evaluate-idea-sciencelisted

Run an 8-step iterative pre-execution evaluation of a research idea targeting the broad general-science quality bar — PNAS, Nature Human Behaviour, Nature, Science. Use whenever the user wants to evaluate an idea for "a general-science venue", "PNAS", "Nature Human Behaviour", "Science", "Nature", or asks "is this big enough for a broad audience", "does this have general-interest impact", "could this go to Nature?" Also use when the user has a marketing/economics/CS idea and wonders whether to reframe it for a generalist editor. Covers phenomenon novelty, mechanism strength, generalizability, society-level implications, narrative tightness for a non-specialist editor, lit-review threat search, and a final verdict — looping on the pivot until the idea scores at least 7/10 against the broad-science bar.
ericluo04/claude-academic-workflow · ★ 3 · AI & Automation · score 66

Install: claude install-skill ericluo04/claude-academic-workflow

# evaluate-idea-science ## Personalization This skill resolves placeholders against `~/.claude/state/personal_config.json`. See `_config/README.md` and `_config/personal_config.example.json` for setup. If the config is missing or a needed field is unset, the skill must surface an error to the user and refuse to proceed rather than guess. Required config fields: - `personal_config.user.name` — used to fill the **Author** line in the generated report. - `personal_config.user.affiliation` — optional, also used in report metadata. ## Purpose Run an iterative pre-execution review of a research idea against the publishable bar of broad general-science journals: **PNAS, Nature Human Behaviour, Nature, Science**. This bar differs sharply from any field-journal bar — generalist editors and a non-specialist audience care about big-picture phenomena, broad generalizability, society-level stakes, and a clean narrative a smart non-expert can follow in two paragraphs. Be exacting, hedged, and constructive — never hostile. The point is to catch problems and hallucinated rationale *before* months of data work are committed to a target that may not actually want the paper. The output is a single structured Markdown report saved to disk. ## Phase 0: Parse the input Inspect the user's request for an idea description. Three modes: 1. **Template mode** — if the user asks for the template, says "give me the template", or has not provided any idea content, write the template at the path b