Read and resolve pinned human feedback on live prototypes from your coding agent.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "io.github.richardofortune/tyrekick" MCP server from askskill: Run: claude mcp add 'io-github-richardofortune-tyrekick' -- npx -y tyrekick-mcp
Read all pinned human feedback on the current live prototype, organize it by page and priority, and mark handled items as resolved.
A feedback list, organized results, and resolution status for handled items.
Check new feedback in the live prototype, extract UI issues that require changes, and produce an actionable fix list.
A feedback-based list of changes for continued development or design iteration.
While building a live prototype, a developer can let the coding agent read feedback pinned on the interface directly, reducing manual comment triage. After handling the issues, the agent can mark related feedback as resolved.
After reviewing a live prototype, a product manager or designer can use this tool to collect participant feedback and drive follow-up changes and closure. It suits fast iteration centered on the prototype.
It lets a coding agent read human feedback pinned on a live prototype and handle or mark that feedback as resolved. Its core capability is feedback retrieval and resolution tracking.
The provided material does not specify supported platforms, installation steps, or required keys. See the source repository for exact prerequisites.
Based on the description, it emphasizes a coding agent directly reading pinned feedback on a live prototype and resolving it. The provided material does not describe further differentiators; see the source repository.
Pause AI coding tasks, add feedback and screenshots, and steer progress live.
Give AI coding agents persistent project memory that detects stale knowledge.
Record agent decisions and rationales for traceable recall and better memory.
Process submitted session feedback and turn it into targeted improvements.
Evaluate code review feedback rigorously before deciding whether to implement it.
Clarify ambiguous changes into testable acceptance criteria and implementation requirements.