用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/shenli/devtool-ax-kit --skill ax-comparison命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Capture agent runs with checkpoints, effect receipts, and redacted trajectories.
Build independent, deterministic verifiers for agent-tool tasks.
Design controlled coding-agent tasks for measuring developer-tool agent experience.
正在显示 SKILL.md
| name | ax-comparison |
| description | Compare raw and official agent-tool surfaces using replicated AX tasks. |
Compare one controlled task under clearly named conditions, such as public docs/CLI versus an official Skill, MCP server, or plugin. Hold the fixture, verifier, resource limits, and prompt intent constant. Randomize or repeat runs when practical, and record timing, retries, duplicate effects, recovery, and transcript safety.
Treat differences as agent-usability evidence unless the protocol isolates a vendor defect. Report non-reproductions and alternative explanations. Do not generalize from a single successful run.
Attribute each failure to one layer where possible: task/model, harness/session, tool interface, or external infrastructure. Track human attention and verifier disagreement alongside completion and wall-clock time.
