A command is the one you type. It runs exactly when you ask it to, and never before.
8,043 commands across 582 plugins.
Setup conversion tracking — Facebook/Meta Pixel, TikTok Events API, Google Ads, GTM
AI-powered UX/UI design — apply 48 UX Laws, generate UI previews, and run design tests
Sync reviewer metadata from markdown files to reviewers-meta.json for the dashboard.
Complete a cycle. Triggers reflection if pending learnings, then archives.
Design a cycle — create new cycles with planned stories, detail existing planning cycles, or quick-sketch a roadmap. Detects planning docs in .craft/planning/…
Activate a cycle and start implementing its stories.
Generate a complete, valid theme.json (schema v3) from a design system, CSS custom properties, or design tokens.
Generate a WordPress block theme style variation (styles/*.json) — dark mode, color palette swap, or font swap.
Azure cost and pricing analysis for a subscription — Advisor cost recommendations, retail pricing lookups, and quota-driven right-sizing signals, scoped to one…
Resource health and diagnostics triage for an Azure resource or subscription — Resource Health status, AppLens deep diagnostics, and Azure Monitor alert state
Check Backup Radar health across a client's backups and surface failures
Archive completed milestone and prepare for next version
Systematic debugging with persistent state across context resets
Route freeform text to the right hunt or THRUNT command automatically
Set up and troubleshoot Datadog — Agent deployment on Kubernetes, APM instrumentation, Log Management, Monitors, Dashboards, SLOs, Synthetic tests, and live…
Structured platform troubleshooting — classifies the problem layer, collects evidence, forms a root-cause hypothesis, and proposes a fix with validation and…
Generate, format, and validate code documentation — docstrings, JSDoc, OpenAPI/Swagger specs, documentation sites, and developer guides.
Execute the BetterCallClaude 5-step Swiss legal framework: intake → research → strategy → adversarial → draft. A complete end-to-end pipeline for any Swiss…
Define a checkable legal success condition for /legal-loop. Accepts a named profile (citations-clean, draft-passes-gate, adversarial-converge, nda-batch-clean,…
Iterate a worker-evaluator cycle against a Goal Record until the success condition is met or a stop limit is reached. The evaluator (a different agent than the…
Scan this repo and build a trusted, citation-verified knowledge base (docs/superpowers/architecture/*) plus an AGENTS.md/CLAUDE.md bridge, behind a human…
Materialize a Compound V execution manifest from a plan (or an accepted fast-path pre-eval). Applies the routing policy and writes manifest.yaml plus an…
Deep, two-axis, stack-agnostic code review of a pull/merge request or a local diff — review-only, never edits code. Runs the pr-review skill. Works on GitHub…
Health-check Cursor CLI, list models, guide installation, or toggle the stop-time review gate.
List past Agent Team sessions stored in claude-teams-brain
Instantly seed the brain with pre-built stack conventions so your AI team starts informed from session one. Run `/brain-seed` to list available profiles, or…
Generate creative assets for all posts in the current month's calendar
Track ENCODE experiments locally with publications and provenance
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic