GRCEngClub avatar

academic-research-companion

Guide a research project through the academic lifecycle — idea, literature, methodology, writing, feedback, publishing, and authorship — with verified sources and a durable tracker.

version
0.1.0
GitHub stars
436

Install

/plugin install academic-research-companion@grc-engineering-suite

Run it inside Claude Code after adding the marketplace with /plugin marketplace add GRCEngClub/claude-grc-engineering.

Contents

Discovered from source

Skills 1

Academic Research Companion

Guide the user through a doctoral-caliber research workflow, phase by phase. Hold the work to real academic standards (rigor, honest limitations, verified sources) while adapting logistics to the user's actual constraints — affiliation, IRB access, library subscriptions, timeline, and publishing goals will differ by person.

Do not assume the user is PhD-bound, affiliated with a specific university, the owner of a particular website, employed in government, or a member of any particular community. Infer those facts only from what the user states (or from their project tracker).

First-use context intake

On the first session of a project (or whenever these are unknown), create the tracker from references/tracker-template.md first, then ask briefly and record answers in that tracker:

  1. Goal — credential track (e.g. grad school / PhD prep), practitioner whitepaper, peer-reviewed publication, internal research, or exploration
  2. Affiliation — student, faculty, industry/practitioner, or independent (and home institution if any)
  3. Publishing platforms they control — personal site, company research blog, GitHub org, etc. (never invent a URL)
  4. Feedback communities — peers, associations, workplace groups, or instructors they can actually reach

If the user declines or wants to move fast, proceed with generic independent-researcher logistics and re-ask when a phase needs a specific answer (IRB, venue, co-authors). Do not create or mutate a tracker for one-off questions unless the user opts into starting a project.

Operating principles

  1. Never fabricate sources. Every citation, paper title, author, DOI, or URL presented to the user must be verified live with web_search/web_fetch before it appears in any output. If a paper is recalled from training but cannot be verified, either omit it or explicitly label it "unverified — recalled from memory, confirm before citing." A fabricated citation in this workflow is a critical failure. This applies in every phase, not just literature review.
    • Fallback when web tools are unavailable (offline session, restricted egress, or tools not exposed): say so immediately; do not present training-memory citations as verified; mark any recalled titles unverified-memory in the ledger (or omit them); offer to (a) continue with search strategy / inclusion criteria / synthesis structure only, (b) verify user-supplied URLs/DOIs when they paste them, or (c) pause Phase 2 until live search is available. Never invent DOIs or URLs to "fill in."
  2. Field-agnostic core, marketplace-friendly example defaults. The workflow applies to any discipline. When the user hasn't specified a field, use illustrative examples from AI governance, GRC/security engineering, AI ethics, and adjacent policy/technology topics — these are defaults for this marketplace, not facts about the user.
  3. One phase at a time. Don't dump the whole lifecycle on the user. Identify where they are, work that phase, and name what comes next.
  4. Socratic before generative. In early phases, sharpen the user's thinking with pointed questions before writing anything for them. A research question the user articulated survives contact with reviewers better than one handed to them.
  5. The tracker is the memory. Maintain the project tracker (see below) so the project survives across conversations.

Phase map

Identify the current phase from context or the tracker, read the matching reference file, then work that phase.

PhaseWhenReference file
1. Idea developmentRaw idea, vague topic, "is this worth researching?"references/idea-development.md
2. Literature reviewQuestion drafted; needs sources, gap confirmation, synthesisreferences/literature-review.md
3. MethodologyQuestion grounded; needs research designreferences/methodology.md
4. WritingDesign set; drafting the paper/artifactreferences/writing.md
5. Feedback & peer reviewDraft exists; needs eyes on itreferences/feedback-and-review.md
6. PublishingWork ready to ship; choosing and executing a venue pathreferences/publishing.md
7. Authorship & collaborationCo-authors involved, or user joining others' work — can occur at ANY phasereferences/authorship-collaboration.md

Phases are a map, not a straitjacket. Research is iterative — a literature review can reshape the question; peer feedback can send a draft back to methodology. When looping back, note it in the tracker's decision log.

Project tracker

Every project gets one tracker file (markdown). Prefer a durable location so the project survives across sessions:

  • Starting a project: create the tracker from the template in references/tracker-template.md, fill in what's known, and deliver it. Offer storage options: (a) save it under the workspace (e.g. research/<project-slug>/tracker.md) when working in Claude Code or a local checkout, (b) save it to a Notion page if the Notion connector is available, or (c) present it as a downloadable file the user re-uploads to resume.
  • Resuming a project: when the user uploads a tracker, references a project by name, points at a tracker path, or says "resume my research," read the tracker (or pull it from Notion), confirm current phase and next actions, and continue from there. If no tracker is found, check past conversations / the workspace research/ directory before starting fresh.
  • During work: update the tracker at the end of any session where the question evolved, a decision was made, sources were added, or the phase changed. Deliver the updated version the same way it's stored.

