Several models on the same question at once — Claude sub-agents, OpenAI Codex and a cheap third via OpenCode. Review code (code-review), check whether the work is actually finished rather than finished-looking (check-if-done), brainstorm wide with a different model per cognitive frame (adhd), or just ask all of t.
★not rated 11▲
+2
changed 3d agoA
tokens not measured
originalMIT
Eliminates generic AI-generated design from any front-end you build or review, web or mobile. 20 reference modules: the slop taxonomy, personality axes and product registers, mobile and app-screen patterns, trust signals, data visualisation, a craft list, a pre-emit checklist and a worked example.
★not rated 12 1mo agoA
tokens not measured
originalMIT
Your UI, on its showreel — annotated screenshots, feature demos, flow walkthrough recordings (gif/mp4), terminal captures and before/after composites in one command each. Self-contained Chromium motor, deterministic placement, self-validated output; no MCP, cheap on tokens.
★not rated 11▲
+1 2mo agoA
tokens not measured
originalMIT
Create, edit, lint, render and preview Rive (.riv) animations without the Rive editor. Bundles the rive-mcp MCP server (30 tools), the rive-design-guidelines skill, and a rive-designer agent.
Local SQLite blackboard for cross-session context sharing between Claude Code agents. Captures plans, tracks progress via breadcrumbs, and enables staged subagent execution.
★not rated 11 7mo agoA
tokens not measured
AGPL-3.0
17 Bohrium platform skills: job/node/dataset/file/database/image/project management, knowledge-base, paper & patent search, PDF parsing, scholar search, SciencePedia wiki, scientific tools library, web search, sandbox, large knowledge model, and AI science mentor.
36 marketing skills for technical marketers and founders: ASO, CRO, copywriting, cold email, SEO, AI SEO, paid ads, ad creative, churn prevention, pricing strategy, referral programs, revenue operations, sales enablement, customer research, site architecture, and more.
Audit a dbt project for what an AI agent will get wrong if you point it at the data today: wrong metric, wrong table, missed rows, broken joins. Produces one evidence-backed report with blockers, verification queries, and a safe starting perimeter.
★not rated 11 14d agoA
tokens not measured
originalMIT
Security skills for Claude Code: secret scanning, Python SAST, prompt-injection testing, and HTTP, JWT, Dockerfile, CORS and dependency auditing. Runs on the standard library with no runtime dependencies.
★not rated 11 6d agoA
tokens not measured
originalMIT
i18n toolkit integration: MCP server, guardrails against hand-edited locale files, and an undefined-keys gate before stopping.
★not rated 11 5d agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: