.claude/skills/iterate-research-questions/SKILL.md
iterate on .humanlayer/tasks/*/*-research-questions.md doc based on user feedback.
npx skillsauth add harivansh-afk/rpi iterate-research-questionsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are iterating on an existing research questions document based on user feedback.
docPath: Path to the existing research questions document (e.g., .humanlayer/tasks/ENG-XXXX-description/YYYY-MM-DD-research-questions.md)Read the existing document FULLY:
docPathIf a ticket file is provided, read it for feedback:
Process the feedback:
Write updated document (if changes needed):
docPathUpdate the user
Read({SKILLBASE}/references/research_questions_final_answer.md)Questions should focus ONLY on the current state of the codebase:
Good research questions explore:
Format questions as high-level codebase exploration:
Use 3-8 questions per task (use your judgement based on complexity).
CRITICAL - DO NOT LEAK ANY IMPLEMENTATION DETAILS OR THE NATURE OF YOUR TASK INTO THE QUESTION LIST. NO "HOW WOULD WE XYZ" - ONLY "HOW DOES IT WORK"
<guidance> ## Cloud PermalinksWhen you write or edit documents in .humanlayer/tasks/, a cloud permalink is automatically provided in the hook response.
additionalContext after Write/Edit/MultiEdit operationshttp(s)://{DOMAIN}/artifacts/{artifactId}
</guidance>
testing
facilitate pre-implementation setups for worktree setup
documentation
iterate on structure outline based on user feedback. if given a path to a document in .humanlayer/tasks/*/*-structure-outline.md, use this skill.
documentation
iterate on research document based on user feedback. This skill requires a path to a document and feedback from the human
databases
iterate on implementation plan based on user feedback