discoverlisted

# /discover > Produce a ranked shortlist of paper candidates from one of three seed modes. Surface them to the user (or to the calling skill) with rationales. Never auto-ingest — `/discover` is a proposal stage, `/ingest` is the action stage. Use these local references on demand: - `references/seed-modes.md` — when to pick anchor / topic / wiki mode and how to translate the user's phrasing into one - `references/ranking-signals.md` — what `tools/discover.py` scores on and why discovery does **not** share `/init`'s survey preference - `references/wiki-dedup.md` — how candidates are filtered against `wiki/papers/` and what to do with matches ## Inputs - `--anchor <id>` (repeatable): one or more anchor paper IDs (arXiv IDs preferred; S2 paperIds also accepted). Drives the **anchor mode** — the primary use case, including the post-`/ingest` "what to read next" flow. - `--negative <id>` (repeatable, optional): IDs to push recommendations away from. Only meaningful with `--anchor`. - `--topic "<str>"`: a topic / query string. Drives the **topic mode** — lighter alternative to `/init`'s planner. - `--from-wiki`: derive seeds automatically from the wiki's most recently modified papers. Drives the **wiki mode**. - `--limit N` (optional, default 10): max shortlist size. Exactly one of `--anchor`, `--topic`, `--from-wiki` must be given. ## Outputs - `.checkpoints/discover-{seed-slug}-{YYYY-MM-DD}.json` — full shortlist payload, machine-readable; the seed slug is derived from the