mirror of
https://github.com/addyosmani/agent-skills.git
synced 2026-08-12 18:07:26 +02:00
Addy Osmani
194b2099c6
Per review from @federicobartoli and @nucliweb on #342: Tier 3 (behavioral): - Grade the execution trace, not the final output: executor runs with --output-format stream-json --verbose so the grader judges tool calls and file edits rather than the model's self-reporting. - Run each eval in a throwaway workspace; files[] fixtures materialize from evals/fixtures/ so evals can operate on real code. - Node-level timeouts on executor and grader calls; grader output parsed and shape-validated before writing (raw saved on failure); the trace is fenced as untrusted data in the grader prompt. - All 24 behavioral evals flagged trust_level: "provisional" until they gain fixtures; the runner surfaces this and exits nonzero on failed expectations. Tier 2 (deterministic): - Negative triggers accept an "owner" skill that must outrank this one, turning them into pairwise routing tests that cannot pass vacuously; 37 of 48 negatives now declare owners (the rest are tracked in #351). - Warn when a case file is below the documented minimums (3 positive / 2 negative / 1 behavioral); promotion to error tracked in #352. - Stemmer: cluster trailing y/i ("simplify"/"simplifies"). Baseline holds: 120 checks, 0 errors, 85% trigger rank-1 rate.
43 lines
1.2 KiB
JSON
43 lines
1.2 KiB
JSON
{
|
|
"skill_name": "source-driven-development",
|
|
"trigger": {
|
|
"positive": [
|
|
{
|
|
"prompt": "Verify against the official Next.js docs before implementing this",
|
|
"top_k": 3
|
|
},
|
|
{
|
|
"prompt": "I want source-cited code for the new Stripe integration",
|
|
"top_k": 3
|
|
},
|
|
{
|
|
"prompt": "Ground every framework decision in the official documentation",
|
|
"top_k": 3
|
|
}
|
|
],
|
|
"negative": [
|
|
{
|
|
"prompt": "Fix the flaky test in CI",
|
|
"owner": "ci-cd-and-automation"
|
|
},
|
|
{
|
|
"prompt": "Break the spec into ordered tasks",
|
|
"owner": "planning-and-task-breakdown"
|
|
}
|
|
]
|
|
},
|
|
"evals": [
|
|
{
|
|
"id": 1,
|
|
"prompt": "Implement session handling with the framework's recommended approach, citing sources.",
|
|
"expected_output": "An implementation grounded in official documentation with citations, flagging anything unverified",
|
|
"expectations": [
|
|
"Claims about framework behavior cite official documentation",
|
|
"Unverified assumptions are flagged rather than presented as fact",
|
|
"Deprecated patterns are avoided in favor of documented current ones"
|
|
],
|
|
"trust_level": "provisional"
|
|
}
|
|
]
|
|
}
|