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 follows the Node.js commit message style: correct subsystem-prefixed format, validation using core-validate-commit, and strict prohibition on AI co-authorship lines.",
"type": "weighted_checklist",
"checklist": [
{
"name": "subsystem prefix format",
"description": "Every commit message in commit-messages.txt uses the format `subsystem: short imperative description` (e.g., `fs: fix race in readdir`) — the subsystem is a known Node.js module name followed by a colon and space",
"max_score": 15
},
{
"name": "Imperative description",
"description": "Each commit message subject line uses an imperative verb (e.g., 'fix', 'add', 'update', 'remove') rather than past tense or gerund ('fixed', 'fixing')",
"max_score": 10
},
{
"name": "Fixes: footer with full URL",
"description": "At least one commit message contains a `Fixes:` footer with a full GitHub issue URL (e.g., `Fixes: https://github.com/nodejs/node/issues/NNNNN`), not just an issue number",
"max_score": 12
},
{
"name": "core-validate-commit used",
"description": "The validation-output.txt file exists and contains output from running core-validate-commit (the tool name or its output appears in the file)",
"max_score": 15
},
{
"name": "Validation passes",
"description": "The validation-output.txt does NOT contain a failure or error message for any of the commit messages (i.e., the commit messages pass core-validate-commit validation)",
"max_score": 15
},
{
"name": "No AI co-authorship lines",
"description": "commit-messages.txt does NOT contain any of: 'Co-Authored-By: Claude', 'Co-Authored-By: Codex', 'Generated by ChatGPT', or any Signed-off-by line claiming an AI agent as author",
"max_score": 20
},
{
"name": "No trailing AI attribution",
"description": "commit-messages.txt does NOT contain lines like 'Co-Authored-By: Claude Sonnet', '🤖 Generated with', or similar AI tool footers",
"max_score": 13
}
]
}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