From hb
Spawns a background agent to research a question against primary sources (docs, source code, specs) and saves findings as a cited Markdown file. Use when you need facts gathered without blocking your workflow.
How this skill is triggered — by the user, by Claude, or both
Slash command
/hb:researchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Spin up a **background agent** to do the reading, so the user keeps working while it investigates.
Spin up a background agent to do the reading, so the user keeps working while it investigates.
Give the agent this job:
.specs/research/<slug>.md and say where.Report the file path back when the agent finishes. Don't summarize the findings inline unless asked — the cited file is the deliverable.
npx claudepluginhub helderberto/agent-skills --plugin hbInvestigates questions against primary sources (official docs, source code, specs) and saves findings as a Markdown file. Delegates reading legwork to a background agent.
Investigates questions against high-trust primary sources (docs, source code, specs) and writes cited Markdown findings to a project conventions file.
Spawns a background agent to research a question against high-confidence primary sources (official docs, source code, APIs) and writes findings as a Markdown file in the repo.