horizon-journal-recommender
Recommend and verify target journals for a finished or near-finished manuscript. Use for submission shortlists, single-journal fit checks, realistic venue-level calibration, indexing/OA/APC/speed constraints, or China-context journal screening. Build a broad candidate pool, cheaply filter it, deeply verify only 8-12 finalists, then rank them as Reach, Core, and Backup with speed/OA/cost tags. Every final journal must be verified live for official scope, current constraints, and recent related papers. LetPub is auxiliary evidence for review speed and China-specific context, not an eligibility requirement. Use before paper-cover-letter.
yujie-jason-zhang · Static checks on file
Installation
Read the source and dependencies before running a command. Copying does not install or execute anything.
npx skills add yujie-jason-zhang/horizon-academic-writing --skill horizon-journal-recommenderAbout this skill
name: horizon-journal-recommender description: >- Recommend and verify target journals for a finished or near-finished manuscript. Use for submission shortlists, single-journal fit checks, realistic venue-level calibration, indexing/OA/APC/speed constraints, or China-context journal screening. Build a broad candidate pool, cheaply filter it, deeply verify only 8-12 finalists, then rank them as Reach, Core, and Backup with speed/OA/cost tags. Every final journal must be verified live for official scope, current constraints, and recent related papers. LetPub is auxiliary evidence for review speed and China-specific context, not an eligibility requirement. Use before paper-cover-letter.
Journal Recommender
Scope
Use this skill when a manuscript is finished or nearly finished and the user needs to decide where to submit it. Typical tasks include:
- generating a realistic journal shortlist;
- checking whether one named journal fits the manuscript;
- comparing journals by level, scope, indexing, OA/APC, language, or review speed;
- deciding which venues are Reach, Core, or Backup targets;
- verifying a shortlist produced by an advisor, another tool, or another skill.
This skill matches manuscripts to venues. It does not validate the science itself and does not draft the cover letter.
Read references/journal_recommendation_guide.md for the scoring rubric, source hierarchy, review-speed protocol, red-flag checks, rationale templates, and output template.
Use another skill when the primary task is novelty assessment, literature review, manuscript restructuring, language polishing, or cover-letter writing. Reuse an existing paper-level assessment when one is already available instead of re-deriving it.
Operating Modes
Recommendation mode
Default mode. Generate candidates, filter them, verify the finalists, and return a ranked shortlist.
Verification mode
Use when the user already has a shortlist or a journal-fit claim.
- Preserve the supplied list unless a venue clearly violates a hard constraint or legitimacy rule.
- Verify scope, recent-content fit, level, indexing, OA/APC, speed claims, and red flags.
- Report unsupported or incorrect claims explicitly.
- Re-rank only when the user asks for ranking or when the current tier assignment is materially misleading.
Single-journal fit mode
For one named journal, skip broad candidate generation. Verify the journal and return fit, level, constraints, recent-content evidence, risks, and any concrete adjustment needed.
Non-Negotiable Rules
- Live verification is mandatory for the final shortlist. Model memory may seed search queries or candidate ideas, but no journal may appear in the final recommendation until it has been verified in the current session.
- Never invent a journal, URL, ISSN, metric, indexing status, APC, review time, or related-paper evidence. If a fact cannot be confirmed, label it
not found,unknown, orunverified. Do not treat an unknown journal-specific fact as a favorable default. If required indexing, OA model, or mandatory cost cannot be verified, the journal does not pass that hard constraint for the decision-ready shortlist. - Official scope comes first. Open the journal's official aims/scope or equivalent page for every finalist.
- Recent-content fit is required. For every finalist, verify recent papers from the journal itself and/or a scholarly index. Aims & Scope alone is not enough.
- Hard constraints are gates. A journal that fails required indexing, language, budget, article type, avoid-list, or another explicit non-negotiable constraint is excluded rather than down-ranked.
- Do not select by manuscript template. IEEE/Elsevier/Springer/other formatting is a reformatting issue, not venue-fit evidence, unless the user explicitly makes publisher family a constraint.
- Metrics are time-sensitive. Verify any JIF, quartile, CiteScore, indexing, APC, or fee you report, and state the relevant year/version where applicable. For work performed in 2026 or later, report a CAS partition only as the last available historical edition, state its edition year, and do not describe it as a current tier because the official partition series is no longer updated from 2026.
- Review speed is uncertain evidence, not a promise. Attribute it to the source, use a qualitative band, and include a confidence label. Never convert crowd-sourced timing into a guaranteed decision date.
- LetPub is auxiliary, not a gate. In China-oriented or speed-sensitive tasks, try to locate the mainland-China Simplified-Chinese LetPub page on
letpub.com.cn. Use it as supporting evidence for turnaround and China-context signals. If it is absent, writenot found; do not exclude an otherwise strong journal for that reason and do not substitute a guessed URL. - Screen legitimacy and warning signals. Exclude or clearly flag predatory, hijacked, or warning-listed venues. Screen fast, OA, unfamiliar, and high-APC journals especially carefully.
- A level estimate is not an acceptance prediction. Reach/Core/Backup describe relative submission risk, not acceptance probability.
- Do not pad the list. A shorter, well-supported shortlist is better than a long weak one.
Intake
Use information already provided before asking questions. If key information is missing, collect it in compact groups; if the user does not answer, proceed with clearly stated assumptions when reasonable. Default missing indexing requirements to SCI/SCIE and missing OA preference to non-OA / subscription-preferred.
Hard constraints
- required indexing: SCIE / SSCI / A&HCI / EI / Scopus / 北大核心 / CSSCI / CSCD / none;
- OA preference: must be OA / optional / prefer subscription;
- APC or page-fee ceiling;
- language: English / Chinese / either;
- deadline or time sensitivity;
- avoid-list: warning lists, institutional blacklist, publishers, conflicts, or venues already rejected.