원클릭으로 Manus에서 모든 스킬 실행

omcr-setup

스타30

포크8

업데이트2026년 5월 19일 23:39

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 install a curated permission allowlist in `.claude/settings.json`. Does NOT ask about the user's research project (no working title / hypothesis / venue / preset interview). For that, run `/start-research` after this completes. Safe to re-run — never overwrites existing user content.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

youngeun1209

youngeun1209/oh-my-claudecode-research

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

Setup

Install-style flow that lays down the infrastructure OMCR needs to operate in a project. This is OMCR's analog of OMC's /omc-setup — no research-interview questions, no preset selection, no manuscript scaffolding. Just makes the plugin work.

After /omcr-setup completes, the user should run /start-research for interview-style first-project initialization.

When this skill is invoked, immediately execute the workflow below. Do not only restate or summarize these instructions back to the user.

Safe to re-run. Diffs against current state; only adds what is missing.

What this installs

CLAUDE.md infrastructure — ## Project context, ## Research stack, ## Language preference blocks with placeholder fields. (Filled in later by /start-research.)
Agent memory directories — .claude/agent-memory/<agent>/MEMORY.md for the 6 core agents, seeded from the canonical template. Existing files are never touched.
Bibliography files — empty paper/references.bib (with header comment) and references.csv (with header row) at default paths. Existing files are never touched.
Permission allowlist — curated .claude/settings.json so common research-flow tools (read-only git, file search, edits, LaTeX build, citation lookups, figure crop) don't prompt every time. Dangerous operations (git write, file deletion, wildcard bash) are intentionally excluded so they always prompt.

What this explicitly does NOT do

Ask about your project (working title, hypothesis, target venue, datasets, etc.)
Pick or apply a domain preset (neuro-fmri, etc.)
Scaffold the LaTeX manuscript directory
Clone Overleaf or commit anything

All of those belong to /start-research.

Phase execution

Execute phases sequentially. For each phase, read the linked file and follow its instructions exactly.

Phase 1 — State check. Read phases/01-state-check.md.
Phase 2 — CLAUDE.md scaffold. Read phases/02-claude-md-scaffold.md.
Phase 3 — Agent memory. Read phases/03-agent-memory.md.
Phase 4 — Bibliography. Read phases/04-bibliography.md.
Phase 5 — Permissions. Read phases/05-permissions.md.
Phase 6 — Report. Read phases/06-report.md.

Re-running policy

CLAUDE.md marker blocks are inserted only if missing. Existing blocks are inspected but not overwritten.
Existing MEMORY.md files are never overwritten (phase 3).
Existing references.bib / references.csv are never overwritten (phase 4).
Permission allowlist (phase 5) prompts the user before replacing or merging. Existing broad wildcards trigger a narrowing offer with backup to .claude/settings.json.backup.YYYY-MM-DD.

Final recommendation

After phase 6's report, recommend the user run /start-research to fill in their project context and scaffold the manuscript.

이 저장소의 다른 Skills

같은 저장소

paper-ingest

youngeun1209/oh-my-claudecode-research

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/ folder, upserts a row in that folder's index.csv, judges whether the paper is relevant to the project's narrative (from CLAUDE.md

2026-07-1030

save-session-log

youngeun1209/oh-my-claudecode-research

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 working record for the user, not a scientific artifact and not a status/sync report. Reconstructs content faithfully from the actual conversation; never invents. Use at the end of (or partway through) a session, or when the user types /save-session-log.

2026-07-1030

session-start

youngeun1209/oh-my-claudecode-research

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, no memory edits, no report files, no analysis runs. Runs in light mode (cheap, core files only — the default for auto-trigger) or full mode (full corpus sweep). Use at the start of a session to reproduce the effect of "understand this project", or when the user types /session-start.

2026-07-1030

update-version

youngeun1209/oh-my-claudecode-research

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 downstream tool points at a stale file, then offer to delete genuinely-obsolete archive files (never auto-delete). Reads the previously-current values from CLAUDE.md

2026-07-1030

cropfig

youngeun1209/oh-my-claudecode-research

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 into the outline.md figures dir, then inserts/updates image links after each result heading.

2026-05-1930

figure-bake

youngeun1209/oh-my-claudecode-research

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 artifacts in lockstep. The third Phase 2 engine — a 3-agent loop, more complex than `/iterate-revision`'s 2-agent loop, and the only Phase 2 engine that executes real code per iteration. Safe to re-run; safe to resume after BLOCKED or HALT.

2026-05-1930

name

omcr-setup

description

Setup

After /omcr-setup completes, the user should run /start-research for interview-style first-project initialization.

When this skill is invoked, immediately execute the workflow below. Do not only restate or summarize these instructions back to the user.

Safe to re-run. Diffs against current state; only adds what is missing.

What this installs

CLAUDE.md infrastructure — ## Project context, ## Research stack, ## Language preference blocks with placeholder fields. (Filled in later by /start-research.)
Agent memory directories — .claude/agent-memory/<agent>/MEMORY.md for the 6 core agents, seeded from the canonical template. Existing files are never touched.
Bibliography files — empty paper/references.bib (with header comment) and references.csv (with header row) at default paths. Existing files are never touched.
Permission allowlist — curated .claude/settings.json so common research-flow tools (read-only git, file search, edits, LaTeX build, citation lookups, figure crop) don't prompt every time. Dangerous operations (git write, file deletion, wildcard bash) are intentionally excluded so they always prompt.

What this explicitly does NOT do

Ask about your project (working title, hypothesis, target venue, datasets, etc.)
Pick or apply a domain preset (neuro-fmri, etc.)
Scaffold the LaTeX manuscript directory
Clone Overleaf or commit anything

All of those belong to /start-research.

Phase execution

Execute phases sequentially. For each phase, read the linked file and follow its instructions exactly.

Phase 1 — State check. Read phases/01-state-check.md.
Phase 2 — CLAUDE.md scaffold. Read phases/02-claude-md-scaffold.md.
Phase 3 — Agent memory. Read phases/03-agent-memory.md.
Phase 4 — Bibliography. Read phases/04-bibliography.md.
Phase 5 — Permissions. Read phases/05-permissions.md.
Phase 6 — Report. Read phases/06-report.md.

Re-running policy

CLAUDE.md marker blocks are inserted only if missing. Existing blocks are inspected but not overwritten.
Existing MEMORY.md files are never overwritten (phase 3).
Existing references.bib / references.csv are never overwritten (phase 4).
Permission allowlist (phase 5) prompts the user before replacing or merging. Existing broad wildcards trigger a narrowing offer with backup to .claude/settings.json.backup.YYYY-MM-DD.

Final recommendation

After phase 6's report, recommend the user run /start-research to fill in their project context and scaffold the manuscript.