From deep-research
Bootstrap the deep research workspace directory structure and verify the environment is configured correctly.
How this skill is triggered — by the user, by Claude, or both
Slash command
/deep-research:initThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Initialize the deep research workspace.
Initialize the deep research workspace.
Create the .deep-research/ directory structure if it doesn't exist:
.deep-research/
└── runs/
Verify the environment:
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS environment variable)Report the status:
If $ARGUMENTS contains a topic, also initialize a new run for that topic using:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/dr_init_run.py "$ARGUMENTS"
npx claudepluginhub defiect/deep-research-pluginResearches codebases in Phase 1: analyzes architecture, patterns, risks on existing projects; or investigates tech stack, conventions, data-model on zero-base projects using WebSearch + Context7.
Installs OMCR project infrastructure: CLAUDE.md markers, agent memory directories, bibliography stubs, and a permissions allowlist. Safe to re-run.
Initializes a research project with folder structure, study_spec.md, and analysis_plan.md. Runs once at project start; does not analyze or audit data.