ask-llm
MCP server and CLI for second opinions: lets Claude Code, Codex and Cursor consult Codex, Claude, Gemini, Grok and local Ollama models for code review and plan debate
Measured catalogue entries in Agents, skills and MCP.
Results stay in Agents, skills and MCP. Search instead in the Whole catalogue
MCP server and CLI for second opinions: lets Claude Code, Codex and Cursor consult Codex, Claude, Gemini, Grok and local Ollama models for code review and plan debate
A QA engineer for your coding agent. It tests each React Native change on a simulator and tells you PASS or FAIL, with video proof.
Software Engineering workflows for Claude Code (MIRROR)
Wall-clock awareness for LLM agents. Two tools: elapsed-time-between-turns + day rollover detection.
Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.
An Agent Skill helping you to optimize Xcode incremental and clean builds by running benchmarks and optimizing build settings.
Agent Skill that turns messy notes into rendered strategy-consulting visuals, with SVG examples and validation.
Harness engineering applied to knowledge production: a self-evolving multi-agent newsroom that turns your documents into a cross-linked markdown wiki. A "reground" loop pulls published pages back in before they go stale — writer ≠ reviewer, local-first, a structured alternative to RAG.
Everything Anthropic ships for builders, archived as markdown and refreshed 4× daily. 4,200+ files: API, Claude Code, MCP, support, cookbooks, skills, plugins.
Redis' official collection of agent skills