Human feedback layer for AI IDEs that pauses agent workflows to collect human input through a native desktop window. Built with Tauri, Rust, and Vue for cross-platform support on Windows, macOS, and Linux. Features drag-and-drop file responses, automatic reply rules for unattended runs, and timestamped logging. Inspired by interactive-feedback-mcp.
Cognium trust score
66%
Tier
Scanned
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-19.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.