Review an existing scientific manuscript, evidence, citations and figures and verify targeted revisions. Use for independent manuscript critique or a requested response to feedback.
76%
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 ./paperspine5/core/01_PaperSpine4/src/skill-editions/paper-spine-review/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 required workflow reads the user-selected manuscript and then actively fetches cited sources and citation passages, which are outsider-authored text the agent must choose to retrieve rather than text delivered to a monitored queue.
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.