persona-panel
Run a parallel multi-persona domain-expert review panel against a file, directory, or output range
A command is the one you type. It runs exactly when you ask it to, and never before.
1,184 commands across 626 plugins.
Run a parallel multi-persona domain-expert review panel against a file, directory, or output range
Plan a new project, feature, or retrospective with structured requirement gathering
Aggregate cross-repo issue/MR/CI health across vault-registered projects into a single Markdown dashboard
One-time setup to initialize the Craft harness for a project.
Live HTML mockup funnel - 3 options, converge by reacting, graduate to tweak/story/todo.
Low-ceremony capture for ideas (half-formed, want to mature into stories), todos (concrete actions), and notes (durable project/team facts for future recall).…
Run an independent cross-model (Codex) adversarial review of a Compound V plan/manifest before dispatch, then arbitrate the findings. Codex advises; the…
Render the state of a Compound V orchestrator run — pipeline phase plus a per-job status table — by reading state.json from the run directory. Optional run-id…
Run the drift-detection checklist (incl. agent-drift signals); report + fix in-turn
Execute a PRP — TodoWrite breakdown, parallel implementation, validate every gate, deploy, prove on prod
Orchestrate the final review fan-out (integration + diversity + risk + release readiness)
Autonomous backend/infrastructure development session driven by a work file
Autonomous frontend implementation session with designer-level quality standards
Context-aware autonomous implementation session driven by a work file
Guided onboarding - walk through a complete OpenSpec workflow cycle with narration
Search and read peer-verified solutions on Stack Overflow for Agents (SOFA) — status, search, read. Read-only CONSUME phase; clean no-op when SOFA is not…
Create a new remote with name, type and options.
An elite context engineering specialist focused on comprehensive, semantic, and dynamically adaptable context preservation across AI workflows. This tool…
You are a cloud cost optimization expert specializing in reducing infrastructure expenses while maintaining performance and reliability. Analyze cloud…
Guided component creation with proper patterns
Analysis for a run and its results, process, suggestions for process improvements, process optimizations, fixes, etc. for the next runs.
Set up babysitter for yourself. Guides you through onboarding — installs dependencies, interviews you about your specialties and preferences, builds your user…
Orchestrate a babysitter run. use this command to start babysitting a complex workflow in a non-interactive mode, without any user interaction or breakpoints…
Print the Agent Monitor dashboard URL and how to start/open it
List the most expensive sessions pushing your spend up
Check Agent Monitor reachability and print UP/DOWN with latency
Coordinate multi-agent swarms for complex tasks
🧠 Auto-Coder - You write clean, efficient, modular code based on pseudocode and architecture. You use configurat...
Unified entry for all development intents — classify intent, assess complexity, route to the correct execution channel: /maestro-companion (lightweight),…
Long-running iterative cycle — one entry, six modes (debug|improve|planex|review|security|ui). Shared archaeology/audit → fix → verify → generalize → discover…
Phase 1 Context of init-workspace-flow
Phase 3 Discovery of init-workspace-flow
Phase 7 Documentation of init-workspace-flow
Called by team.md router when action is `present`. Activates the presentation specialist team.
Generate a visual project recap for context switching
Show latest emails from a specific person. Usage: /email-read alice
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic