Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From oh-my-claudecode-research
Installs OMCR project infrastructure: CLAUDE.md markers, agent memory directories, bibliography stubs, and a permissions allowlist. Safe to re-run.
npx claudepluginhub youngeun1209/oh-my-claudecode-research --plugin oh-my-claudecode-researchHow this skill is triggered — by the user, by Claude, or both
Slash command
/oh-my-claudecode-research:omcr-setupThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
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.
First-research-project initialization for OMCR — interviews user about working title, hypothesis, venue, datasets; fills CLAUDE.md placeholders; scaffolds LaTeX manuscript directory.
Automates oh-my-codex (OMX) setup in Codex CLI projects: global npm install (skippable), init with omx setup/doctor, idempotent .gitignore .omx addition, AGENTS.md injection with confirmation. Invoke via /mst:setup-omx.
Initializes Claude Code project configuration with directory skeleton, AGENTS.md, and interactive setup for project-specific rules and workflows. Use when starting a new project or configuring Claude Code.
Share bugs, ideas, or general feedback.
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.
## Project context, ## Research stack, ## Language preference blocks with placeholder fields. (Filled in later by /start-research.).claude/agent-memory/<agent>/MEMORY.md for the 6 core agents, seeded from the canonical template. Existing files are never touched.paper/references.bib (with header comment) and references.csv (with header row) at default paths. Existing files are never touched..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.neuro-fmri, etc.)All of those belong to /start-research.
Execute phases sequentially. For each phase, read the linked file and follow its instructions exactly.
phases/01-state-check.md.phases/02-claude-md-scaffold.md.phases/03-agent-memory.md.phases/04-bibliography.md.phases/05-permissions.md.phases/06-report.md.CLAUDE.md marker blocks are inserted only if missing. Existing blocks are inspected but not overwritten.MEMORY.md files are never overwritten (phase 3).references.bib / references.csv are never overwritten (phase 4)..claude/settings.json.backup.YYYY-MM-DD.After phase 6's report, recommend the user run /start-research to fill in their project context and scaffold the manuscript.