Superpowers
Leading#1 in Skillshigh confidence
The recognized leader of the Claude Code skills ecosystem (~260k★): composable SKILL.md skills chaining brainstorming, planning, subagent-driven TDD and code review.Our read
Why it ranks #1
~260.4k GitHub stars make Superpowers the most-adopted coding-skill framework by a wide margin; it is also the first recommendation in the cited 2026 Claude Code skills roundup.Here is the catch
rigid workflow can feel heavy for small or exploratory tasks
many coordinated skills increase context and execution time
quality still depends on the host model following the process
Does this well
opinionated end-to-end engineering process rather than isolated prompts
very large community and broad agent compatibility
strong emphasis on tests, review and incremental execution
Pricing
Checked by hand on 2026-07-23. Prices in this category change often — if this looks wrong, it probably is.
Key features
brainstorming and specification skillssubagent-driven implementationtest-driven development workflowcode review and debugging skills
Sources we read
Quick facts
More in this area
The rest of the Skills column.- 2Anthropic Skills (official)Anthropic's official SKILL.md skill library (~164k★) — production-grade skills like webapp testing, MCP-server building and document editing that any agent can load.
- 3awesome-claude-skillsThe most-starred curated directory of Agent Skills (~70k★): one place to discover and install community SKILL.md skills for coding and beyond.
- 4Vercel Agent SkillsVercel's official SKILL.md collection (~29k★): React/Next.js performance and composition best-practices plus project auditing and instant deploys.
- 5agentskills.io (open standard + registry)The open Agent Skills spec and directory (~23k★) — discover SKILL.md skills that work across Claude Code, Codex, Gemini CLI, Cursor and more.
- 6Trail of Bits SkillsSecurity-focused SKILL.md skills from a top audit firm (~6k★) — CodeQL and Semgrep vulnerability detection wired into the agent's workflow. Niche but high-signal.
- 7DietrichGebert/ponytailRuleset that pushes coding agents down a ladder — reuse, stdlib, one-liner — before writing new code, plus over-engineering review and audit commands.