Skip to main content

Ecosystem picks

What is worth taking from the big catalogs, verified 2026-09-20.

Star counts in this space are noisy — several repos with six-figure counts have thin commit histories. Ordered by usefulness to this stack, with the count as context rather than as ranking.

Installed here

SourceWhat you gotWhy
obra/superpowers15 skills: test-driven-development, systematic-debugging, brainstorming, writing-plans, verification-before-completion, using-git-worktrees, dispatching-parallel-agents, subagent-driven-development, receiving-code-reviewThe most complete methodology set in the ecosystem. verification-before-completion alone — "evidence before assertions, always" — is worth the install
addyosmani/agent-skillscode-review-and-quality, debugging-and-error-recovery, security-and-hardening, performance-optimization, observability-and-instrumentation, incremental-implementation, deprecation-and-migration, spec-driven-development, frontend-ui-engineering, ci-cd-and-automation, git-workflow-and-versioning, doubt-driven-development, source-driven-development, context-engineeringProduction engineering, broad and consistent. The closest thing to a senior-engineer checklist set
anthropics/skillsdocx, pptx, xlsx, pdf, mcp-builder, skill-creator, canvas-design, webapp-testing, frontend-design, artifacts-builderOfficial. mcp-builder and skill-creator are the meta-tools — they build the things this kit is made of
mattpocock/skillstdd, pr, research, prototype, wizard, codebase-design, domain-modeling, diagnosing-bugs, resolving-merge-conflicts, setup-pre-commit, migrate-to-shoehornTypeScript-shaped and very active. wizard is unusual and good: it generates an interactive bash wizard for steps only a human can do
RobMitt/grill-me-skillgrill-me, grillingRelentless interview until shared understanding. grill-with-docs leaves ADRs and a glossary behind
elayadesign/ai-design-skillslanding-page-designLayout, conversion copy, and strict visual rules
dmmulroy/anti-slopinstall-anti-slopOxlint rules that reject low-evidence code — the linter equivalent of "prove it"
s1dashu/ip-as-logo-skillip-as-logoCharacter/logo generation
LukasNiessen/kubernetes-skillkubernetes-skillPrevents K8s hallucinations: insecure defaults, resource starvation, privilege sprawl, API drift. EKS/GKE/AKS/OpenShift
firecrawl/anydocconvert-documents-to-markdownWord, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, PDF → Markdown
npx -y skills@latest list # what is installed, and from where
npx -y skills@latest update -y # or /skills-sync

Worth adding next

SourcePickWhy
wshobson/agents ★40kSubagent marketplaceThe gap in this kit: 3 subagents against dozens there
BagelHole/DevOps-Security-Agent-Skills10–15 of 146AWS/Azure/GCP, Terraform, Helm, ArgoCD GitOps, CIS benchmarks, incident response, compliance. Install selectively — 146 descriptions is a real context tax
a vendored third-party toolkit~58 not yet takenspeckit-* (12 skills), openspec-lifecycle, compass-* bootstrap tooling, agent-teacher, project-memory, long-running-task, work-splitting, architecture-advisor, gen-docs, figma-mcp-frontend
nizos/tdd-guard ★2.3kHook-enforced TDDBlocks implementation until a failing test exists — tdd as a hook, not a suggestion

MCP servers

From punkpeye/awesome-mcp-servers ★95k:

ServerWhy
github/github-mcp-serverOfficial. Issues, PRs, Actions, code search
microsoft/playwright-mcpReal browser. The agent runs the test it wrote
headroomlabs-ai/headroom ★73kCompresses tool output before it enters context — attacks the >150k problem directly
DeusData/codebase-memory-mcp ★44kStructural code index
GLips/Figma-Context-MCPFigma layout as data, not screenshots
grafana/mcp-grafanaAlready in use — see my servers

Catalogs themselves

ListUse it for
hesreallyhim/awesome-claude-code ★54k21 categories. The best-curated overall
ComposioHQ/awesome-claude-skills ★75kSkills specifically
VoltAgent/awesome-agent-skills ★35k1000+, breadth over curation
sickn33/agentic-awesome-skills ★47kLocal agent-first control plane
github/awesome-copilot ★37kInstructions, agents, skills, configs for Copilot
agentation.comAgent tooling directory, broader than Claude

Skip

RepoWhy
multica-ai/andrej-karpathy-skills ★199kIt is a single CLAUDE.md, no commits since April. Read it for ideas; there is nothing to install
Anything with six figures and three commitsThe counts in this ecosystem do not survive scrutiny. Open the commit history before trusting one

How to evaluate before installing

A skill is a prompt running with your tool permissions. Read SKILL.md first — same reflex as reading a shell script before | bash.

  1. allowed-tools — does it ask for more than its job needs?
  2. Network or out-of-project writes — why?
  3. Commit history — real iteration, or one bulk drop?
  4. Description quality — a vague description means it fires at random, or never