Helps Claude make deterministic, auditable choices about which agent and skills to use for a given task — replacing prose-scanning agent/skill selection with a typed scoring kernel.
★not rated 4 todayA
tokens not measured
originalMIT
Generative animation for Claude Code — flow fields, physarum, strange attractors, boids, reaction-diffusion, domain warping; GPU/WebGL2 GPGPU and raymarched SDFs; density-to-tone mapping, post-processing and art direction. Parameters are machine-verified, and a bundled capture script records the running result so the…
★not rated 4 3mo agoA
tokens not measured
originalMIT
Intelligence layer for Claude skills. Searches skills.sh, a trust-rated curated catalog and GitHub topics with blended ranking (relevance, project fit, trust, popularity), recommends what fits your project, returns ranked lists with pros, cons and customization advice, persists every decision, and migrates skills…
★not rated 4
changed 24d agoA
tokens not measured
originalMIT
A writing plugin that extracts useful points from long material—such as course outlines, scripts, transcripts, or notes—and turns them into promotional copy in the author’s style, usually as a Facebook post.
A Chinese-language toolkit for writing and completing an engineering-management master's thesis, with 21 skills covering research, writing, review, data presentation, and defense preparation.
Tutoring skill (teach) for learning a topic interactively — calibration, syllabus planning, and a Socratic/Feynman/drill teach loop. Named after Richard Hamming.
★not rated 4▲
+1 6mo agoA
tokens not measured
originalMIT
A testable knowledge base of real engineering practice — every skill backed by its own deterministic eval suite, checked automatically with this repository's own eval runner (smeval).
★not rated 4 29d agoA
tokens not measured
originalApache-2.0
The research-essay skill: turn an idea into a literature-grounded, tutorial-like standalone HTML essay, with the literature-fetching and build tooling that goes with it.
★not rated 4
changed 2mo agoA
tokens not measured
originalMIT
Strict multi-agent Supervisor for Claude Code: web-grounded anti-hallucination, expert coding/frontend implementation, independent judges, adversarial review, and final Stop release gate.
Useful AI things an engineer uses daily. Ships prodcheck (senior-engineer production review), prodtest (senior-QA test pass with Playwright), mergemain (context-aware merge of main into the current branch), shipit (clean commits and PRs, with or without AI attribution), and adonis-next-monorepo (scaffolds a verified…
★not rated 4
changed 17d agoA
tokens not measured
originalMIT