triage-for-autonomylisted

Use BEFORE starting an unattended run, to score an existing queue of open items — a to-do list, an issue tracker, plan steps, or a persistent open-items store — into what is safe to do now, what is autonomous but heavy, and what is gated on a human. Produces a tier verdict plus a gate reason per item, and ranks the gated pile by how cheaply each item could be released so an attended pass asks the best questions first. Do NOT use for executing the items (execute-unattended), for the closing wrap (close-out-the-run), or for walking gated items with the user present (ungate-queue).
haiggoh/run-to-completion · ★ 1 · AI & Automation · score 74

Install: claude install-skill haiggoh/run-to-completion

# triage-for-autonomy — score the queue before you touch it Selection is what makes unattended work safe. The failure mode of autonomous execution is not incompetence; it is taste-dependent guesses made while nobody is watching. This skill prevents that by forcing an explicit, recorded verdict on every item before execution begins — so that nothing gets attempted by default. ## The three scoring axes Apply these three filters to every item in your queue. An item must pass **all three** to be Tier 1. 1. **Not gated on a human:** Does this require user input, a supervised interactive session, a download, or a fresh session state? If yes, it is gated. 2. **Objective decision or spelled-out plan:** Is the outcome defined by objective criteria (a bug fix, a known-correct doc update, a written test procedure)? If it requires design taste, methodology choice, or creative judgment, it is not objective. 3. **Verifiable by observable outcome:** Can you prove it is done by checking a diff, a test result, or a file state? If success is subjective or internal, it is not verifiable. ## The three tiers Bucket items based on the axes above. - **Tier 1 — do now:** Fully autonomous, objective, bounded, and verifiable. Examples: documentation fixes with known-correct outcomes, clear bug fixes, test procedures already written out, read-only investigations, and objectively-closeable items. - **Tier 2 — autonomous but heavy:** Delegatable but liable to sprawl. Examples: benchmarks, research