Benchmarked Claude Code plugin that makes cheaper Claude models (Haiku, Sonnet, Opus) match Fable 5's output at a fraction of the token cost...
#anthropic
1104 posts
SKILL.md linter for Claude Code — auto-diagnose and fix skills against Anthropic best practices. npx pulser
Claude Code skill: parametric FDM 3D-print modeling with a headless view-screenshot-iterate loop (trimesh/manifold3d/build123d).
Deepdive skill for Claude Code — 9-phase pipeline, 105 report blocks, 29 search channels, 460+ stat sources, 39 APIs. Claims-ledger triangul...
🥋 Claude Code plugin that teaches programming while you vibecode — contextual explanations, micro-quizzes, and belt progression. Free & ope...
Evidence-based design playbooks for Claude Code — rules synthesized from 407 real product sites: page-type playbooks with pattern frequencie...
Test suites + deterministic Python for your agent skills' decision logic. Adversarial persona reviewers write the tests; the generated code...
Two composable Claude Code skills for design-to-code fidelity: extract exact specs from Figma, then verify the running web or mobile app mat...
Turn a one-line idea into a production-grade, copy-paste-ready AI image prompt for posters, landing and UI mockups, ads, game art, and logos...
Measured token routing for Codex, Claude Code, Hermes, GG Coder and any CLI agent. Less noise. Better judgment.
Open-source Claude Code skills that bring planning, building, and verification gates to agentic coding workflows.
A "trust, but verify" workflow of AI-agent skills: prompt to verified code, every step trackable and deviations logged — plus an autonomous...