Analytics and metrics commands

apache/superset

Command Claude Code

Command "js-to-ts" from apache/superset, covering javascript to typescript migration command, usage and agent instructions.

metabase/metabase

Command Claude Code

Review this conversation and generate a structured improvement report.

metabase/metabase

Command Claude Code

Launch a bot command in an isolated autobot session with its own worktree, backend, and frontend.

metabase/metabase

Command Claude Code

Aggregate per-task UXBot reports into an overall UX report, looking for patterns across tasks.

iOfficeAI/AionUi

Command Claude Code

Convert an OfficeCLI skill into a fully wired AionUi assistant preset, or update an existing one.

phuryn/pm-skills

Command

Static performance audit of AI-built code — find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by effort and impact.

promptfoo/promptfoo

Command

Commander.js-based CLI commands registered in src/main.ts.

tanweai/pua

Command

A reminder-and-action command based on the Chinese essays 《置身钉内》 and 《置身钉外》, which discuss workplace pressure, management language, and distorted performance data.

tanweai/pua

Command

Use when the user invokes /pua or asks for PUA mode, try-harder/retry help, change-approach coaching, completion-quality checks, evidence requests, test-before-done reminders, or Ding-style workplace reminders. Routes to p7, p9, p10, pro, yes, mama, loop, on/off/offline, kpi, survey, flavor, ding, again, done-check…

vendurehq/vendure

Command

Compiles a Vendure project for production: the server and worker are compiled with TypeScript, the dashboard with Vite.

repowise-dev/repowise

Command

Ask a codebase question and get a cited, synthesised answer with a confidence rating (costs an LLM call).

repowise-dev/repowise

Command

Triage card for files, modules, or symbols — layer, hotspot, fix history, freshness (relationships, not source bytes).

repowise-dev/repowise

Command

Work with architectural decisions — list, inspect health, add, or confirm auto-proposed decisions.

Helicone/helicone

Command Cursor

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓.

lightdash/lightdash

Command Claude Code

Add a CLAUDE.md context file in the directory $ARGUMENTS.

lightdash/lightdash

Command Claude Code

Manage a production-like Lightdash deployment on Azure AKS with the Azure Container Apps Sandboxes backend. Args: (none) = status, up = idempotently provision + deploy, deploy = build this branch → ACR → roll the deployment, down = tear everything down to stop spend.

lightdash/lightdash

Command Claude Code

Get all open customer support bugs from the customer support milestone (184).

Galaxy-Dawn/claude-scholar

Command

Run a blocker-first post-experiment workflow: validate evidence, produce strict statistical analysis when possible, and generate a decision-oriented results report only when the analysis bundle is sufficient. Uses results-analysis + results-report as a gated two-stage workflow.

skyhook-io/radar

Command Claude Code

Review Radar's weekly Dependabot updates and batch only soaked, low-risk bumps into one tested PR.

skyhook-io/radar

Command Claude Code

Build and test Radar changes using a real running instance. Combines build verification, API smoke tests, and optional Playwright E2E tests.

skyhook-io/radar

Command Claude Code

Visually test Radar changes against a real cluster using Playwright MCP. Takes screenshots, organizes them, and reports what looks right or wrong.

workweave/router

Command

Print the session id that correlates this session in router telemetry and logs.

openlit/openlit

Command Claude Code

Use this command before changing organisation, project, or database config behavior.

openlit/openlit

Command Claude Code

Use this command before handing off security-sensitive OpenLIT changes.