arm-pz

Choose Effort — Productivity skill for Claude Code

Productivity community

Claude Code skill that asks how heavy a task is before you start, then recommends an effort level, whether to use subagents, /goal, workflows or agent teams, the /effort command to set it, and when to.

How to install Choose Effort

This entry records only its repository, not the path inside it, so there is no exact command to give. Open arm-pz/choose-effort and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Choose Effort does

Alternatives in Productivity

Configure Claude HUD — FIRST: Use the Read tool to load ~/.claude/plugins/claude-hud/config.json if it exists 10.9k ★
Grow A Product — Workflow recipe — turn a growth goal into a funnel diagnosis, experiment backlog, retention loop, and lifecycl 1.3k ★
Toolset — Built-in tools are available when the user asks for calculations, conversions, local date/time utilities, URL 250 ★

README

choose-effort

An AI agent skill (a `SKILL.md` for Claude Code) that asks how heavy a task is before you start, then recommends an effort level, whether to fan out to subagents, `/goal`, workflows or agent teams, the `/effort` command to set it, and when to check `/usage`. It recommends; you set the level. The starting table is a rough default, because Anthropic's guidance differs per model.

Siblings: [diagnose-usage](https://github.com/arm-pz/diagnose-usage) for working out why a session already drained your limit. For plan limits and which models support which levels, see Anthropic's docs.

Install

npx skills add arm-pz/choose-effort --skill choose-effort

Or copy the repo files into `~/.claude/skills/choose-effort/` and start a new session.

Ask it things like

"What effort level should I use to refactor the auth module?"
"Set me up to run this overnight."
"Plan an agent team run to rewrite the test suite."

Status

Structure checks done by hand; trigger cases in `references/trigger-cases.md` are hand-read against the skill descriptions and **not** run in a live session. `check_skill.py`: OK, 0 fail 0 warn.