Auto-generated tile from GitHub (10 skills)
92
94%
Does it follow best practices?
Impact
92%
1.16xAverage score across 44 eval scenarios
Advisory
Suggest reviewing before use
{
"context": "Tests whether the agent formats commit messages according to Node.js core conventions, uses core-validate-commit to validate them, and avoids adding any AI or agent attribution footers.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Subsystem prefix",
"description": "Every commit message in commit-messages.txt begins with a known Node.js subsystem prefix followed by a colon and space (e.g., 'stream:', 'fs:', 'crypto:', 'test:', 'doc:', 'build:', 'http:')",
"max_score": 15
},
{
"name": "Imperative subject line",
"description": "Each commit subject line uses an imperative verb as the first word after the subsystem prefix (e.g., 'fix', 'add', 'update', 'remove', 'implement') — not past tense ('fixed', 'added') or gerund ('fixing', 'adding')",
"max_score": 10
},
{
"name": "No AI co-authorship",
"description": "commit-messages.txt does NOT contain any of: 'Co-Authored-By: Claude', 'Co-Authored-By: Codex', 'Generated by ChatGPT', 'Signed-off-by:' attributed to an AI or agent, or any similar AI attribution footer",
"max_score": 20
},
{
"name": "core-validate-commit used",
"description": "validation-results.txt exists and contains output from running 'core-validate-commit' (or 'npx core-validate-commit') against the commit messages — the tool name or its output format is visible",
"max_score": 20
},
{
"name": "Validation passed",
"description": "The validation output in validation-results.txt shows that at least one commit message passed core-validate-commit validation without errors",
"max_score": 15
},
{
"name": "Fixes/Refs footer format",
"description": "At least one commit message includes a 'Fixes:' or 'Refs:' footer with a URL (e.g., 'Fixes: https://github.com/nodejs/node/issues/NNNNN')",
"max_score": 10
},
{
"name": "No generic signatures",
"description": "commit-messages.txt does NOT contain 'Signed-off-by:', 'Generated by', or any footer line claiming automated or AI authorship",
"max_score": 10
}
]
}evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17
scenario-18
scenario-19
scenario-20
scenario-21
scenario-22
scenario-23
scenario-24
scenario-25
scenario-26
scenario-27
scenario-28
scenario-29
scenario-30
scenario-31
scenario-32
scenario-33
scenario-34
scenario-35
scenario-36
scenario-37
scenario-38
scenario-39
scenario-40
scenario-41
scenario-42
scenario-43
scenario-44
skills
documentation
fastify
init
linting-neostandard-eslint9
node
nodejs-core
rules
oauth
octocat
snipgrapher