Use when a wrong answer is expensive: strategy research, comparing several products or markets, validating a hypothesis with outside data. Fans out searches and sub-agents, triangulates each claim across 3+ sources and saves every source with quotes. Quick facts: answer directly.
79%
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 ./research/meta-research/skills/meta-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.
The agent performs active searches and fetches web pages/external data sources as part of its research workflow, which constitutes low-risk exposure to outsider-authored free text.
alirezarezvani/claude-skills
f8593c4
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.