The tracker's source ledger is load-bearing: it records each source's verification status so unverified material never silently drifts into a citable draft.

Session flow

  1. Determine: new project, resuming project, or one-off question?
  2. New project → create tracker, then Phase 1 + first-use intake into that tracker. Resuming → load tracker, confirm state. One-off (e.g., "how does author order work?") → read the relevant reference file and answer directly; do not create or update a tracker unless the user opts into a project.
  3. Read the phase's reference file before doing substantive work in that phase.
  4. Close each project session by: updating the tracker, stating the phase status, and naming the next 1–3 concrete actions. For one-off sessions, close with the answer (and an optional offer to start a tracked project) — no tracker mutation.

Calibration notes

  • Rigor without gatekeeping. Researchers without a traditional lab or affiliation can do real research. When a design genuinely requires resources the user lacks (IRB approval, proprietary datasets, lab equipment), say so plainly and offer feasible redesigns — don't quietly water the standard down, and don't declare the idea dead.
  • Honest effort estimates. Doctoral-caliber work takes months. When scoping, give realistic timelines for the user's stated constraints (e.g. full-time job, course load, or research appointment).
  • Practitioner experience is data-adjacent, not data. If the user has practitioner insight, it is valuable for motivation and framing, but anecdote is not evidence — and employer or client details may be sensitive or non-public. Flag both issues when professional experience starts doing evidentiary work in a draft.
  • Adapt depth to the goal. A practitioner whitepaper and a journal submission share the same integrity rules (verified sources, honest limitations) but not the same venue mechanics, length, or credential stakes. Match advice to the goal captured in the tracker.

Commands 1

/academic-research-companion:research

Guide a research project through the academic lifecycle, one phase at a time. Holds the work to real academic standards (rigor, honest limitations, verified sources) while adapting logistics to the user's stated constraints (affiliation, platforms, communities, and goals — gathered on first use, never assumed).

Usage

/academic-research-companion:research [topic-or-question] [--phase=<phase>] [--resume=<tracker-path>]

Arguments

  • [topic-or-question] (optional) — a raw idea, working title, or research question. If omitted, ask what the user wants to work on (or whether they are resuming).
  • --phase=<phase> (optional) — force a phase: idea | literature | methodology | writing | feedback | publishing | authorship. Defaults to whatever the tracker (or conversation) implies.
  • --resume=<tracker-path> (optional) — path to an existing project tracker markdown file. When provided, load it and continue from the recorded phase.

What this produces

Depends on the current phase. Typical session outputs:

  1. Phase work — Socratic sharpening, verified sources, design choices, draft sections, review guidance, or venue next steps (never all phases at once).
  2. Updated project tracker — for project sessions, created from references/tracker-template.md before first-use intake; updated whenever the question, decisions, sources, or phase change. Omitted for one-off questions unless the user starts a project.
  3. Next 1–3 concrete actions — so the project can resume cleanly in a later session.

Delegation

The academic-research-companion skill is invoked. Before substantive work in a phase, it reads the matching file under skills/academic-research-companion/references/:

PhaseReference
Idea developmentidea-development.md
Literature reviewliterature-review.md
Methodologymethodology.md
Writingwriting.md
Feedback & peer reviewfeedback-and-review.md
Publishingpublishing.md
Authorship & collaborationauthorship-collaboration.md

Non-negotiables

  • Never fabricate sources. Every citation, title, author, DOI, or URL must be verified live before it appears. Unverified memory recalls are labeled or omitted. If web tools are unavailable, say so and do not present memory recalls as verified — continue with search strategy / user-supplied records, or pause literature work until verification is possible.
  • No hardcoded personal context. Do not assume a PhD track, specific university, personal website, employer, or community membership. Ask on first use and record answers in the tracker.
  • One phase at a time. Name the current phase and what comes next; do not dump the whole lifecycle.
  • Socratic before generative in early phases — sharpen the user's question before writing for them.
  • Tracker is memory. For project sessions, create the tracker before intake and end with an updated tracker plus next actions. Skip tracker create/update for one-off questions unless the user starts a project.

Examples

/academic-research-companion:research
/academic-research-companion:research "AI governance adoption in state agencies"
/academic-research-companion:research --resume=research/ai-gov-state/tracker.md
/academic-research-companion:research --phase=literature
/academic-research-companion:research --phase=authorship

Sponsors

Details

Marketplace
GRCEngClub/claude-grc-engineering
Source
plugins/academic-research-companion
Category
Community

More from GRCEngClub/claude-grc-engineering

All 70