# Claude Research Kit

> A rigorous co-author for Claude Code — source-grounded academic writing for LaTeX + BibTeX. The kit is a configuration system that layers on top of Claude Code CLI: advisory rules in CLAUDE.md, deterministic shell hooks in .claude/hooks/ (citation gates, fabrication blocks), review agents, skills, and a Literature Vault. The cardinal rule it enforces: every claim traces to a real source; never invent a citation, DOI, quote, or quantity; never overclaim beyond the evidence.

## Install

```bash
npx @tansuasici/claude-research-kit init
```

Source: https://clauderesearchkit.tansuasici.com
Repository: https://github.com/tansuasici/ClaudeResearchKit

## Getting Started

- [Introduction](https://clauderesearchkit.tansuasici.com/docs): A rigorous co-author for Claude Code — source-grounded academic writing for LaTeX + BibTeX.
- [Why This Kit](https://clauderesearchkit.tansuasici.com/docs/why-this-kit): Why a configuration kit beats prompting carefully — deterministic citation discipline, a Literature Vault, and review agents that pre-empt Reviewer 2.
- [FAQ](https://clauderesearchkit.tansuasici.com/docs/faq): Common questions about Claude Research Kit — LaTeX requirement, how the citation gates work, the Literature Vault, and cross-tool export.
- [CLAUDE.md](https://clauderesearchkit.tansuasici.com/docs/claude-md): Core agent instructions — the brain of the kit, where the cardinal rule lives.
- [Manuscript Map](https://clauderesearchkit.tansuasici.com/docs/manuscript-map): The single most important file — thesis, contribution, target venue, section budgets, key sources. Read first, every session.

## Writing Discipline

- [Writing Workflow](https://clauderesearchkit.tansuasici.com/docs/writing-workflow): The full Question → Evidence → Draft → Verify → Cite loop and outline template.
- [Citation Discipline](https://clauderesearchkit.tansuasici.com/docs/citation-discipline): Sourcing rules — never invent a citation, DOI, quote, or quantity.
- [Academic Style](https://clauderesearchkit.tansuasici.com/docs/academic-style): Calibrated language — match verbs and quantifiers to what the evidence licenses.
- [Statistics](https://clauderesearchkit.tansuasici.com/docs/statistics): Numerical reporting — effect sizes, confidence intervals, N, and avoiding causal overclaim.
- [Reproducibility](https://clauderesearchkit.tansuasici.com/docs/reproducibility): Data and code availability — what an independent team needs to rerun the work.
- [Peer Review](https://clauderesearchkit.tansuasici.com/docs/peer-review-guide): How the kit simulates a tough-but-fair Reviewer 2 before you submit.

## Field Overlays

- [Field: AI / ML](https://clauderesearchkit.tansuasici.com/docs/field/ai-ml): ML/NLP venue cues (NeurIPS/ICML/ACL/EMNLP), reproducibility, baselines & ablations, eval contamination.
- [Field: Life Sciences](https://clauderesearchkit.tansuasici.com/docs/field/life-sciences): ARRIVE/STROBE/PRISMA standards, IRB/IACUC ethics, wet-lab reproducibility, figure integrity, GEO/SRA deposition.
- [Field: Social Sciences](https://clauderesearchkit.tansuasici.com/docs/field/social-sciences): APA 7, preregistration & the replication crisis, construct validity, qualitative coding, effect sizes over bare p.
- [Field: Medicine](https://clauderesearchkit.tansuasici.com/docs/field/medicine): CONSORT/STROBE/STARD/SPIRIT, trial registration, effect measures (ARR, NNT, ITT), bias, COI disclosure.

## Agents

- [Peer Reviewer Agent](https://clauderesearchkit.tansuasici.com/docs/agents/peer-reviewer): Simulates a tough-but-fair Reviewer 2 — novelty, soundness, claim↔evidence support, recommendation.
- [Integrity Reviewer Agent](https://clauderesearchkit.tansuasici.com/docs/agents/integrity-reviewer): Research-integrity scan — overclaim, p-hacking/HARKing, citation misuse, missing limitations.
- [Fact Checker Agent](https://clauderesearchkit.tansuasici.com/docs/agents/fact-checker): Claim-by-claim verification against sources — Supported / Overstated / Unsupported / Uncited.
- [Outline Planner Agent](https://clauderesearchkit.tansuasici.com/docs/agents/outline-planner): Turns a thesis into a claim-driven IMRaD outline with evidence and word budgets.
- [Vault Maintainer Agent](https://clauderesearchkit.tansuasici.com/docs/agents/vault-maintainer): Heavy-lifting Literature Vault worker — ingest, cross-reference, health checks. Never fabricates a source.

## Recipes

- [Recipes](https://clauderesearchkit.tansuasici.com/docs/recipes): Concrete how-to guides for the things you'll actually do — fill the manuscript map, build the vault, respond to reviewers, add a field overlay.
- [Fill the Manuscript Map](https://clauderesearchkit.tansuasici.com/docs/recipes/fill-the-manuscript-map): The single most important setup step — give the agent a thesis, a venue, section budgets, and key sources so it stops drifting and overclaiming.
- [Build the Literature Vault](https://clauderesearchkit.tansuasici.com/docs/recipes/build-the-literature-vault): Ingest your sources into a grounded annotated bibliography so the cardinal rule has somewhere to trace claims to — never a fabricated source.
- [Respond to Reviewers](https://clauderesearchkit.tansuasici.com/docs/recipes/respond-to-reviewers): Draft a point-by-point response letter that quotes each comment, states the change and its location, and never claims a change that wasn't actually made.
- [Add a Field Overlay](https://clauderesearchkit.tansuasici.com/docs/recipes/add-a-field-overlay): Wire in discipline-specific reporting standards — CONSORT, ARRIVE, APA 7 — so the agent uses the right nomenclature and structure for your field.

## Audit Skills

- [Claim Check](https://clauderesearchkit.tansuasici.com/docs/claim-check): Walk every substantive claim in a section, classify it (cited / author's-own / common-knowledge / UNSUPPORTED), verify the citation licenses the claim's verb and quantifier, and report.
- [Citation Audit](https://clauderesearchkit.tansuasici.com/docs/citation-audit): Deep manual bibliography health check — dangling \cite keys, orphan .bib entries, duplicates, malformed/placeholder DOIs, missing required fields, inconsistent author/journal formatting, and.
- [Gap Finder](https://clauderesearchkit.tansuasici.com/docs/gap-finder): Breadth-first scan of a draft for unsupported and uncited claims and missing-evidence gaps — classify every claim, list what is UNCITED/UNSUPPORTED, and for true gaps emit search directions.
- [Stats Check](https://clauderesearchkit.tansuasici.com/docs/stats-check): Run the agent_docs/statistics.md checklist over a Results section — flag bare p-values, missing N/effect-size/CI, causal overclaim on observational data, multiple-comparison issues, and numbers that.
- [Methods Review](https://clauderesearchkit.tansuasici.com/docs/methods-review): Reproducibility check of the Method(s) section against agent_docs/reproducibility.md — enumerate what an independent team needs to rerun the work, check the section, and flag every missing ingredient.
- [Journal Fit](https://clauderesearchkit.tansuasici.com/docs/journal-fit): Assess a manuscript's fit to a target journal/venue — scope, novelty bar, length & structure limits, reference style (ACS/IEEE/APA/Nature), audience, article types — and output a fit score with.
- [Scorecard](https://clauderesearchkit.tansuasici.com/docs/scorecard): Aggregate reports/session-audit.log (one JSON line per session, written by the SessionEnd hook) into a per-session table plus a windowed summary — citation-gate pass rate, which guardrail hooks.

## Workflow Skills

- [Manuscript Cycle](https://clauderesearchkit.tansuasici.com/docs/manuscript-cycle): End-to-end orchestrator — runs the whole CLAUDE.md research lifecycle for a section or manuscript as one command (outline → ground → draft → verify → review → revise), halting on any gate failure.
- [Submission Pipeline](https://clauderesearchkit.tansuasici.com/docs/submission-pipeline): Pre-submission review battery — runs the peer-reviewer, integrity-reviewer, and fact-checker agents plus the deterministic audits in parallel over the whole manuscript, dedupes, confidence-gates, and.
- [Outline](https://clauderesearchkit.tansuasici.com/docs/outline): Turn a thesis + target venue into a claim-driven IMRaD outline — each section is the one claim it establishes plus the evidence needed and a word budget — ready for MANUSCRIPT_MAP.md, flagging.
- [Abstract](https://clauderesearchkit.tansuasici.com/docs/abstract): Draft or tighten the abstract as a contract — every number and claim in it must appear identically in the body, within the venue's word limit, calibrated to what the paper actually shows.
- [Literature Review](https://clauderesearchkit.tansuasici.com/docs/literature-review): Synthesize a related-work / literature-review section from the project's OWN library (references.bib + sources/ + vault) — thematic, gap-driven, calibrated, real citations only.
- [Peer Review](https://clauderesearchkit.tansuasici.com/docs/peer-review): Run a full simulated peer review — dispatch the peer-reviewer and integrity-reviewer agents over the manuscript, dedupe their findings, and produce a referee report with a recommendation.
- [Response To Reviewers](https://clauderesearchkit.tansuasici.com/docs/response-to-reviewers): Draft a point-by-point response letter — quote each reviewer comment, state the change made and its exact location, stay courteous, and NEVER claim a change not actually made.
- [Cover Letter](https://clauderesearchkit.tansuasici.com/docs/cover-letter): Draft a concise, honest editor cover letter from MANUSCRIPT_MAP — states the contribution, fit to the venue, and required declarations, with no fabricated significance or invented metrics.
- [Plain Language Summary](https://clauderesearchkit.tansuasici.com/docs/plain-language-summary): Draft a lay / plain-language summary for a general audience, funder, or a journal's required PLS — accessible to a non-specialist without distorting the science, with a claim-by-claim fidelity check.
- [Reference Format](https://clauderesearchkit.tansuasici.com/docs/reference-format): Convert or normalize the bibliography's citation style via the toolchain (biblatex/biber, CSL via pandoc, bibtex .bst) — deterministic, presentation-only, never altering the underlying facts and.
- [Retro](https://clauderesearchkit.tansuasici.com/docs/retro): Windowed retrospective on the writing process — what shipped (sections drafted, commits over the window), recurring reviewer critiques (tasks/reviews/ by applies_to frequency), what was learned.

## Meta Skills

- [Note](https://clauderesearchkit.tansuasici.com/docs/note): Append a timestamped tagged line (finding / decision / summary) to the session journal at .hook-state/session-journal.md, so a discovered fact, a settled choice, or a transient breadcrumb survives.
- [Review Resurface](https://clauderesearchkit.tansuasici.com/docs/review-resurface): Surface dormant reviewer-feedback notes from tasks/reviews/ (and _archive/) whose applies_to topics match the current task, returning POINTERS ONLY — paths plus frontmatter, never bodies.

## Literature Vault (module)

- [Literature Vault (VAULT.md)](https://clauderesearchkit.tansuasici.com/docs/vault-schema): Literature Vault schema — annotated bibliography, source/concept/entity pages, ingest workflow.
- [Lit Ingest](https://clauderesearchkit.tansuasici.com/docs/lit-ingest): Ingest ONE raw source (a sources/ PDF or .txt path, or pasted text) into the Literature Vault — read it, write a vault/summaries/<bibkey>.md annotated page with claims+locators and verbatim quotes,.
- [Lit Lint](https://clauderesearchkit.tansuasici.com/docs/lit-lint): Health-check the Literature Vault — find cross-source contradictions, orphan pages (a summary with no matching references.bib key, or a .bib key with no summary), broken [[wikilinks]], claims missing.
- [Lit Briefing](https://clauderesearchkit.tansuasici.com/docs/lit-briefing): A short "since last time" briefing from vault/log.md + vault/index.md — recently ingested sources, open follow-ups and citation-chaining leads, and gaps relative to MANUSCRIPT_MAP.md → Thesis (themes.

## HTML Artifacts (module)

- [HTML Artifacts (ARTIFACTS.md)](https://clauderesearchkit.tansuasici.com/docs/artifacts-schema): HTML artifact conventions — when to prefer HTML over markdown/LaTeX, artifact types, two-way interaction patterns.

## Reference

- [Changelog](https://clauderesearchkit.tansuasici.com/docs/changelog): All notable changes to Claude Research Kit.

## Optional

- [Full content (llms-full.txt)](https://clauderesearchkit.tansuasici.com/llms-full.txt): every page concatenated for single-shot ingestion