Skills, plugins and agents for AI automation

Use TaskFlow when a job needs to outlive one prompt or one detached run, but you still want one owner session, one return context, and one place to inspect or resume the work.

1Password CLI

Follow the official CLI get-started steps. Don't guess install commands.

Browser Automation

Use this skill when you need the `browser` tool for anything beyond a single page check.

Trello Skill

Manage Trello boards, lists, and cards directly from OpenClaw.

iMessage / SMS (macOS)

Use `imsg` to read and send iMessage/SMS via macOS Messages.app.

Gemini CLI

Use Gemini in headless one-shot mode. Positional text starts interactive mode; use `-p/--prompt`.

goplaces

Modern Google Places API (New) CLI. Human output by default, `--json` for scripts.

Himalaya : IMAP/SMTP email (CLI)

Use `himalaya` for IMAP/SMTP email from shell.

mcporter

Use `mcporter` to work with MCP servers directly.

Dispatching Parallel Agents

You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit

superpowers

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

Requesting Code Review

Dispatch a code reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation - never your session's history. This keeps the reviewer focused on t

Subagent Driven Development

Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.

Executing Plans

Load plan, review critically, execute all tasks, report when complete.

Agent Introspection Debugging

Use this skill when an agent run is failing repeatedly, consuming tokens without progress, looping on the same tools, or drifting away from the intended task.

Checkpoint Management

Create, verify, or list workflow checkpoints after running the validation checks.

Jira

Retrieve a Jira ticket, analyze requirements, update the status, or add comments. Use the "jira-integration" skill and the

Autonomous Loops

Models and architectures for Claude Code autonomous loops, from simple sequential pipelines to RFC-driven multi-agent DAG systems.

Autonomous Loops

Models and architectures for Claude Code autonomous loops, from simple sequential pipelines to RFC-driven multi-agent DAG systems.

Debugging via agent introspection

A structured process for self-diagnosing failures in AI-agents, based on capture, diagnosis, recovery in a confined mode, and

API Connector Generator

Build a new API connector or provider by matching the target repo's existing integration pattern exactly. Use when adding one more integration without