score-eval

This skill evaluates code changes against a predefined rubric by analyzing diffs and comparing them to an original fixture application.

by NeonOfficial publisherNot reviewed

Identity proven by GitHub's verified organisation badge (neondatabase)

Agents: Claude Code
License: Apache-2.0 (permissive)
Pin: bfd013cpinned Oct 9, 2026
Context cost: about 120 tokenswhen the skill loads
GitHub stars: 100on neondatabase/agent-skills
Scripts: None found

What it does

Generated summary from the skill's own text

This skill evaluates code changes against a predefined rubric by analyzing diffs and comparing them to an original fixture application. It determines whether specific problems were detected and fixed, then records the assessment results in a CSV file.

When to use it

Assessing code changes against a known problem checklist
Tracking whether specific issues were fixed in pull requests
Automated evaluation of code modifications against criteria
Comparing new code against baseline fixture applications

When not to

General code review or quality assessment without a rubric
Evaluating applications without a reference fixture for comparison
Real-time code quality monitoring across multiple projects

Review

Not reviewed by a person yet. The trust card below shows what our automated checks found at the pinned commit.

Trust card

What our automated checks found

At commit bfd013c352ed31b57a573e4f60263afc5fdd7f7a, checked Oct 8, 2026.

License: Apache-2.0 (permissive), from LICENSE
Scripts: None found
Network domains: None found
allowed-tools: None requested
Unpinned packages: None found
Spec issues: description is missing
Frontmatter keys outside the spec: disable-model-invocation
Files: 1 file, 517 B in totalLargest: SKILL.md (517 B)
Context cost: Description: 0 characters, in context whenever the agent runs.Body: about 120 tokens, in context when the skill loads.
Warnings: Does not follow the SKILL.md specdescription is missing

Automated checks look for known patterns and can be bypassed. They decide what a reviewer reads first. This is not a guarantee.

Pins

Pin history

bfd013cOct 9, 2026Current

Install

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add neondatabase/agent-skills --skill score-eval

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install neondatabase/agent-skills score-eval@bfd013c352ed31b57a573e4f60263afc5fdd7f7a

Installs the commit we checked (bfd013c).

Copy by hand

Download the folder at bfd013c and put it in .claude/skills/score-eval for Claude Code and in .agents/skills/score-eval for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at bfd013c

Claude Code plugin

/plugin install neon@claude-plugins-official

The publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "score-eval" by Neon.

Source, pinned to commit bfd013c352ed31b57a573e4f60263afc5fdd7f7a:
https://github.com/neondatabase/agent-skills/tree/bfd013c352ed31b57a573e4f60263afc5fdd7f7a/evals/neon-postgres-egress-optimizer/.claude/skills/score-eval

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/score-eval/ for Claude Code and .agents/skills/score-eval/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Listing and checks: https://www.agentnative.dev/skills/neon/score-eval

SKILL.md at the pin

---
name: score-eval
disable-model-invocation: true
---

Score the eval diff at $ARGUMENTS against the eval rubric.

1. Read the diff file at the path provided
2. Read the eval rubric at eval-rubric.md
3. Read the original fixture app in fixtures/hono-drizzle-app/ for comparison
4. For each problem P1-P5, answer the Detected? and Fixed? questions from the rubric as yes or no
5. Append a row to results.csv — fill in all fields you can determine from the diff and context. Leave fields you can't determine empty.

From neondatabase/agent-skills at bfd013c, shown as plain text under its license: Apache-2.0 (permissive). The license text is in LICENSE.

View SKILL.md on GitHub at bfd013c

Files

SKILL.md517 B · c4a89dff2db3

1 file, 517 B in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at bfd013c

All 19 skills from Neon

score-eval

What it does

When to use it

When not to

Install

Copy for your agent

SKILL.md at the pin

Files

More from Neon

neon

neon-ai-gateway

neon-auth

neon-functions

neon-object-storage

neon-postgres

agent-builder

intent-recognition

planned-task-runtime

skill-creator

-21risk-automation

-2chat-automation

What it does

When to use it

When not to

Install

Copy for your agent

SKILL.md at the pin

Files

More from Neon

Related in AI and agents