Project configuration and setup tools including CLAUDE.md creation and maintenance with ground truth validation. The maintain flow preserves existing references and information by default: removal requires cross-verification proving the content false or obsolete (else: keep, extract to docs/, or ask the user). It…
★not rated 9
changed 16d agoA
tokens not measured
originalMIT
Progressive Web App expert for the 2025-2026 baseline. Covers Web App Manifest (id, displayoverride, scopeextensions, handlelinks, filehandlers, sharetarget), Service Workers (Workbox 7 / Serwist), Web Push (VAPID, RFC 8030/8291/8292, Declarative Push for Safari 18.4+), install flows (beforeinstallprompt, Window C.
★not rated 9
changed yesterdayA
tokens not measured
originalMIT
React performance optimization, React 19 API adoption, state management audit, bundle analysis, re-render detection, and Vercel best practices checklist.
★not rated 9
changed yesterdayA
tokens not measured
originalMIT
Workspace tidying decided by the filesystem and git alone, with no source comprehension anywhere in it: filesystem garbage and shell-redirection artifacts, generated artifacts tracked in git (checked against publication conventions before anything is proposed for untracking), .gitignore completeness per ecosystem and…
★not rated 9
changed yesterdayA
tokens not measured
originalMIT
Deep web research (any topic) modelled on the commercial deep-research products: /research:team-research clarifies scope only when needed, shows a plan of sub-questions for approval, spawns one iterative deep-researcher per sub-question in parallel, verifies contradictions with quick-searcher, synthesizes a long-form…
★not rated 9
changed yesterdayA
tokens not measured
originalMIT
Unified evidence-aware code, team and PR review with scope-selected available domain knowledge and canonical React, TypeScript and platform specialists. One preparation, delivery ledger, verification panel and report; application subtraction, test quality, structural entropy and workspace hygiene reuse their canonical.
★not rated 9
changed yesterdayA
tokens not measured
originalMIT
Tauri 2 desktop and mobile development - IPC optimization, Rust backend patterns, cross-platform builds, and React integration for high-performance apps.
★not rated 9 todayA
tokens not measured
originalMIT
Durable project knowledge: instructions, audience-specific guides, implementation drift and README maintenance. Reuses existing documents, plans ownership before writing and preserves evidence, intent and author voice. Audit-only methods are callable independently by the project lifecycle.
★not rated 9
changed todayA
tokens not measured
originalMIT
Complete AI development lifecycle: consultant handover, a guided Senior Maintainer campaign, coherence assessment, evidenced repair, implementation, verification and consolidation. Uses canonical specialist methods, exact run identities and honest coverage.
★not rated 9
changed yesterdayA
tokens not measured
originalMIT
Create professional editable PowerPoint presentations through SlidePoise, work with native Excel formulas, tables and charts, and create, read or edit Word documents with styles, tables and sections. Includes runtime discovery and document preservation evidence.
★not rated 9
changed yesterdayA
tokens not measured
originalMIT
Ultra Nerd: bounded multi-model problem solving with independent proposals, reciprocal challenges and evidence-backed synthesis. Explicit opt-in for difficult tasks with increased token consumption.
★not rated 9 todayA
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: