Conduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc.
73%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./skills/research-en/research/SKILL.mdThe skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
In SKILL.md Step 2 (“Web Search Supplement”), the agent performs WebSearch and then ingests the returned sources’ contents via the “web-search-agent” background workflow, while user-controlled {topic} and {time_range} determine what external pages are searched and summarized (outsider-authored text exposure).
Weizhena/Deep-Research-skills
6ce38f6
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.