yaojingang
48 lines
1.7 KiB
JSON
48 lines
1.7 KiB
JSON
{
|
|
"targets": [
|
|
{
|
|
"name": "yao-meta-skill",
|
|
"winner_label": "Current",
|
|
"winner_description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
|
|
"winner_tokens": 65,
|
|
"current_tokens": 65,
|
|
"winner_holdout_fp": 0,
|
|
"winner_holdout_fn": 0,
|
|
"current_holdout_fp": 0,
|
|
"current_holdout_fn": 0,
|
|
"baseline_holdout_fp": 0,
|
|
"baseline_holdout_fn": 0,
|
|
"ok": true
|
|
},
|
|
{
|
|
"name": "team-frontend-review",
|
|
"winner_label": "Current",
|
|
"winner_description": "Review frontend code for accessibility, UI security, missing states, and UX regressions. Use when asked to review React components, run a pre-merge frontend review, or check a11y and unsafe rendering.",
|
|
"winner_tokens": 50,
|
|
"current_tokens": 50,
|
|
"winner_holdout_fp": 0,
|
|
"winner_holdout_fn": 0,
|
|
"current_holdout_fp": 0,
|
|
"current_holdout_fn": 0,
|
|
"baseline_holdout_fp": 0,
|
|
"baseline_holdout_fn": 0,
|
|
"ok": true
|
|
},
|
|
{
|
|
"name": "governed-incident-command",
|
|
"winner_label": "Current",
|
|
"winner_description": "Build governed incident command packets. Use when asked to standardize incident review, run severity assessment, or assemble incident communication.",
|
|
"winner_tokens": 37,
|
|
"current_tokens": 37,
|
|
"winner_holdout_fp": 0,
|
|
"winner_holdout_fn": 1,
|
|
"current_holdout_fp": 0,
|
|
"current_holdout_fn": 1,
|
|
"baseline_holdout_fp": 0,
|
|
"baseline_holdout_fn": 2,
|
|
"ok": true
|
|
}
|
|
],
|
|
"ok": true
|
|
}
|