Give Claude Opus 5.5 responsibility for reasoning, design judgment, read-only investigations, recommendations, or finished text drafts. Use when the result benefits from thoughtful reasoning or taste, when asked to consult Claude, or when supplying the Claude seat of an independent review. Completed edits and executable experiments belong to delegate-claude.
79%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
Fix and improve this skill with Tessl
tessl review fix ./.agents/skills/consult-claude/SKILL.mdThe skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
The skill mainly routes reasoning work to Claude, but it tells the agent to request approval to run the launcher outside the Codex workspace sandbox and to run `claude auth login` to create a new work credential profile, which bypasses a security boundary and changes machine login state.
EpicenterHQ/epicenter
04f87cb
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.