Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Universal Multi-Agent Swarm Exposer over Model Context Protocol for IDEs
MCPLink onlyFew stars
AI-powered financial fraud detection using MCP + Claude Opus 4.8
MCPLink only★ 1Few stars
Advisor Strategy skill for AI coding agents, spawns a stronger model as strategic advisor for architecture, security, debugging, and performance. Works with Claude Code, Cursor, Gemini CLI, Cline, Cod
SkillLink only★ 3Few stars
AI-assisted plugin review add-on for the WordPress Plugin Check plugin. Uses OpenRouter (default: Claude Opus 4.7).
MCPLink only★ 1Few stars
Replica of Claude Opus 4.8's dynamic workflow architecture - team-based adversarial convergence with parallel workers and dedicated verifiers
SkillLink only★ 1Few stars
A Claude Code skill that brings Claude Fable 5's engineering discipline to Claude Opus 4.8 and other models: act decisively, ground progress claims in tool output, verify with fresh context, avoid ove
SkillLink only★ 3Few stars
See what your code actually means. In 3D. Claude Opus 4.7 hackathon entry.
MCPLink only★ 1Few stars
Read-only booking info for Opus Lumiere photography, London: services, prices, availability.
Hosted by authorNo licenseFew starsNo key
Autonomous AI coding agent — scan, plan, execute, review & self-evolve. Powered by Claude Opus + Codex with dual review, meta-prompt reflection, and MCP plugin integration.
MCPLink only★ 2Few stars
Claude Code skill: equipo Sonnet(PM)/Opus(dev)/Haiku(QA+adversarial) con contrato de tests congelados
SkillLink only★ 1Few stars
Agent-driven geospatial analysis: Claude Opus 5 orchestrating QGIS through the Model Context Protocol to audit and correct a multi-criteria flood model.
MCPLink onlyFew stars
Claude Code skill: strategic audit with dual-model C-level council (Claude Opus + GPT-5.4 in parallel)
SkillLink onlyFew stars
MCP control plane kernel — routes intents through policy, federates upstream MCP servers, and reasons with Claude Opus 4.7. Named after IBM Project Stretch (IBM 7030, 1961).
MCPLink onlyFew stars
Release channel for TheAuditor — see blog.theauditortool.com
MCPLink only★ 549
Opus-orchestrated coding pipeline: Claude Code (Opus/Sonnet) plans and reviews, delegates well-specified, mechanical work to Command Code's cheaper models (DeepSeek, MiniMax) via a custom subagent, wi
SkillLink onlyFew stars
Turn one long video into vertical (9:16) captioned shorts, 100% local. A home-made Opus Clip as a Claude Code skill.
SkillLink only★ 1Few stars
An agent skill that plays ARC-AGI-3. One rule: say what an action will do before you spend it. Claude Code on Opus 5 finished all 25 public games at 100.00 RHAE in 7,645 actions.
SkillLink only★ 89
A Claude Code skill that builds polished Excel financial models via a three-agent team: Architect (Opus) designs the blueprint, Coder (Sonnet) writes Python/openpyxl, Challenger (Opus) stress-tests fo
SkillLink only★ 5
Motion designing especially for opus 5.5, to create premium, stunning motion videos
SkillLink only★ 6
use opus as your brain,and use minimax as your cheap hands。
SkillLink only★ 4Few stars
Agent-team workflow lifecycle for Claude Code: brief a team of Opus subagents, verify cross-model (codex 5.5/5.4 + Opus + Fable), ship reviewed results. deep-work + agent-team + deep-scan + loop-forge
SkillLink only★ 1Few stars
Run Claude Fable 5 on Opus 4.8 in Claude Code. The Mythos-class model pulled by export controls — brought back as a native agentic distillation (FABLE_CODE.md), measured playbook, verification hooks,
MCPLink only★ 17
Local /ultrareview skill — 3-stage Opus pipeline with live logs and implementation plan
SkillLink only★ 8
Viral hook detector and short video clip curator (Opus Clip style)
SkillLink only★ 8
Who stands behind it