Setting the file. One moment.
Subchapter 23.42
evals/scenarios/reference-backed-integration.json
JSON58 lines2 KB
{
"name": "Reference-backed integration",
"prompt": "Create a skill named sentry-event-search for helping agents write correct Sentry event-search queries. It should use the supplied repository conventions, keep SKILL.md as a router, and place query syntax, examples, and edge cases in focused references. Include a lightweight validation result before finishing.",
"judge": [
{
"check": "The agent created and registered skills/sentry-event-search with SKILL.md, SPEC.md, and focused routed reference files.",
"weight": 0.25
},
{
"check": "SKILL.md is a compact router with direct open-when reasons for references; it does not hide required instructions in optional references.",
"weight": 0.25
},
{
"check": "The references are scoped by lookup need, such as syntax, examples, and edge cases, rather than one catch-all document.",
"weight": 0.2
},
{
"check": "The generated skill is honest about source gaps and does not invent unsupported Sentry query behavior.",
"weight": 0.2
},
{
"check": "The transcript or final response shows structural validation was run.",
"weight": 0.1
}
],
"setup": [
{
"action": "run_script",
"command": "rsync -a --exclude .git --exclude .axis --exclude .codex --exclude .agents \"$AXIS_CONFIG_DIR/../../..\"/ ."
},
{
"action": "run_script",
"command": "git init"
},
{
"action": "run_script",
"command": "git config user.email skill-writer-eval@example.invalid"
},
{
"action": "run_script",
"command": "git config user.name 'Skill Writer Eval'"
},
{
"action": "run_script",
"command": "git add ."
},
{
"action": "run_script",
"command": "git commit -m baseline"
}
],
"artifacts": [
"skills/sentry-event-search/**",
"README.md",
".claude/settings.json",
"skills/claude-settings-audit/SKILL.md"
]
}