Work out where a teammate, the champion, or a team is on the steps of AI adoption, and what to try next. Use when a champion wants to help someone move up a step.
77%
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 ./plugins/champion-kit/skills/climb/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 only outsider-exposure path is the optional, consented read of the champion's own Claude Code transcripts by repo-scout, which may contain web-fetched or pasted external text, but its return is strictly validated to counts, names, and citations.
anthropics/claude-plugins-official
43fd1f9
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.