the introducing commit, later changes, current authors, repeated companion files, and likely intent. Use when the user asks…
Garry Tan
Gstack
Garry Tandesign-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them; --build checks UI while you build it. (gstack)
Vercel
Skills
Verceltriage
Identify focused, evidence-backed skills CLI bug fixes worth quuu's attention.
sickn33
Agentic Awesome Skills
sickn33access-review
Conduct periodic access reviews and certifications. Implement access governance and recertification workflows. Use when managing access compliance.
sickn33
Agentic Awesome Skills
sickn33active-directory-attacks
Assess Active Directory attack paths using scoped configuration review and controlled synthetic lab validation; identify prerequisites, evidence and mitigations.
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