Skillcrossroads

Skill Crossroads

[](https://sgharlow.github.io/ai-control-framework/) **Part of [Workshown](https://sgharlow.github.io/ai-control-framework/) — show your work.** [ai-control-framework](https://github.com/sgharlow/ai-control-framework) (the how) · [orchestra-lite](https://github.com/sgharlow/orchestra-lite) (the scale) · [ai-pr-bot](https://github.com/sgharlow/ai-pr-bot) (the enforcement) · [skillcrossroads](https://github.com/sgharlow/skillcrossroads) (the grade) · [recipes](https://github.com/sgharlow/claude-code-recipes) (the front door) · [case study](https://github.com/sgharlow/distraction)

[](https://skillcrossroads.com/s/sgharlow/skillcrossroads)

Claude Code artifacts graded by [Skill Crossroads](https://skillcrossroads.com) — click the badge for the evidence-cited scorecard.

**Know before you ship.** The signpost for Claude Code skills, agents, slash commands, MCP configs, and plugins — live at [skillcrossroads.com](https://skillcrossroads.com).

[](https://skillcrossroads.com/s/anthropics/skills)   

Every skill hits a crossroads before you ship it. Skill Crossroads reads a Claude Code artifact — a **Skill**, subagent, slash command, `.mcp.json` config, or plugin — against an evidence-based rubric and points you one of three ways: **ship, fix, or rethink**. You get a letter grade, an embeddable badge, and a fix list — every finding cited to a file and line.

• Ship — grade A/B. It is ready. Here is your badge.
• Fix — grade C/D. Specific, evidence-cited problems to correct first.
• Rethink — grade F. Fundamental issues (will not trigger, u