journal-scout
Skill4 starsChanged 41 days agoMITView on GitHub
Find and compare target journals after the research question and data are defined. Use for Stage 1B or explicit venue-selection requests.
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- academic-humanizerSkill
- citation-verificationSkill
- claim-numerics-auditSkill
- cover-letterSkill
- experiment-planSkill
- experiment-runnerSkill
- paper-auditSkill
- paper-illustrationSkill
- paper-planSkill
- paper-writeSkill
- research-data-auditSkill
- research-ideationSkill
- research-publicationSkill
- research-quality-gateSkill
- research-refineSkill
- result-to-claimSkill
- scientific-figure-makingSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Use the available scholarly-search capability, then verify venue metadata and author guidance against official journal, publisher, or …
- Distinctive: line 18
Use journal recommendation tools only for discovery.
- Distinctive: line 46
Author Guidelines: Read the current official journal or publisher page using the available official-web/browser route.
- Distinctive: line 55
Search for papers similar to the research direction, published in the last 2 years
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Journal Scout
Find, evaluate, and select target journals based on research direction, data characteristics, and publication goals.
Process
Phase 1: Bounded Candidate Search
Given the research direction, data characteristics, and user's domain suggestions, cast a wide net:
- Use the available scholarly-search capability, then verify venue metadata and author guidance against official journal, publisher, or conference sources.
- Begin with 3–5 plausible candidates. Expand only when coverage, disciplinary fit, or fallback needs remain unresolved; do not fill a quota.
- Use journal recommendation tools only for discovery. Treat their matches as candidates, not verified fit.
- Record impact metrics, review time, or acceptance rate only when a current authoritative source provides them; otherwise mark them unavailable instead of estimating.
Output: Candidate comparison table
| # | Journal | Publisher | Current metric/source | Scope Match | Review Time/source | Acceptance Rate/source | Notes |
|---|---------|-----------|-----------------------|-------------|--------------------|------------------------|-------|
| 1 | ... | ... | ... | High/Med/Low | ... / unavailable | ... / unavailable | ... |Done when: the comparison table contains enough verified candidates to support a defensible shortlist, with unavailable metadata stated explicitly.
Phase 2: Discussion & Selection
Present the comparison table to the user. Discuss:
- Which journals best match the research scope?
- Which have reasonable review timelines?
- Which are realistic given the current idea maturity?
Reuse any target set already selected in the current task. Otherwise ask for the ranked target set only when it affects the work; a scope-limited discovery or local test may record no submission target.
Done when: User has confirmed the target set and ranking.
Phase 3: Deep Dive
For each confirmed target journal:
- Author Guidelines: Read the current official journal or publisher page using the available official-web/browser route. Extract:
- Scope and aims
- Page/word limits
- Abstract structure requirements
- Figure/table specifications
- Reference format
- Any special requirements (data availability, ethics, etc.)
- Recent Papers Scan (abstract level — deep reading happens in 1C):
- Search for papers similar to the research direction, published in the last 2 years
- Confirm this journal actually publishes this type of work
- Note common methodological standards and baseline choices
- Journal Intelligence Card for each confirmed target:
journal: [Name]
publisher: [Publisher]
scope_match: [How well the research fits]
author_guidelines_summary: [Key formatting rules]
recent_relevant_papers: [Count + example titles]
suggested_ranking: 1st/2nd/3rd choiceDone when: each confirmed target has an intelligence card with current guidance, recent-paper evidence, and ranking.
Phase 4: Final Output
Consolidate into docs/02_journal_scouting.md:
- Candidate comparison table (bounded set, expanded only when justified)
- Ranked target-journal intelligence cards
- Final recommendation: primary venue and any justified backups
- Key formatting requirements for the primary target
Done when: docs/02_journal_scouting.md records the relevant candidates, one card per actual selected target, verified requirements and unresolved choices. Do not invent three cards or recommend submission when the study lacks a suitable contribution.
References
| File | Open when |
references/venue-routing.md | BEFORE starting the scout. Classify your manuscript type and match to journal categories. Quick-elimination heuristics. |
references/domain-journal-profiles.md | Understanding journal archetypes and common rejection patterns in civil/transport engineering + AI. |
references/journal-card-template.md | Phase 3 deep dive. Fill one card per target journal. |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

