World news API in Portuguese — query Daily Journal's public API for current events, politics, economy, business, finance, technology, science, and sports. Aggregated coverage with cited source outlets.
★not rated 10 22d agoA
tokens not measured
originalMIT
Drive a live Rocq/Coq proof session through coqtail-mcp. Bundles the skill (server mechanics + proof recipes) and four named subagents (proof-repair, admitted-filler-deep, axiom-auditor, proof-golfer).
Production-quality Elixir development with enforced precommit gates, TDD workflows, and escalation-based patterns for OTP, Phoenix LiveView, and distributed systems.
A plugin containing reusable Chinese-language project-development skills based on a structured software delivery process. It covers project setup, planning, feature development, and final delivery.
★not rated 10 1mo agoA
tokens not measured
originalApache-2.0
Official Upstage AI bundle for Claude Code — Solar models, document processing (OCR, parse, classify, extract), schema generation, Studio agent workflows, multi-API builder for webapps, and the BotMadang community client. One install activates all 9 skills with auto-trigger by description.
★not rated 10 4mo agoA
tokens not measured
originalMIT
Presenter Agent for talks and pitches. Takes raw sources (PDFs, papers, chat exports, URLs, images) through an 8-step workflow — Frame → Collect → Corpus → Draft → Review → Polish → Render → Learnings — to a structured outline you edit (draft.md), a polished deliverable (final.md), and a self-contained HTML/Reveal.js…
★not rated 10
changed 11d agoA
tokens not measured
originalMIT
Discipline rules for long-running agent tasks — recurring loops and run-until-done goals. Checkpoint to .loopgoal/state.json, isolate each iteration in a fresh subagent, and write an explicit exit condition.
★not rated 10 2mo agoA
tokens not measured
originalMIT
Toolkit for authoring and validating Claude Code skills and agents via a real script-backed check (description cap, PII, em-dash, Task completeness, vague ask-user prose), not a self-scored rubric. Auto-invoke on 'create skill', 'validate skill', 'validate agent'.
★not rated 10 todayA
tokens not measured
originalMIT
Automatic context engineering — observes your coding sessions and generates rules, suggestions, skills, and hooks so Claude gets smarter on your codebase over time.
★not rated 10 5mo agoA
tokens not measured
originalMIT
A Chinese-language plugin that provides a method for researching and designing website front ends. It includes guidance on visual direction, avoiding generic AI design patterns, image-generation prompts, and workflows for tools such as v0, Bolt, and Lovable.
★not rated 10 2mo 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: