Menú
Pipe long running commands through tee(1) to allow watching output and repeated analyses without rerunning
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Review all unreviewed documents in Hubdoc. Use when reviewing, processing or publishing Hubdoc receipts and bills.
Use the Xero MCP server — obtain/refresh OAuth2 bearer tokens, troubleshoot authentication, and pick up other operational notes for working with Xero MCP tools. Use when Xero MCP tools fail with authentication errors, when the bearer token has expired (tokens last ~30 min), before starting any Xero workflow, or for general guidance on Xero MCP usage.
Size the agent-browser Chromium window to fill its current screen, leaving a configurable bottom margin for the desktop panel. Use before any agent-browser automation that needs the full screen visible without elements overlapping or scrolling off (e.g. Xero, dense web apps).
General Xero browser automation notes. Use when automating any Xero page with agent-browser — covers non-standard UI patterns, waiting, and dropdown menus.
Convert XLSX spreadsheets (single or multi-sheet) to CSV files you can read and grep. Use whenever you need to process an .xlsx report from Xero, Cryptio, bank exports, or any tool that delivers spreadsheet output.
Create Claude Code slash commands, OpenCode command files, and Pi prompt templates that delegate to the right subagent or skill. Use when creating new commands or refactoring existing ones to follow platform conventions.
Basado en la clasificación ocupacional SOC
| name | slow-command-running |
| description | Pipe long running commands through tee(1) to allow watching output and repeated analyses without rerunning |
Use it whenever running commands that:
gh) or similarAlways pipe these commands through tee(1) to capture output to a file while
still displaying it in real-time.
Never blindly pipe through head(1) unless you're sure premature
termination via SIGPIPE won't cause problems.
When tee-ing into a temporary logfile, prefer the tmp/ subdirectory
of the repository rather than /tmp, so that you don't have to ask
permission for access to /tmp.
Don't assume tmp/ exists - you might need to create it first.
Create tmp/ directory if it doesn't exist: mkdir -p tmp/
Run the command with tee: command | tee tmp/output.log
The user can now choose to monitor that log file as it runs.
If you subsequently need to examine the output multiple times, reading from the log file prevents needing to re-run the slow command each time.
# Run tests with logging
mkdir -p tmp/
npm test | tee tmp/test-output.log
# Check GitHub action run
mkdir -p tmp/
gh run view 12345 | tee tmp/action-run-12345.log
# Access some API
mkdir -p tmp/
some-API-call-command | tee tmp/logs.log