research-implement
Build a research definition and execute the study based on a Linear issue.
Profile →npx skills add majiayu000/claude-skill-registry --skill research-implement --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 Implementation Build a research study definition and execute it based on a Linear issue created by `/research-evaluate`. ## Usage ```bash /research-implement ENG-XXX ``` ## Workflow ### Step 1: Get Issue Details ```python issue = mcp__linear__linear_getIssueById(id="ENG-XXX") ``` Extract from description: - Source file path - Data requirements (assets, timeframe, period) - Methodology - Charts/tables to reproduce ### Step 2: Read Source Material ```bash # Read the source markdown file cat report_notes/<topic>/<source_file>.md ``` Understand: - Exact signal logic - Position sizing rules - Rebalancing frequency - Any special conditions ### Step 3: Update Issue Status ```python mcp__linear__linear_updateIssue( id="ENG-XXX", stateId="49c7285c-33c4-443c-a0af-49b51b8e1739" # In Progress ) ``` ### Step 4: Create Research Definition Create a JSON definition file following the study generation grammar. **File location:** `project/definitions/test_runner/<source_id>_research.json` **Template:** ```json { "name": "<source_id>_research", "type": "RESEARCH", "description": "<hypothesis from source>", "source_reference": { "id": "<source_id>", "url": "<source_url>", "title": "<source_
- Usage
- Workflow
- Step 1: Get Issue Details
- Step 2: Read Source Material
- Step 3: Update Issue Status
- Step 4: Create Research Definition
- Step 5: Validate Definition
- Step 6: Build Job Data Binary (if needed)
- Step 7: Execute Study
- Step 8: Analyze Results
- Step 9: Compare with Source
- Step 10: Update Linear Issue
- Step 11: Update research.csv
- Definition Structure Reference
Read the source markdown file
cat report_notes/<topic>/<source_file>.md
cd /home/adesola/EpochDev/ClaudeCodeResearch
source .venv/bin/activate
Check JSON syntax
python -c "import json; json.load(open('project/definitions/test_runner/<source_id>_research.json'))"
Get tearsheet reports
Query data if neededWhat does the research-implement skill do?
Build a research definition and execute the study based on a Linear issue.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill research-implement --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.