Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From awb
Runs Agent Workbench (awb) CLI components for interactive confirmations, checklists, inputs, tables, code/markdown/HTML views, and plan viewers. Follow interactive runs with 'awb wait' ID; use tmux for background tasks.
How this skill is triggered — by the user, by Claude, or both
Slash command
/awb:awbThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
1. Ensure the user has the playground open with `awb ui`.
awb ui.awb run --title "..." <component> [args].awb wait <id> and read the JSON response.Interactive: confirm, checklist, ask
Display: code, table, markdown, plan-viewer, html
--title for every awb run.awb run --help before using a component you are unsure about.awb is not on PATH, ask the user to install or run the local CLI.awb run returns immediately with an ID. Always call awb wait <id> to get the response.
ID=$(awb run --title "Q1" confirm --prompt "Approve?")
awb wait $ID
Fire multiple at once, then wait for each:
ID1=$(awb run --title "Q1" confirm --prompt "Approve?")
ID2=$(awb run --title "Q2" checklist --items "A,B,C")
awb wait $ID1
awb wait $ID2
awb wait <id> returns JSON with the user's response:
{"confirmed": true}
{"items": [{"text":"A","checked":true}]}
{"answers": {"key": "value"}}
confirm
awb run --title "Deploy" confirm --prompt "Deploy to production?"
checklist
awb run --title "Tasks" checklist --items "Build,Test,Deploy"
ask (1-4 questions)
awb run --title "Name" ask --questions '[{"question":"Your name?","header":"name"}]'
awb run --title "Pick" ask --questions '[{"question":"Language?","header":"lang","options":[{"label":"TypeScript"},{"label":"Python"}]}]'
awb run --title "Features" ask --questions '[{"question":"Enable?","header":"feat","multiSelect":true,"options":[{"label":"Auth"},{"label":"API"}]}]'
table
awb run --title "Data" table --data '[{"name":"Alice","age":30},{"name":"Bob","age":25}]'
code (file only)
awb run --title "Source" code --file ./src/index.ts
markdown
awb run --title "Docs" markdown --file ./README.md
awb run --title "Notes" markdown --content "# Hello\n\nWorld"
html
awb run --title "Config" html --content '<html>...</html>'
plan-viewer
awb run --title "Plan" plan-viewer --file ./plan.md
Use tmux for long-running processes. Run awb --help to see your tmux session name.
tmux new-session -A -d -s <session-name>
tmux new-window -t <session-name> -n "dev" "npm run dev"
tmux capture-pane -t <session-name>:dev -p
tmux send-keys -t <session-name>:dev "npm test" Enter
tmux kill-window -t <session-name>:dev
npx claudepluginhub joshuarweaver/cascade-ai-ml-agents-misc-1 --plugin lobu-ai-agent-workbenchRuns AI coding agents (Claude Code, Codex, etc.) in isolated Docker/Apple containers with parallel sessions, multi-step workflows, and a REST API. Use when configuring agent sandboxes, authoring workflows, or managing worktrees.
Scaffolds complete TypeScript TUI for OpenRouter agents like create-react-app for terminals. Generates customizable interface with input styles, tool modes, ASCII banners, streaming output, session persistence, configurable tools. Use for agent projects or coding assistants.
Creates bite-sized, testable implementation plans from specs or requirements, with file structure and task decomposition. Activates before coding multi-step tasks.