Multi-quest orchestrator for Claude Code. Coordinates parallel quests via agent teams, with structured research-plan-implement lifecycles and isolation via worktrees.
★not rated 5
changed 9d agoA
tokens not measured
originalApache-2.0
Daily tech news skill for the vatt-ghern public blog (Eleventy + Cloudflare Pages). Drafts one roundup + several deep-story HTML posts per day, opens a PR for review.
★not rated 5 yesterdayA
tokens not measured
originalMIT
Build and maintain Claude Skills representing your favourite experts' worldviews. Scrapes LinkedIn (Apify), RSS, podcast snips, and other sources you configure; judges each excerpt for signal vs noise; distills into compact Claude Skills with frameworks, principles, and voice samples. Invoke via…
★not rated 5 3mo agoA
tokens not measured
originalMIT
Socratic-method tutor for Claude Code. Asks questions, reveals hints in layers, refuses to give you the answer until you've made the discovery yourself.
★not rated 5 3mo agoA
tokens not measured
originalMIT
Project-wide living documentation for AI-assisted codebases. Maintains one source of truth per user-visible feature in a hierarchical feature tree, with drift detection and bidirectional code-doc linkage.
★not rated 5 3mo agoA
tokens not measured
originalMIT
Skills for building NestJS bounded contexts with Hexagonal Architecture, DDD, and CQRS patterns. Covers domain modeling, application layer, infrastructure wiring, presentation, full TDD workflow, and architecture review.
★not rated 5 1mo agoA
tokens not measured
originalMIT
A plugin that organizes software development into a fixed PM, architect, developer, and QA cycle, with separate files for requirements, design, implementation, and acceptance.
★not rated 5
changed yesterdayA
tokens not measured
originalMIT
Surface your unknowns (unknown unknowns / unknown knowns) before, during, and after implementation — eight lightweight techniques, Cartographer mode (a quadrant-coverage-gated, regret-weighted interview backed by a lifecycle-persistent unknowns ledger), and four companion agents: blindspot-scout, prototype-smith…
★not rated 5 2mo agoA
tokens not measured
originalMIT
Orchestration (insistir, constatar, remoto), prompting (metaprompt), knowledge compounding, file-based TODOs, an illustrated Claude Agent SDK wizard, and OpenAI tooling (askcodex, image-to-frontend) as one Claude Code plugin.
★not rated 5
changed 12d agoA
tokens not measured
originalMIT
A command entry point for Supathink, a system for declaring thinking methods, asking multiple models to review a problem, and checking results before delivery.
★not rated 5 2mo agoA
tokens not measured
originalApache-2.0
Rules your coding agent physically cannot ignore. A Claude Code plugin (and LLM-agnostic rule pack) that stops reactive patching, guessed citations, surface-level fixes and premature "done" claims by intercepting the agent's own tool calls — PreToolUse denies the edit before it lands, and a nine-layer Stop gate…
Turn a video you already have into a complete scroll-scrubbed hero page — Next, Nuxt, Astro or plain HTML. The clip advances frame by frame as the visitor scrolls, with copy beats fading in over it. Measures every frame while encoding it, so the page background matches each frame's own border color and each block of…
★not rated 5 1mo agoA
tokens not measured
originalMIT