agentleFS
Sign inStart free
taljeontaljeon/plzdo/skills/academic-research-router/SKILL.md

academic-research-router

Skill9 starsChanged 18 days agoMITView on GitHub

Route academic research, literature review, citation checking, paper planning, manuscript review, systematic review, meta-analysis, experiment planning, or ARS-style requests to the smallest safe workflow. Use when the user mentions academic research skills, ARS, papers, manuscripts, citations, PRISMA, peer review, research questions, claim verification, thesis/report research, or asks whether to install/adapt Imbad0202 academic research skills.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 11 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    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
  1. Distinctive:

    Use this skill to route academic work safely, not to install the full ARS suite by default.

    line 8
  2. Distinctive:

    If the task is current or factual, use primary/authoritative sources and cite links.

    line 12
  3. Distinctive:

    If the user has only a broad topic, start with Socratic research-question narrowing before drafting.

    line 13
  4. Distinctive:

    If the user asks for literature review or systematic review, define search scope, inclusion/exclusion criteria, evidence table, and …

    line 14
  5. Distinctive:

    If the user asks for paper writing, require the research question, audience/venue, source set, citation style, and allowed output format …

    line 15
  6. Distinctive:

    If the user asks for review, keep source material read-only unless they explicitly request edits.

    line 16
  7. Distinctive:

    If the user asks to install ARS, read references/adoption.md and produce a preflight first.

    line 17
  8. Distinctive:

    Do not fabricate citations or claim that a source supports text you did not verify.

    line 21
  9. Distinctive:

    Do not upload unpublished manuscripts, reviewer letters, private notes, full corpora, or raw data to external APIs/models without explicit …

    line 22
  10. Distinctive:

    Do not enable ARS hooks, cross-model verification, API-backed citation checks, caches, or experiment execution by default.

    line 23
  11. Distinctive:

    Do not treat the upstream ARS workflow as source of truth for this repo.

    line 24

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Academic Research Router

Use this skill to route academic work safely, not to install the full ARS suite by default.

Route

  1. If the task is current or factual, use primary/authoritative sources and cite links.
  2. If the user has only a broad topic, start with Socratic research-question narrowing before drafting.
  3. If the user asks for literature review or systematic review, define search scope, inclusion/exclusion criteria, evidence table, and citation verification gate.
  4. If the user asks for paper writing, require the research question, audience/venue, source set, citation style, and allowed output format before drafting.
  5. If the user asks for review, keep source material read-only unless they explicitly request edits.
  6. If the user asks to install ARS, read references/adoption.md and produce a preflight first.

Boundaries

  • Do not fabricate citations or claim that a source supports text you did not verify.
  • Do not upload unpublished manuscripts, reviewer letters, private notes, full corpora, or raw data to external APIs/models without explicit consent.
  • Do not enable ARS hooks, cross-model verification, API-backed citation checks, caches, or experiment execution by default.
  • Do not treat the upstream ARS workflow as source of truth for this repo; use it as a reference pattern.
  • Store only reusable sanitized research workflow memory, never full papers or raw notes.

Output

For routed academic work, return:

  • Route: scoping, literature review, citation check, paper plan, manuscript review, or full pipeline.
  • Evidence Gate: source links, citation existence check, claim-support table, PRISMA-like selection log, or reviewer rubric.
  • Install Decision: use built-in router, opt-in ARS preflight, or skip.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free