Skip to content
Agentmart
Submit a tool

eval-review

Review an Inspect-based eval suite for the pi harness along independent criteria: contract validity (does it measure what it claims), outcome vs path grading…

Skill by Y4shin

IndexedLicense unknown
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/y4shin-eval-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Review an Inspect-based eval suite for the pi harness along independent criteria: contract validity (does it measure what it claims), outcome vs path grading, isolation and baseline-vs-treatment soundness, and scorer integrity. Use when asked to review or audit an eval suite, check whether an eval measures the capability it claims, sanity-check scorers, isolation, or the baseline-vs-treatment setup, or triage a failed or flaky eval run (scorer bug vs skill defect vs spec mismatch). Suite reviews spawn parallel read-only sub-agents; nothing is edited during a review. Do NOT use for authoring, scaffolding, improving, or tuning an eval suite, reviewing code changes (use code-review), or reviewing Agent Skills (use skill-review).

Use cases: documents, security, agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/eval-review

What's inside

Skill name
eval-review
Description
Review an Inspect-based eval suite for the pi harness along independent criteria: contract validity (does it measure what it claims), outcome vs path grading, isolation and baseline-vs-treatment soundness, and scorer integrity. Use when asked to review or audit an eval suite, check whether an eval measures the capability it claims, sanity-check scorers, isolation, or the baseline-vs-treatment setup, or triage a failed or flaky eval run (scorer bug vs skill defect vs spec mismatch). Suite reviews spawn parallel read-only sub-agents; nothing is edited during a review. Do NOT use for authoring, scaffolding, improving, or tuning an eval suite, reviewing code changes (use code-review), or reviewing Agent Skills (use skill-review).
License
unknown
Instructions
170 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • isolation-checklist.md · references/

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from Y4shin/skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 15, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
License unknown
Repository
github.com/Y4shin/skills
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from Y4shin

Cite this page

eval-review skill. Agent Mart. https://agentmart.dev/skills/y4shin-eval-review (last updated 2026-10-24)