跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
开发与测试

differential-audit

Compare two implementations of the same thing — a port (R↔Python↔Stata), a reimplementation, a replication package, a refactor, or a new version against the old — so that agreement means something. Freeze inputs first, inventory every expected output, test the comparator itself, compare every channel (not just the headline number), and give each divergence a stable ID and a smallest witness. Use for cross-language parity, replication, upgrade/regression gates, or whenever "the numbers match" is about to license a claim.

pedrohcgs · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add pedrohcgs/claude-code-my-workflow --skill differential-audit

技能说明


name: differential-audit description: Compare two implementations of the same thing — a port (R↔Python↔Stata), a reimplementation, a replication package, a refactor, or a new version against the old — so that agreement means something. Freeze inputs first, inventory every expected output, test the comparator itself, compare every channel (not just the headline number), and give each divergence a stable ID and a smallest witness. Use for cross-language parity, replication, upgrade/regression gates, or whenever "the numbers match" is about to license a claim.

differential-audit

This skill's instructions live in .claude/skills/differential-audit/SKILL.md. Read that file now and follow it, with the files it points to. Read AGENTS.md first if you have not already.

It was written for Claude Code. Running it from Codex, Antigravity or another agent:

  • Arguments. Where it says $ARGUMENTS, use what the user asked for.
  • Claude Code agents. Where a step hands work to an agent in .claude/agents/ (through the Agent or Task tool), do that step where it appears in the procedure: never later, and never skip it. A step that gates what follows still gates it (/commit runs its verifier before it commits). Read the agent's file for what the step checks.
  • Fresh context. If the step needs a context that has not seen your work, for example a claim verifier that must never see the draft, run it in a separate session or worker that has not seen the draft, if your tool can start one, and give it only what the step says to pass. If it cannot, do the step yourself, mark every result it produced not independently verified, and tell the user to repeat that check in Claude Code (/verify-claims for citations) before relying on it.
  • Claude Code settings. allowed-tools, model, effort, argument-hint and disable-model-invocation in the source's frontmatter configure Claude Code. Ignore them.
  • Guards. Claude Code's guard hooks do not run for you. Follow the rules in AGENTS.md yourself; the git pre-commit gate and CI still apply to your commits.