Anthropic
The best AI skills for Claude Opus.
Claude Opus is Anthropic's most capable model for long, hard tasks. Skills keep it on track over hours of work and stop it from overbuilding.
npx alyn-cli add writing-plans subagent-driven-development dispatching-parallel-agentsAlyn picks for Claude Opus
Use planning and verification skills so long sessions end with working, tested code.
Jesse Vincent
Superpowers
Jesse Vincentwriting-plans
Use when you have a spec or requirements for a multi-step task, before touching code
Jesse Vincent
Superpowers
Jesse Vincentsubagent-driven-development
Use when executing implementation plans with independent tasks in the current session
Jesse Vincent
Superpowers
Jesse Vincentdispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Garry Tan
Gstack
Garry Tanplan-ceo-review
CEO/founder-mode plan review. (gstack)
Matt Pocockgrilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Matt Pocockcodebase-design
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more…
Jesse Vincent
Superpowers
Jesse Vincentverification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success…
Anthropic
Skills
Anthropicskill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to…
Why skills make Claude Opus better
Opus gains a lot from skills too: on SkillsBench it rose from 22.0% to 45.3% with curated skills. Skills that plan, delegate and verify matter most on long runs.
Where to use Claude Opus with skills
Top ranked AI skills right now
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…
Matt Pocockcodebase-design
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more…
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.
affaan-magent-self-evaluation
Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion…
affaan-mangular-developer
Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource)…
affaan-mbrand-discovery
Run a structured, resumable multi-session brand identity interview across 8 modules (purpose, positioning, audience, personality, voice, narrative, founder tension) using laddering, 5 Whys…
JuliusBrusseecaveman
Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or…
JuliusBrusseecaveman-commit
Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
Claude Opus FAQ
Do AI skills work with Claude Opus?
Yes. Skills are SKILL.md files your agent loads into the context, so they work with Claude Opus in Claude Code, Claude, Cursor.
What are the best AI skills for Claude Opus?
Alyn's picks for Claude Opus: writing-plans, subagent-driven-development, dispatching-parallel-agents, plan-ceo-review, grilling. Use planning and verification skills so long sessions end with working, tested code.
Why use skills with Claude Opus?
Opus gains a lot from skills too: on SkillsBench it rose from 22.0% to 45.3% with curated skills. Skills that plan, delegate and verify matter most on long runs.