explore Eval report.

Task wording matches this skill metadata.

• Evaluate explore before installing it in an agent workflow
• coding-agents
• Coding agents workflows; Claude Code teams; builders willing to evaluate younger projects

Install handoff is available.

• npx skills add darkroomengineering/cc-settings --skill explore

standard package or runtime install path

• npx skills add darkroomengineering/cc-settings --skill explore

Potentially useful, but at least one trust signal needs human inspection.

• Manual review
• 42 GitHub stars
• MIT

Needs review

• References to 'tldr semantic' and 'tldr impact' assume a specific MCP tool that may not be present; the skill could be more explicit about fallbacks when TLDR is unavailable in Claude environments.

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

• Test manually in an isolated workspace and compare against safer alternatives.
• High-risk permission hints: Shell or command execution

MIT

• MIT

shell or command execution, filesystem or document access

• Shell or command execution: high
• Network access: medium
• Filesystem access: medium