External pipelines · RISE project catalogue
Academic Research Skills (ARS)
A comprehensive Claude Code plugin suite (v3.9.0 at scoring date) for the academic research pipeline: literature → write → review → revise → finalize. Three sub-suites — Deep Research (13 agents), Academic Paper (12 agents), Academic Paper Reviewer (7 agents) — with Style Calibration, anti-leakage protocols, Semantic Scholar API verification, VLM figure verification, and explicit human-in- the-loop gates throughout.
Where it sits
left: what it builds on · right: what builds on it · pale: exampleContributed by Edward Cheng-I Wu
How studies reach it
No published study reaches it yet.
Disciplines it reaches
No study reaches it yet.
Solid: published studies. Light: examples.
Computed from the records on this site: what each study, template and specialist names as used, which study extends which, and who contributed what. 0 studies in total.
What it does
Most-adopted Claude Code-native research plugin (9k+ stars) with an explicit "AI as copilot, not pilot" design stance. v3.8 introduces a *claim-faithfulness audit pass* (`ARS_CLAIM_AUDIT=1`) that fetches each cited source against three-layer citation anchors and gate-blocks output on five hallucination classes (claim-not-supported, negative-constraint-violation, fabricated-reference, anchorless, constraint-violation-uncited). This is the most operationally serious anti-hallucination apparatus in the catalog.
- Focus
- end-to-end
- Inputs
- research-topic, paper-draft, reviewer-comments
- Outputs
- paper-pdf, paper-docx, literature-review, reviewer-report, revision-plan
- Architecture
- multi-agent, debate-consensus, human-in-loop, tool-use, rag-knowledge-base, artifact-versioning
- Maintained by
- Edward Cheng-I Wu
- Started
- 2026
Description
Data model- Discipline
- General
- Method family
- not specified
- Design
- not specified
- Research stage
- Literature discoveryLiterature synthesisDraftingRevision and editingReview
- Contributors
- Edward Cheng-I Wu
- Usage
- not used in published research yet
- Source
- RISE project catalogue · projects/landscape · @4c17bae
- Record
- pipeline:academic-research-skills · JSON
Solid tags are declared by the source or mapped from its terms; dashed tags are inferred by a published rule. Hover a tag for its provenance.
Bring it into the standard
A pipeline built outside E2ER can meet the standard by describing its steps as a template, attaching the floor of checks and publishing evaluation records. Its authors keep ownership and credit.