principle-never-block-on-the-human
Apply when tempted to ask 'should I do X?' on reversible work.
How do I install this agent skill?
npx skills add https://github.com/christofferbergj/agent-skills --skill principle-never-block-on-the-humanIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill provides behavioral guidelines for an AI agent to proceed with tasks autonomously when they are considered 'reversible' (like writing code or editing notes) to avoid unnecessary blocking of the user. It explicitly maintains safety boundaries for high-risk, irreversible actions.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Never Block on the Human
The human supervises asynchronously. Agents must stay unblocked. Make reasonable decisions, proceed, and let the human course-correct after the fact. Since code changes are reversible and reviewable, a wrong decision usually costs less than blocking.
- Proceed, then present. Do the work, show the result. Don't ask "should I do X?" Do X, explain why.
- Make the system self-healing. When you notice a problem, log it and fix it in the next round.
- Irreversible actions (force-push, delete production data, send external messages) require the user's authorization. Honor authorization already given for that action; ask only when it is missing.
- Authorized reversible actions (write code, edit notes, split tasks) should proceed without blocking.
- Product direction, interview confirmation, and explicitly requested approval checkpoints come from the human. Proceed within the accepted phase and scope; a later incompatible change to an approved contract returns to that decision gate. Execution within the grant should not block.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/christofferbergj/agent-skills/principle-never-block-on-the-human">View principle-never-block-on-the-human on skillZs</a>