pick-issuelisted

# Pick the next thing to implement Goal: look at everything that's open, decide what is the **best single next thing to build**, justify the choice briefly, and then hand it off to the skill that builds it. The judgement is a **value-for-effort** call — not simply "the smallest" and not simply "the flashiest" — with a few things that override the ranking and jump straight to the front. **The biggest of those overrides: an open non-draft human PR is picked first.** Someone is waiting on us, and review latency is the one cost that grows while we do something else — so a pending PR beats every issue on the board, however valuable that issue is. Only two things outrank it (a security exposure, broken core functionality), and both are rare. See phase 3. This skill *chooses and then hands off automatically*; the actual shipping (branch, PR, review, merge) happens in `implement` / `dependabot` / `review-pr`, which are outward-facing. Present the pick, then hand it off in the same turn — don't stop to ask for a go-ahead (see phase 4). The safeguards that *do* pause are narrow: a candidate that trips the malicious-intent check (phase 2) or one too underspecified to build without more input. ## 1. Gather all the candidates Open work comes in several forms — collect all of them: ```bash gh issue list --state open --limit 100 \ --json number,title,labels,body,assignees,createdAt,updatedAt,comments gh pr list --state open --limit 100 \ --json number,title,labels,body,author,isDr