Skip to content
SkillModel-led12,091 tokens in use

Deep Research (Academic Research Skills)

A 13-agent research team with eight modes, from Socratic question forming and literature reviews to PRISMA systematic reviews and APA 7.0 reports.

57,881 stars on the repository Custom / UnknownImbad0202/academic-research-skills · deep-research
/plugin marketplace add Imbad0202/academic-research-skills /plugin install academic-research-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Deep Research (Academic Research Skills) costs

372tokens idle
12,091tokens in use
158,256tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure25/25
  • Examples15/15
  • Output15/15
  • Size2/15
  • Resources13/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community60
  • Maturity32
  • Momentum40

Deep Research is a domain-agnostic research team for rigorous academic work. It turns a vague topic into a scored research question, designs the method, searches the literature, verifies sources, synthesises the findings and compiles an APA 7.0 report.

Eight modes cover the common situations: full research, a quick brief, paper review, literature review, fact-check, a three-way paper scan, Socratic guided dialogue, and systematic review with optional meta-analysis. Editor, devil’s advocate and ethics agents review the result before it is final.

What You Get

  • A precise research question with scope boundaries and a methodology blueprint
  • An annotated APA 7.0 bibliography with a documented, reproducible search strategy
  • A synthesis that resolves contradictions and names gaps, plus a risk-of-bias assessment for systematic reviews
  • A complete research report reviewed by an editor, a devil’s advocate and an ethics agent

Common Use Cases

  • Researching a topic from question to finished APA report
  • Running a systematic review or meta-analysis with PRISMA reporting
  • Fact-checking specific claims against graded sources
  • Thinking through a vague research direction with Socratic questions

What Makes It Unique

The team has specialist roles that most single-prompt research skills lack: a source verification agent that grades evidence and flags predatory journals, a devil’s advocate that challenges assumptions, an ethics reviewer, and bias and meta-analysis agents for systematic reviews. A routing step asks for clarification when your materials span several phases, and retrieved web text is treated as data and never as instructions. It pairs with sibling skills for writing, reviewing and a full pipeline.

Under The Hood

The skill loads a long SKILL.md that routes your request to one of eight modes and dispatches agent files from its agents folder, each limited to one phase and its own output folder. The bibliography agent searches literature sources and web pages for the search strategy, and can query the Semantic Scholar API to resolve and de-duplicate sources, skipping that step when the service is unavailable. Agents write the briefs, bibliographies and reports to your project as files. Pasted and fetched text is treated as data, and directives inside it are reported and not followed.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers