Score
9.3
/ 10
Installs
381K
Repo Stars
237.3K
Last Updated
1d ago
Quality Ratio
96%
Description
Verified
Language
Shell
First Published
Jul 2026
Summary
The Research agent skill systematically gathers external knowledge, such as library behavior, API usage, and best practices, distilling it into a durable, citable research log to ensure agent outputs are grounded in facts. This agent skill is essential for developers working on projects that involve external dependencies, new technologies, or require adherence to established patterns like authentication or payment processing. It is a skill with 357K installs, indicating its broad utility across various development tasks. The agent skill guides the AI to scope unknown areas into concrete questions, gather information from primary sources, and distill findings into concise, sourced log entries. It strictly enforces source discipline, requiring every finding to cite a URL, repository, RFC, or paper, flagging unverified claims with a `?` rather than presenting them as fact. The skill also ensures that research outputs, labeled as `§R` rows, are handed off to the spec skill for durable logging, preventing the agent from directly writing architectural specifications.
Skill Definition
Spin up a background agent to do the research, so you keep working while it reads.
Its job:
- Investigate the question against primary sources (official docs, source code, specs, first-party APIs), not a secondary write-up of them. Follow every claim back to the source that owns it.
- Write the findings to a single Markdown file, citing each claim's source.
- Save it where the repo already keeps such notes; match the existing convention, and if there is none, put it somewhere sensible and say where.