admiral Eval report.

Task wording matches this skill metadata.

• Evaluate admiral before installing it in an agent workflow
• research
• Research agents workflows; Claude Code teams; builders willing to evaluate younger projects

Install handoff is available.

• npx skills add RConsortium/pharma-skills --skill admiral

standard package or runtime install path

• npx skills add RConsortium/pharma-skills --skill admiral

Good trust signals with a few areas worth checking before rollout.

• Strong shortlist
• 104 GitHub stars
• MIT

Needs review

• The SKILL.md is a parent skill and does not include a complete end-to-end workflow; it relies on child skills for dataset-specific derivations. This is by design but may be less immediately actionable without the child skills loaded.

Usable candidate, but the agent should surface permission and audit notes before installation.

• Require human approval before installing into a real workspace.
• The SKILL.md is a parent skill and does not include a complete end-to-end workflow; it relies on child skills for dataset-specific derivations. This is by design but may be less immediately actionable without the child skills loaded.

MIT

• MIT

no high-risk permission surface in public metadata

• Network access: medium
• Filesystem access: medium