Web research
Skill aizech/bernhard-zechmann-skills/skills/productivity/web-research
Modular AI agent skills used across engineering, writing, and research workflows. Model‑agnostic, composable, and production‑tested. Includes engineering, productivity, personal, and experimental skill packs.
npx -y skills add aizech/bernhard-zechmann-skills --skill web-researchAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Research a topic across multiple web sources and produce a cited report. Use when the user asks to research online, search the web, compare options, or produce a research report.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
1.3 KB, as published. Nobody here has run it
Web Research
Research a topic across multiple sources and synthesize the findings.
Process
-
Plan: create a folder
research_[topic_name]/and writeresearch_plan.mdwith:- Main question
- 2-5 non-overlapping subtopics
- Expected information per subtopic
- How results will be synthesized
-
Delegate: for each subtopic, spawn a research task with:
- Clear, specific question
- Instructions to save findings to
findings_[subtopic].md - 3-5 web searches maximum
-
Synthesize: read all findings files, then produce:
- Direct answer to the original question
- Integrated insights from all subtopics
- Source citations with URLs
- Gaps or limitations
-
Report (optional): write
research_report.mdif requested.
Best practices
- Plan before delegating.
- Use file-based communication for subagents.
- Stop at 3-5 searches per subtopic.
- Cite specific sources.
Note
Use fetch_url for URLs, not read_file.