sciagent-skill-creator

# SciAgent Skill Creator Repo-local scaffolder for `skills/` entries. Mechanizes the boilerplate from `AGENTS.md` Steps 1, 2, 4, 5, 6 so authoring effort stays on *content* (When to Use, Workflow, Recipes, References) and not on field plumbing. ## When to invoke this skill - User asks for a new SciAgent skill entry on a specific tool, library, database, or guide topic - User invokes `/sciagent-skill-creator` directly - The agent is about to hand-edit `registry.yaml` and create a `skills/<cat>/<name>/SKILL.md` from scratch — use this instead Do **not** invoke for: - Editing an existing entry's content (just edit the file) - Migrating an existing entry (read `AGENTS.md` "Migrating from Existing Entries" first — the scaffolder generates a skeleton, but migration requires content judgment) - Updating `registry.yaml` only (use a normal edit) ## What you need to collect from the user Before calling the scaffold script, gather these — in conversation, not via flags hidden from the user: 1. **Topic** — concrete tool/library/concept name. Reject vague topics ("ML stuff") with a clarifying question. 2. **Sub-type** — `pipeline` | `toolkit` | `database` | `guide`. Use the decision rule from AGENTS.md Step 1b. If unsure, ask the user. 3. **Category** — primary category directory. List the table from `AGENTS.md` Step 2 if the user is unsure. 4. **Entry name** — kebab-case slug. Convention: `{tool-name}-{purpose}` (e.g., `pydeseq2-differential-expression`). Confirm with the user. 5....