Journal Recommender

What problem it solves

Journal selection often becomes a guess: manuscript quality is hard to infer from an abstract alone, journal scope memory goes stale, and metrics such as IF, APC, review speed, and indexing status need current evidence. This skill turns “feel-based” journal choice into an auditable workflow: parse the abstract, confirm submission preferences, then return only 3–5 supported candidates.

How it works

• Abstract parsing: extract main discipline, research type, and 3–5 keywords for retrieval, without treating them as a quality verdict.
• Strategy estimate: estimate a tentative baseline, such as CAS/JCR tier, from novelty, problem importance, evidence strength, and writing clarity.
• Preference checkpoint: before web retrieval, ask for target tier, review speed, OA/APC budget, challenge/target/safety strategy, and hard exclusions.
• Candidate pooling: build challenge, target, and safety pools, prioritizing scope fit, practical risk, and verifiable data.
• Evidence output: each recommendation includes ISSN, IF, CAS/JCR, scope-fit rationale, risk status, and audit links.

Note: this skill does not replace formal academic judgment. If official Aims & Scope or risk sources are unavailable, it should mark fields as unverified and cap the scope-fit score instead of fabricating conclusions.