Update to fstack

{
  "description": "Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.",
  "included_files": [],
  "name": "principle-never-block-on-the-human",
  "skill_md_contents": "---\r\nname: principle-never-block-on-the-human\r\ndescription: \"Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.\"\r\nuser-invocable: false\r\ndisable-model-invocation: true\r\n---\r\n\r\n# Never Block on the Human\r\n\r\nThe human supervises asynchronously. Agents must stay unblocked: make reasonable decisions, proceed, and let the human course-correct after the fact. Code is cheap. Waiting is expensive.\r\n\r\n**Why:** Every permission pause stalls the pipeline and makes the human the bottleneck. Since code changes are reversible and reviewable, a wrong decision usually costs less than blocking.\r\n\r\n**Pattern:**\r\n- **Proceed, then present.** Do the work, show the result. Don't ask \"should I do X?\" Do X, explain why.\r\n- **Reserve questions for genuine ambiguity.** Ask only when you truly cannot infer intent from context.\r\n- **Make the system self-healing.** When you notice a problem, log it and fix it in the next round.\r\n- **Supervision is async.** The human reviews plans, diffs, and changes on their own schedule. Design workflows for review-after-the-fact.\r\n- **Code is cheap, attention is scarce.** A wrong implementation costs minutes to fix. A blocked agent costs the human's attention to unblock.\r\n\r\n**Boundaries:**\r\n- **Irreversible actions** (force-push, delete production data, send external messages) still require confirmation.\r\n- **Reversible actions** (write code, edit notes, split tasks) should proceed without blocking.\r\n- **Product direction** comes from the human; *execution* should not block.\r\n"
}