AugmentClaude

Ask Human

Pause execution and request human approval before proceeding with critical decisions.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.

    This copies the whole skill folder into ~/.claude/skills/smithers-ask-human-smithersai/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Raise a blocking human-approval request from inside a run and wait for the decision. Use when blocked, uncertain, or about to do something irreversible — never guess. Run `smithers ask-human --help` for usage details.

What this skill does

smithers ask-human

Raise a blocking human-approval request from inside a run and wait for the decision. Use when blocked, uncertain, or about to do something irreversible — never guess.

Arguments

NameTypeRequiredDescription
promptstringyesThe decision or question to put to a human

Options

FlagTypeDefaultDescription
--contextstringExtra context appended to the prompt
--choicesstringComma-separated choices; makes this a fixed-choice decision
--runIdstringRun to attach to (default: SMITHERS_RUN_ID or the single active run)
--nodestringNode id to attach to (default: SMITHERS_NODE_ID or 'agent-ask')
--iterationnumberLoop iteration (default: SMITHERS_ITERATION or 0)
--timeoutnumberSeconds to wait before the request expires (0/unset = no timeout)
--pollnumberPoll interval in seconds while blocking (default 3)

Related skills