🔌
Plugins
Loading...
Showing 30 of 23013 results
Search, save, and surface your Readwise Reader library via MCP server with OAuth, DuckDB storage, and full-text search
Real estate broker toolkit for Qobrix CRM and WhatsApp (WaSender). Manage listings, leads, viewings, follow-ups, send property selections, run resale-reactivation campaigns, import listings from portals, update prices from developer PDFs, and monitor agent lead inactivity.
Comprehensive real estate agent assistant for buyer representation, seller representation, listing management, offer negotiation, transaction coordination, and closing support — delivering a world-class client experience from first showing to final closing across residential and investment real estate
全能房地产经纪助手，覆盖买方代理、卖方代理、房源管理、报价谈判、交易协调与交割支持——从首次看房到最终交割，为住宅及投资房产提供世界级的客户体验
Điều phối nghiệp vụ Chủ đầu tư bất động sản: RE-HQ, Legal, Investment & Finance, Market Research, Project & Design (due diligence, deal structuring, legal drafting).
Bundles the realfavicon-mcp MCP server: generate favicon assets and HTML from a master image, audit a live page's favicon setup, and query the RealFaviconGenerator change-log.
Stress-tests your ideas, scans the real market, surfaces failure modes, and tells you where a project is actually weak — without the reflexive cheerleading. On by default.
Living Obsidian vault for project knowledge. Core: forge → phase → manifest. Capture, update, query.
Realtime-collaboration-engineering team — 3 agents (collab-architect, sync-engine-engineer, presence-and-transport-engineer) for multiplayer / collaborative-editing systems (Figma/Notion/Docs): the merge model (CRDT vs OT vs last-writer-wins, by data shape), the shared-document model, offline edits + reconnection/merge, presence & awareness kept OUT of the persisted document, transport (WebSocket vs WebRTC, client-server vs SFU vs mesh), and scaling the sync server (doc sharding, snapshots/compaction, access control at the boundary). 5 skills, a knowledge bank (CRDT-vs-OT + transport/topology Mermaid trees, durable consistency concepts, a dated 2026 tooling map), 8 best-practices, 4 templates, 3 commands, 1 advisory hook. Engineering craft, not legal/product advice; library specifics carry a date + verify-at-use. Seams: UI -> frontend-engineering; sync service/store -> backend-engineering; op-log fan-out -> data-streaming-engineering; latency -> performance-engineering. Requires ravenclaude-core@>=0.7.0.
Structured reasoning skills for Claude Code: atom-of-thought decomposes complex multi-part problems into independent and dependent sub-questions before answering; confess produces an honest audit of just-completed work, surfacing confidence levels, shortcuts, and unverified assumptions; postmortem turns a finished session into a root-cause analysis, a minimum-round-trip replay, and proposed fixes.
Automated rebase onto trunk with conflict prediction, resolution, and quality gate verification
Coach • Coaches HVAC and plumbing wholesale distributors through vendor rebate reconciliation — identifying enrolled programs, computing earned vs. received, surfacing leakage, and drafting collaborative claim language. Paste program terms and accruals, get a one-shot reconciliation the user can act on manually.
Use Reboot to build AI Chat Apps (MCP Apps) for ChatGPT, Claude, VSCode, Goose, and others.
Generate a personal Claude Code impact report from your local ~/.claude/projects transcripts, cross-referenced against your local git history — what you shipped, which projects it went to, and each project's share of your usage — for justifying usage to a manager or a self-review. Reads your session transcripts and runs read-only git commands in the projects they mention; mining is local and only a small aggregate summary (counts and project names) is sent to write the report, which is saved to your home directory and published nowhere.
Automatically reviews and fixes Claude's code changes using a separate Claude instance in a git worktree after commits. Two-phase pipeline: code correctness (Phase 1) then functionality verification (Phase 2).
Operational memory for coding agents: recall past mistakes before you act, encode the lesson when something goes wrong.
Evaluate an AI product idea across outcomes, hypotheses, risks, and positioning.
First-pass code review — architecture mapping, bug brainstorming, function micro-analysis, and deep context building.
Recover Claude Code sessions after an Anthropic API output-classifier false positive (the "cyber-related safeguards" / "appears to violate our Usage Policy" hard failure). A JSON-aware .jsonl log surgeon that surgically removes the triggering message + refusal turn and re-stitches the parentUuid chain so the session resumes cleanly, cleans accumulated refusals across old sessions, and installs a per-repo CLAUDE.md framing guard to stop recurrence.
Comprende una aplicacion ya desarrollada aunque no tenga documentacion (vibe-coding): inventaria el codigo, extrae que hace con evidencia archivo:linea, reconstruye la linea de base de requisitos en formato .dev/requirements/ compatible con toda la suite, reporta el estado real y arma el cuestionario de decisiones para el dueño.
Expert recruitment operations and talent acquisition specialist — skilled in China's major hiring platforms, talent assessment frameworks, and labor law compliance. Helps companies efficiently attract, screen, and retain top talent while building a competitive employer brand.
Skills and component specifications for component selection, design token application, and component implementation in Recursica.
Use when needing to know which Red Hat team owns a Konflux-related repository (konflux-ci, hermetoproject, conforma orgs), which JIRA project or component to file issues against, or how the Red Hat Konflux engineering organization maps to the codebase.