research-executor
Execute research experiments using TDD methodology. Pops plans from .claude/plans/research_tasks/, implements with smoke/unit/integration tests, and documents results to results.md. Use when: (1) executing the next experiment from the queue, (2) executing a specific plan by number, (3) running an ad-hoc research idea with TDD.
npx skills add majiayu000/claude-skill-registry --skill research-executor --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Research Executor Execute research experiments using Test-Driven Development (TDD). ## Plan Queue Plans are stored in `.claude/plans/research_tasks/plan-*.md`. ### Pop and Execute 1. **List plans**: `ls .claude/plans/research_tasks/plan-*.md` 2. **Select plan**: Default is `plan-1.md`, or specify `plan-N` 3. **Move to executed**: ```bash mkdir -p .claude/plans/research_tasks/executed mv .claude/plans/research_tasks/plan-{N}.md .claude/plans/research_tasks/executed/{YYYY-MM-DD}_{name}.md ``` 4. **Renumber remaining plans** sequentially (plan-2 → plan-1, plan-3 → plan-2, etc.) If no plans exist, ask user for an ad-hoc research idea. ## Execution Workflow ### Phase 1: Setup - Parse hypothesis, variables, success criteria from plan - Create directory: ``` experiments/{experiment_name}/ ├── README.md ├── notebook.ipynb # Primary deliverable ├── tests/ │ ├── smoke/ │ ├── unit/ │ └── integration/ ├── src/ └── results/ └── figures/ # All generated plots ``` ### Phase 2: Smoke Tests - Test data loading, API calls, metric computation - Implement minimal code to pass - Run: `uv run pytest experiments/{name}/tests/smoke/ -v` ### Phase 3: Unit Tests - Test each component (preprocessing, featu
- Plan Queue
- Pop and Execute
- Execution Workflow
- Phase 1: Setup
- Phase 2: Smoke Tests
- Phase 3: Unit Tests
- Phase 4: Integration Tests
- Phase 5: Finalize
- Jupyter Notebook Deliverable
- Notebook Structure
- Requirements
- Results Documentation
- Code Standards
mkdir -p .claude/plans/research_tasks/executed
mv .claude/plans/research_tasks/plan-{N}.md .claude/plans/research_tasks/executed/{YYYY-MM-DD}_{name}.mdWhat does the research-executor skill do?
Execute research experiments using TDD methodology. Pops plans from .claude/plans/research_tasks/, implements with smoke/unit/integration tests, and documents results to results.md. Use when: (1) executing the next experiment from the queue, (2) executing a specific plan by number, (3) running an ad-hoc research idea with TDD.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill research-executor --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.