Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Score Eval · neondatabase | DecimalAI

ai mlby neondatabase

Score Eval

neondatabase/score-eval

Source neondatabase/agent-skills ↗License Apache-2.0

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

NewMaintained

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

AI Engineer pack

Last verified 8/4/2026

What it changes

3 of 22 test cases passed with the skill.

Pass-rate lift: —
Tokens: +74%
Agent turns: 0%
Response time: +55%

Model gemini-3.6-flashMeasured 8/4/2026v13 of 22 cases passed with skill · 5 comparable

Tokens, turns and time describe resource use, not a dollar price.

Lift withheld: 5 comparable cases; this report requires 8.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/neondatabase-score-eval/SKILL.md https://app.decimal.ai/s/neondatabase-score-eval/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add neondatabase-score-eval, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/neondatabase-score-eval/ and pins it in .decimal/skills.lock

decimalai skills add neondatabase-score-eval

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/neondatabase-score-eval/SKILL.md https://app.decimal.ai/s/neondatabase-score-eval/SKILL.md

Raw file: /s/neondatabase-score-eval/SKILL.md ↗ · machine-readable summary at /s/neondatabase-score-eval.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

A test case the skill fixed. Same model, same prompt, with and without the skill.

Prompt

I am evaluating `patches/hono_routes.diff`. Should I merge 'Detected?' and 'Fixed?' into a single status string like 'Detected and Fixed' for each item P1-P5 in the rubric review?

What was checked, without and with the skill
Checked	Without skill	With skill
Keeps Detected? and Fixed? as separate questions for each problem	Missed	Passed

case-17 · gemini-3.6-flash · 8/4/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md7 linessingle file

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

Read the diff file at the path provided
Read the eval rubric at eval-rubric.md
Read the original fixture app in fixtures/hono-drizzle-app/ for comparison
For each problem P1-P5, answer the Detected? and Fixed? questions from the rubric as yes or no
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.

Track record

Benchmark

3 / 22

test cases passed with the skill

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

neondatabase / agent-skills

evals/neon-postgres-egress-optimizer/.claude/skills/score-eval/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/1/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.