Commands

ComposioHQ/composio

Command Claude Code

Check for open PRs in the Composio client repositories and create a plan for updating the SDKs.

mastra-ai/mastra

Command Claude Code

GitHub OSS maintainer lifecycle triage, review, and approval management.

alirezarezvani/claude-skills

Command Claude Code needs its repo

Update all the documentation related files.

gastownhall/beads

Command Claude Code

Convert a Claude Code plan file into beads epic + tasks for cross-session tracking.

promptfoo/promptfoo

Command Claude Code

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

NVIDIA/SkillSpector

Command Claude CodeOpenCode ✓ vendor

Scan an AI agent skill for security risks with SkillSpector (static analysis by default); use when vetting a skill before install or auditing one in use.

RooCodeInc/Roo-Code

Command Claude Code

Create a new release of the Roo Code extension.

coleam00/Archon

Command Claude Code

Confirm whether the work item still names real current work, judge whether it is a contract a run can start from, choose the kind of reasoning owed next, and stop. Write the decisive evidence and handoff to $ARTIFACTSDIR/triage.md. You assess and route only: the repository must be exactly as you found it when you…

kriasoft/react-starter-kit

Command Claude Code

Check that the Drizzle schema in db/schema/ still satisfies what Better Auth expects. Better Auth derives its required tables from the enabled plugins, so the generated JSON — not the upstream docs — is the source of truth.

teableio/teable

Command Claude Code

Declaration: If the folder I belong to changes, please update me, especially core domain concepts. Add examples or example file paths for abstract concepts when needed.

danielmiessler/LifeOS

Command Claude Code

Full-system integrity check — file references, version anchors, hook registration + wiring, hooks-alive (main sessions actually receiving injections), carrier facts, replay corpus, CLAUDE.md @-imports, skills, intents, retired tokens, gate counts, spinner tips and verbs, command/agent frontmatter. Deterministic, under…

spree/spree

Command Claude Code

Review a change's database impact and publish it as a visual artifact.

mindfold-ai/Trellis

Command Claude Code

Initialize a Trellis-managed development session. This platform has no session-start hook, so manually load the equivalent compact context by following these steps.

browseros-ai/BrowserOS

Command Claude Code

You are a code review specialist. Identify genuine issues while filtering out false positives.

Imbad0202/academic-research-skills-codex

Command Claude Code

ARS /ars-mark-read — record a user-attested reading signal for one or more citation keys.

Untrivial-ai/agent-orchestrator

Command Claude Code

Inspect and control the current AO session's target-isolated browser. The desktop app must be open. The agent and user share the same live page, cookies, navigation state, and WebContentsView; the runtime remains usable while the Browser panel is hidden, except for commands that need the page to be painted (see…

coleam00/context-engineering-intro

Command Claude Code

Execute a comprehensive template generation PRP to create a complete context engineering template package for a specific technology/framework.

EverMind-AI/EverOS

Command Claude Code

Ask a question about past work. Searches memories and combines with current context to answer.

datahub-project/datahub

Command Claude Code

Review DataHub pytest smoke tests for standards compliance and quality.

max-sixty/worktrunk

Command Claude Code

Run the current binary in a temporary test repository with a real PTY. Use tmux-cli when available, capture terminal output, and inspect -vv logs when behavior depends on timing or shell state. Avoid treating a piped command as proof of interactive behavior.

backnotprop/plannotator

Command Claude Code

Open the Plannotator Inbox in the browser, show its address, and learn how to use the Inbox.

higress-group/higress

Command Claude Code

You are a specialized prompt engineer tasked with generating high-quality, structured prompts for AI agents based on user descriptions. Your goal is to create agent prompts that follow a consistent format inspired by subagent creation workflows, similar to Claude's structured agent design. When you receive an input in…

MervinPraison/PraisonAI

Command GitHub Copilot

You are an independent SECURITY REVIEWER. This change has outsider origin: some of what it was built from (a fork, an issue, or comments) came from someone without write access to this repository. Assume that person may be an attacker, and that the code may have been written by an AI agent they manipulated through…

vendurehq/vendure

Command Claude Code

Scaffolds a feature into a Vendure project — a new plugin or a piece of an existing plugin.