cancel
Cancel an active plugin-managed Kimi job for the current repository.
A command is the one you type. It runs exactly when you ask it to, and never before.
478 commands across 665 plugins.
Cancel an active plugin-managed Kimi job for the current repository.
Run a read-only Kimi challenge review that challenges assumptions and surfaces safer alternatives.
Generate or improve UI/UX for the specified platform - ux, web, windows, apple, android, or cross-platform. Routes to matching skill which then asks the user…
Use this command when the user asks for high-end animation direction, Luma-level landing pages, cinematic product reveals, or when an animated design feels…
Plan UI assets for a Stark design before implementation, including references, icons, typography, generated product mocks, and optional image generation when…
Path to the target project (auto-detected if omitted)
If the user's task is using Signum init command syntax instead of a feature request - for example: - exactly `init` - `init --force` - `init --harness` - `init…
**Goal:** Bundle all artifacts into a self-contained, verifiable proof package (schema v4.8) with embedded artifact contents.
Profile how top GitHub contributors work — ingest, build personas, and synthesise a capability model + learnable playbook.
Mute deadeye's advisories, plan-gate nags, and workflow hints for this session
Full repo scan — duplicates / unused / oversized / unfinished work, then a subagent verifies every candidate
hi-vibe's own health check — actually runs hi-vibe's 6 hook scripts & scanner to catch silent failure. Not Claude Code's built-in /doctor (that one checks your…
Pre-write reuse gate — check if it already exists first, then decide where it goes
Pull the latest ECC repo changes and reinstall the current managed targets.
Detect the project build system and incrementally fix build/type errors with minimal safe changes.
Create, verify, or list workflow checkpoints after running verification checks.
Pull the latest ECC repo changes and reinstall the current managed targets.
Detect the project build system and incrementally fix build/type errors with minimal safe changes.
Create, verify, or list workflow checkpoints after running verification checks.
Break work into small verifiable tasks with acceptance criteria and dependency ordering
Conduct a five-axis code review — correctness, readability, architecture, security, performance
Run the pre-launch checklist via parallel fan-out to specialist personas, then synthesize a go/no-go decision
Renamed → /portaljs-add-resource. This alias will be removed next minor release.
Migrate a whole ArcGIS Hub site (opendata.arcgis.com or a Hub Premium custom domain) into a PortalJS Arc portal end-to-end. Harvests the Hub /data.json…
Renamed → /portaljs-architect. This alias will be removed next minor release.
Run all Brooks-Lint analyses in one pass, auto-fix safe findings, confirm risky ones
Refine an annotated implementation plan and generate a QA ledger
Start iterative loop with Codex review
Sharpen a fuzzy idea into §G/§C before spec. Calibrated interrogation, one question at a time.
Gather external knowledge into §R so build grounds in facts, not hallucinations. Every finding cites a source.
Adversarial senior review of the spec before build. Refute, don't rubber-stamp. Ends in a go/no-go gate.
Get GPT (Codex) second opinion on a question or current work. Single-shot, advisory, no contamination.
Get Grok (xAI) second opinion on a question or current work. Single-shot, advisory, no contamination.
Ask a single configured OpenRouter model for a second opinion. Advisory only. Single-shot or multi-turn.
Refina una idea o feature antes de abrir un flujo completo de implementación
Ciclo completo de desarrollo: producto, arquitectura, desarrollo, QA, docs, entrega
This file is read by parent commands (cycle-design, story-new) that need to run content-spark logic inline instead of via nested Skill invocation. The…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic