oh-my-claudecode-research

Plugin oh-my-claudecode-research from marketplace omcr in youngeun1209/oh-my-claudecode-research. Commands read from the repo's manifest — 1 month ago.

Skills (18)

• cropfig

  Three-step pipeline from a Keynote (.key) or PowerPoint (.pptx) deck to manuscript + outline. Func 1 exports vector PDFs per slide; func 2 crops them (vector preserved) and renders an outline-grade PNG from the same cropped artifact; func 3 copies PDFs into the LaTeX manuscript figures dir and PNGs

• figure-bake

  Drive one figure from design idea to manuscript-ready vector PDF + outline-ready PNG. Loops `@figure-descriptor` → `@analysis-implementer` → `@reviewer` against a single fig-id in `figures.json`, with the `cropfig` skill auto-invoked at the end of each implement phase to keep manuscript + outline ar

• iterate-revision

  Revise one manuscript section against the reviewer team until DONE, BLOCKED, or HALT. Loops `@paper-writer` ↔ `@reviewer` with a venue-specific reviewer brief, recording every iteration's issues + verdict to `reviews.json` and updating `paper.json.sections[name]` status / iter. The first OMCR engine

• literature-sweep

  Find, summarize, and verify N papers on a topic, then drop verified entries into `references.bib` and the literature summary CSV. Dispatches `@literature-curator` (one or many instances) over a CrossRef/OpenAlex candidate list, runs every survivor through the `verify-citation` skill, and writes the

• manuscript-scaffold

  Scaffold a LaTeX manuscript directory for a research project — copy the bundled skeleton (main.tex + sections/* + figures/ + references.bib + .gitignore + README), optionally apply a journal-specific documentclass from templates/journal-registry.json, optionally clone an Overleaf project and cache t

• omcr-setup

  Install OMCR infrastructure in a project — scaffold empty CLAUDE.md marker blocks (`## Project context` / `## Research stack` / `## Language preference`), create `.claude/agent-memory/` for the 6 core agents with canonical-template MEMORY.md, initialize empty `references.bib` + `references.csv`, and

• orchestrate

  Internal primitive skill — engine skills compose these four phases. Not invoked directly by the user. Provides state-read, dispatch, evaluate, and loop primitives over `.claude/omcr-state/` so that engines (`/iterate-revision`, `/literature-sweep`, `/respond-reviewer`, `/figure-bake`, `/outline-expa

• outline-expand

  Map-reduce engine — given an outline file and a `paper.json`, draft N sections in parallel by dispatching `@paper-writer` once per section in a single Agent-tool batch, then assemble the prose into each section's `paper.json.sections[name].path`. Passes a shared `nomenclature.md` payload to every di

• paper-ingest

  Ingest a research paper into the project's two-folder reading library. Use when the user hands you a paper — a PDF path, a DOI, or a URL — and wants it read, summarized, and indexed. The skill writes a project-agnostic summary (with a cropped main figure) to the library's bibliographic-management/ f

• respond-reviewer

  Read a reviewer letter, classify each comment by type, dispatch per-comment responses to the right specialist agent (`@paper-writer`, `@analysis-implementer`, `@literature-curator`), and assemble a complete rebuttal letter. Structural comments are surfaced to user attention rather than auto-dispatch

• save-session-log

  Write a structured Markdown record of the current session — the requests, the analyses run, the files touched, decisions made, and open next steps — to the project's session-logs dir (one dated file per invocation), then propagate any durable result/decision into the wiki knowledge vault. This is a

• session-start

  Session-orientation workflow — read the project's Markdown corpus (CLAUDE.md, the outline, project MEMORY, the wiki landing page), build a genuine understanding of the study, then report a concise project summary and an honest current-status snapshot. Read-only with zero side effects — no exports, n

• start-research

  Interview-driven first-research-project initialization — asks about working title, field, hypothesis, target venue, datasets, narrative spine; fills the CLAUDE.md placeholders that /omcr-setup scaffolded; applies an optional domain preset to agent memory (when the existing MEMORY.md is still canonic

• supervisor-drive

  Autonomous OMCR orchestrator. Surveys state across the 5 OMCR state files (paper, reviews, citations, figures, rebuttals), picks the highest-priority engine from a hardcoded bottleneck-ranker, runs it through one of the 5 OMCR engines, then re-evaluates state from scratch and loops. Three modes — in

• sync

  Reconcile current state (captured figure deck) with final goal (outline document), refresh agent memories with factual drifts, and produce a dated status snapshot. Reads `## Research stack` config from the user's CLAUDE.md (Deck file / Outline file / Figure count / Report language / Sync report dir)

• todofig

  Compare a captured-figure deck against an outline document and produce a prioritized TODO of gaps (P0/P1/P2). Reads `## Research stack` config from the user's CLAUDE.md (Deck file / Outline file / Figure count / Result pattern / Report language / Report output dir). Accepts an optional figure identi

• update-version

  When a project artifact whose filename carries a version — the canonical outline or the figure deck — is bumped (e.g. v4→v5, ver7→ver8), propagate the new filename into every file that references the old one (CLAUDE.md, command/skill files, agent memories, manuscript anchors, export scripts) so no d

• verify-citation

  Verify that academic citations exist and match the metadata claimed for them, and optionally write verification results into a project summary table. Looks up DOIs against CrossRef, fetches canonical authors/title/year/journal and the abstract via OpenAlex, and reports any mismatch against a BibTeX

Slash commands (13)

• /oh-my-claudecode-research:figure-bake

  Drive one figure from design brief to manuscript-ready PDF + outline PNG. Three-agent loop (@figure-descriptor → @analysis-implementer → @reviewer) wrapped around `cropfig` for the final artifact pass.

• /oh-my-claudecode-research:iterate-revision

  Revise one manuscript section against the reviewer team until DONE/BLOCKED/HALT. Writer ↔ reviewer loop driven by the orchestrate primitives.

• /oh-my-claudecode-research:literature-sweep

  Find, summarize, and verify N papers on a topic. Parallel-dispatch engine across `@literature-curator` instances; only verified entries enter the BibTeX file.

• /oh-my-claudecode-research:omcr-setup

  Install OMCR infrastructure (CLAUDE.md markers, agent-memory dirs, bibliography files, permission allowlist). No interview. Run /start-research after.

• /oh-my-claudecode-research:outline-expand

  Map-reduce engine — take an outline, dispatch @paper-writer in parallel, one per section, produce first drafts. Refinement is the user's call via /iterate-revision.

• /oh-my-claudecode-research:respond-reviewer

  Classify a reviewer letter into per-comment labels and dispatch each to the right specialist; assemble a rebuttal letter. Structural comments are routed to user attention, never auto-dispatched.

• /oh-my-claudecode-research:save-session-log

  Save a structured record of the current session — what was discussed, what was analyzed/built, where files were saved, decisions made, open next steps — to the session-logs dir. Writes one dated Markdown file per invocation and propagates durable results/decisions into the wiki knowledge vault.

• /oh-my-claudecode-research:session-start

  Read the project's Markdown corpus, build a genuine understanding of the study, and report a concise summary + honest current-status snapshot. The session-orientation command — read-only, no side effects. Light/full modes.

• /oh-my-claudecode-research:start-research

  Interview-driven first-research-project initialization — fills the CLAUDE.md placeholders that /omcr-setup scaffolded (working title, field, hypothesis, target venue, datasets, narrative spine), optionally applies a domain preset to agent memory, and scaffolds the LaTeX manuscript directory via the

• /oh-my-claudecode-research:supervisor-drive

  Autonomous orchestrator — survey state, pick the right OMCR engine, run it, re-evaluate, loop. Interactive by default. Safety-gated. Supports --auto, --plan-only, --resume, and budget caps.

• /oh-my-claudecode-research:sync

  Reconcile current state (captured figure deck) with final goal (outline document), refresh agent memories with drifts, optionally embed cropped figures into a target document. Produces a status snapshot — not a TODO (use /todofig for that).

• /oh-my-claudecode-research:todofig

  Compare a captured-figure deck against an outline document; produce a prioritized TODO of gaps (P0/P1/P2).

• /oh-my-claudecode-research:update-version

  When the canonical outline or the figure deck is bumped to a new version, find every file that points to the OLD filename/version and update it to the NEW one. Reads the current values from CLAUDE.md ## Research stack (Deck file / Outline file); prompts for the new files if not @-mentioned. Also sur

Subagents (6)

• analysis-implementer

  Use this agent when you need to implement analysis pipelines, write data processing code, run and debug computational experiments, or translate a scientific idea into working code. This agent handles statistical analyses, ML/DL model training, simulations, and data-engineering pipelines — primarily

• figure-descriptor

  Use this agent when you need to design figures for the manuscript — deciding how many panels a figure needs, what each panel shows, how to lay them out, what color palette to use, and what the caption should say. This agent thinks at high-impact-journal figure quality and gives implementation-ready

• literature-curator

  Use this agent when you need to find citations for specific claims, build or maintain the project's bibliography, verify that cited works exist and match the content you are citing them for, or resolve `[CITE: ...]` placeholders left by `paper-writer`. This agent owns **two files in lockstep**: the

• paper-writer

  Use this agent when you need to write, revise, or polish any part of the research manuscript — including the Introduction, Methods, Results, Discussion, Abstract, cover letter, or response to reviewers. This agent writes at the level of high-impact journals in your field.\n\nExamples:\n\n- User: \"W

• reviewer

  Use this agent when you need rigorous, adversarial peer review of any component of the manuscript — writing, figures, analyses, or the overall scientific claim — at the level of the target venue. This agent does not encourage; it identifies every weakness that would cause rejection and forces the te

• supervisor

  Use this agent when you need high-level direction for a research project — including sharpening the research question, coordinating other agents, reviewing their outputs, making judgment calls about what analyses matter, deciding what the paper should say, and driving the project from raw data to su

Hooks (4)

• PreToolUse

  bash "$CLAUDE_PLUGIN_ROOT"/hooks/pii-scrub.sh

• SessionStart

  bash "$CLAUDE_PLUGIN_ROOT"/hooks/memory-load.sh

• SessionStart

  bash "$CLAUDE_PLUGIN_ROOT"/hooks/setup-nudge.sh

• PostToolUse

  bash "$CLAUDE_PLUGIN_ROOT"/hooks/citation-warn.sh

Similar plugins