Menu
Submit structured feedback about a tool or command to improve future flywheel sessions.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Relentless goal/design interview that sharpens framing and writes durable docs (brainstorm artifact, ADRs, glossary) as decisions crystallize. Use when refining a flywheel goal, pressure-testing scope, or "grill with docs".
Start or resume the full agentic coding flywheel. Drives the complete workflow: scan → discover → plan → implement → review.
Set up flywheel prerequisites for this project.
One-shot diagnostic of every flywheel dependency — MCP connectivity, Agent Mail liveness, br/bv/ntm/cm binaries, node version, git status, dist-drift, orphaned worktrees, and checkpoint validity. Use when debugging toolchain issues, before starting a new session, after /flywheel-cleanup, or as a CI gate.
Strategic gap analysis between vision (AGENTS.md / README.md / plan docs) and what's actually implemented. Converts gaps into beads, optionally launches a swarm. Use when "reality check", "where are we really", "gap analysis", "did we drift", or before declaring a long-running project done.
Launch a parallel swarm of agents to implement multiple beads simultaneously.
Basé sur la classification professionnelle SOC
| name | flywheel-tool-feedback |
| description | Submit structured feedback about a tool or command to improve future flywheel sessions. |
Submit tool feedback: $ARGUMENTS
Record feedback to improve the agent-flywheel.
Parse $ARGUMENTS. Expected format: <tool-name>: <feedback> or just <feedback>.
If no tool name specified, ask: "Which tool or command are you giving feedback on?"
Collect feedback via a structured survey (ask these in order if not in $ARGUMENTS):
Store feedback by calling send_message via agent-mail MCP:
subject: "Tool Feedback: <tool-name>"body_md: <formatted feedback>thread_id: "agent-flywheel-feedback"importance: "low"Search existing feedback for similar patterns: search_messages with query "Tool Feedback: <tool-name>".
If 3+ similar feedback items found, flag it: "This is a recurring issue. Consider creating a bead to address it."
Confirm: "Feedback recorded. Thank you."