Agent Skills
› brycewang-stanford/Awesome-Journal-Skills
› rt-journal-match
rt-journal-match
GitHub用于为论文匹配最佳投稿期刊或拒稿后重新选刊。通过分析论文画像，从索引中筛选并评估候选期刊，按风险分为冲刺、匹配和保底三类，提供基于实时数据的理由及投稿阶梯建议。
Trigger Scenarios
作者询问应投递哪个期刊
论文被拒需寻找最佳重投目标
当前选题与期刊范围不匹配
Install
npx skills add brycewang-stanford/Awesome-Journal-Skills --skill rt-journal-match -g -y
SKILL.md
Frontmatter
{
"name": "rt-journal-match",
"description": "Use when an author asks \"which journal should I send this to?\" or needs the best resubmission target after a reject. Profiles the paper, shortlists candidate venues across 185+ packs, and ranks them into reach \/ match \/ safe with a resubmission ladder. Reads live venue facts from each pack's source-map; defers fit judgment to the venue's own topic-selection skill."
}
Journal-Match (rt-journal-match)
The missing front-door question — which venue? — across the whole repository. Full
methodology + the stable venue index live in
shared-resources/journal-selection/journal-match.md
and venue-index.tsv.
When to trigger
- The author has a result/draft and no settled target.
- A paper was rejected and needs the best next venue.
- A "not a fit" signal means the scope/venue needs rethinking.
What it does
- Profile the paper — discipline + subfield, method/design, contribution type, setting/data/region, ambition (be honest).
- Shortlist from
venue-index.tsvby discipline / lane / region (long-tail venues → the discipline breadth bundle). - Score each candidate on Fit × acceptance-odds × turnaround × cost/policy ×
audience, reading the live facts from each candidate's
resources/official-source-map.md. - Return reach / match / safe (≈2–3 each) with one-line rationales + the live facts, then a submit order and resubmission ladder.
Hard rules
- Live facts from the source-map, never from memory (fees, acceptance, turnaround, page limits, data policy).
- Fit judgment defers to the venue's
*-topic-selection/*-contribution-framing. - Be honest about odds; don't inflate a paper into a reach it can't clear.
- Coverage honesty: if a plausible venue is outside the index and its bundle, say so.
Output format
【Paper profile】discipline / method / contribution / setting / ambition
【Reach】V — why; key live facts (desk-reject, turnaround, fee)
【Match】V — …
【Safe】V — …
【Submit order & ladder】V_top → if reject → V_next (what to change) → …
【Open questions】facts to re-verify in the source-map before submitting
Anti-patterns
- Recommending only reaches (wastes the timeline) or only safes (undersells the paper).
- Ignoring
lane— sending a qualitative/theory paper to an empirical-only venue. - Treating the
tiercolumn as a precise ranking (it is an indicative bucket).
Next: once a target is chosen, rt-execution-bridge to run the analysis and
rt-submission-readiness to check the bar.
Version History
- 1839142 Current 2026-07-05 14:19
