mattpocock/researchv1.1

research

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

NewUpdated Sep 9, 2026

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.

Files2

2 files · 1.1 KB

Select a file to preview

Overall Score

52/100

Grade

Adequate

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

Quality

Clarity

Completeness

Summary

This skill directs an agent to spawn a background research process that investigates user questions against primary sources (official documentation, source code, APIs) and captures findings as a Markdown file in the repository. The skill emphasizes source verification and proper citation, delegating research work while keeping the main agent available.

Detected Capabilities

file writemarkdown generationbackground process spawningnetwork access (documentation fetch)source code analysis

Trigger Keywords

Phrases that agents use to match this skill to user intent.

research from primary sourcesinvestigate api documentationgather technical specsverify library behaviordelegate background research

Risk Signals

INFO

Outbound network requests to fetch primary sources (official docs, APIs)

core instruction

INFO

File write to repository directories following existing conventions

core instruction

Use Cases

Research API documentation and behavior to inform development decisions
Gather technical specifications from official sources for architecture planning
Investigate edge cases or undocumented behavior in third-party libraries
Build a reference document of facts verified against primary sources for team knowledge base
Delegate background research on emerging frameworks or tools while continuing primary work

Quality Notes

Strength: Clear emphasis on primary sources and citation minimizes misinformation risk
Strength: Repository-scoped output placement respects existing project conventions
Weakness: No error handling guidance — what if a primary source is unreachable or behind authentication?
Weakness: No explicit guardrails on output file size or scope — background agent could generate excessively large files
Weakness: Lacks guidance on how to structure citations or validate source authenticity
Weakness: No examples of what a well-formed research output should look like
Weakness: No discussion of research timeout or depth limits — agent could spend unbounded time on single investigation
Weakness: Very minimal instruction content overall; delegated entirely to background agent's judgment

Model: claude-haiku-4-5-20251001Analyzed: Sep 9, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

v1.1
Content updated
✦ AIAdds agents/openai.yaml configuration file and clarifies primary-source guidance with parenthetical phrasing.
2026-09-09
LATEST
v1.0
2026-07-03
View This VersionInitial version

Use mattpocock/research in your dev environment — a Developer account adds skills to your library and syncs them via the SkillRepo CLI.

Start a Developer trial