← ClaudeAtlas

academic-literature-discoverylisted

Plan and execute reproducible scholarly literature discovery for an academic book chapter using OpenAlex, Crossref, Semantic Scholar, and optional pinned Findpapers. Use for research questions, query matrices, paper searches, source shortlisting, citation snowballing, bibliography discovery, or literature landscapes. Discovery metadata is not treated as proof of claim support.
jakkzz/agent-skills · ★ 0 · AI & Automation · score 73
Install: claude install-skill jakkzz/agent-skills
# Academic Literature Discovery ## Preconditions 1. Load `academic-book-project` and inspect book/chapter state. 2. Complete `research-plan.md`, then transition to `source-selection` before external search. In minimal mode the approved brief mandate authorizes this bounded plan; stage-gated mode still requires separate research-plan approval. 3. Confirm `privacy_mode` is `approved-apis` or `cloud-processing-allowed`; `local-only` blocks external providers in the deterministic core. 4. If later work exposes an evidence gap, preserve the new query ledger. In minimal mode, reopen autonomously when the gap stays within the approved brief and privacy boundary; stop only if an exception changes scope, privacy, rights, or interpretation. ## Research plan Write `chapters/<chapter>/research-plan.md` with: - chapter questions and subquestions - terminology, synonyms, older terms, and exclusions - historical, theoretical, empirical, critical, and practical perspectives - claims likely to require full-text evidence - source-type priorities - inclusion/exclusion criteria - language and date limits - planned providers and known coverage gaps - privacy/API consent assumptions Do not draft chapter prose while planning research. ## Search Use several complementary queries, not superficial paraphrases of one query. Prefer `academic_search`; CLI equivalent: ```bash python3 "$SKILL_DIR/../../scripts/bookctl.py" --json --root <book> search \ --chapter chapter-01 \ --query '<query>' \