Score and improve an artifact with a frozen rubric, independent models, implemented edits, and bounded rescoring
72%
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 ./.claude/skills/skill-refine/SKILL.mdThe canonical home for this skill is skill-refine in nyldn/claude-octopus
The 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-supplied artifact and project files, which are no-risk, but it also obtains remote artifacts and performs model-assisted research, so the agent must fetch outsider-authored content from arbitrary URLs it selects rather than having outsiders post into a monitored queue.
nyldn/claude-octopus
9a6967a
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.