vibe-plugins

Vibe Cartographer — plot your course from idea to shipped app. Spec-driven development delivered as eight slash commands: onboard, scope, prd, spec, checklist, build, iterate, reflect.

AI-powered documentation gap analyzer. Scans your codebase, classifies your project, identifies missing technical documentation, and generates professional docs from your existing artifacts.

Test analyzer and generator for vibe-coded apps. Classifies your app by type and maturity tier, audits existing coverage honestly (no cherry-picked denominators), and generates the tests that actually matter proportional to deployment risk.

Research feeder for vibe-thesis projects. Discovers cutting-edge thesis topics, gathers primary sources / opposing positions / methodological precedents via web search, and emits research notes + a BibTeX bibliography in vibe-thesis-shaped subdirectories ready to drop into ThesisStudio. Optional Smart Brevity blog adapter for BlogStudio.

Vibe Thesis — scaffold and co-author thesis-shaped artifacts (PDF, HTML, lay-version) with Claude Code. Install, say 'scaffold a vibe thesis project,' get a styled PDF skeleton plus a working render pipeline in roughly 30 minutes.

Bootstrap a 626Labs-pattern CLAUDE.md for any repository. The keystone is the load-bearing structural file — every agent decision in the repo rests on it. Inventories the repo, confirms scope, and produces a CLAUDE.md adapted to the repo type (code platform / marketing site / long-form writing / mixed).

Post-ship product iteration — pick a mode (feature-add, competitive, ux-polish, bug-bash), ship one PR. Ingests competitor changelogs, framework releases, and your feedback.md. Maintains your Atlas. Sibling to vibe-cartographer.

Take it with you. Capture a feature out of one repo as a portable bundle; plant it into another and adapt to the destination stack.

Vibe Insights — the deep retrospective for your Claude Code work. Coverage, where-was-I recall, token/cost (incl. the cache reveal), trends, how-you-work, ranked open threads, decisions, languages, per-session friction/satisfaction/outcome, and a synthesized narrative read. Across your full history and every machine you code on. Personal by default; optionally keep chosen sources or repos local-only. No telemetry, all local. MCP-agnostic decisions overlay.

Session wrap-up that reads the breadcrumb trail your toolkit already left — not a cold reconstruction. Multi-repo aware: surfaces what shipped across every repo the session touched, what's uncommitted, and what's unpushed, then gates commit + push on the current repo only (read wide, mutate narrow).