OpenParable
Skip to content
← Back to skills

research:archive

Productivity

research:archive is an Agent Skill for productivity published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Archive completed research. Moves the research to archive/ and updates its status.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/data/research-archive/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/research-archive, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Research Archive Skill

Archive a completed research plan after findings have been synthesized and consumed.

Process

  1. Identify the research to archive:

    • If the user specifies a number/name, use that
    • Otherwise, scan research/NNNN-*/ (exclude archive/ and unnumbered legacy directories) for research with status "synthesized" in .research-state.json
    • If multiple candidates, ask user to choose
  2. Verify completion:

    • Check that synthesis.md exists
    • Check that findings files exist for each question
    • If synthesis is missing, ask: "Research has no synthesis yet. Archive anyway?"
  3. Update research files:

    Update research-plan.md status:

    ## Status: ARCHIVED
    
    **Archived:** YYYY-MM-DD
    

    Update .research-state.json:

    {
      "status": "archived",
      "archived_at": "2026-01-28T10:30:00Z",
      "updated_at": "2026-01-28T10:30:00Z",
      ...existing fields...
    }
    
  4. Move to archive:

    mv research/NNNN-topic-name research/archive/
    
  5. Confirm to user:

    **Archived:** `research/archive/NNNN-topic-name/`
    **Status:** ARCHIVED
    **Questions:** N answered
    **Synthesis:** Yes/No
    **Archived:** YYYY-MM-DD
    

Notes

  • Research referenced by implementation plans (via relative paths like ../../research/NNNN-topic/) will have broken links after archiving. The archive path becomes ../../research/archive/NNNN-topic/. Consider this before archiving research that active plans reference.
  • Unnumbered legacy research directories (e.g., dagre-layout/, edge-routing-deep-dive/) should not be archived through this skill — they predate the numbering convention.