@mutagent/evaluator 0.1.0-alpha.6 → 0.2.0-alpha.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.claude/skills/mutagent-evaluator/SKILL.md +23 -25
- package/.claude/skills/mutagent-evaluator/assets/agents/dataset-builder.md +6 -5
- package/.claude/skills/mutagent-evaluator/assets/agents/evaluator.md +77 -14
- package/.claude/skills/mutagent-evaluator/assets/templates/discover-report.template.html +397 -0
- package/.claude/skills/mutagent-evaluator/assets/templates/eval-report.template.html +594 -0
- package/.claude/skills/mutagent-evaluator/assets/templates/review-report.template.html +560 -0
- package/.claude/skills/mutagent-evaluator/golden/judge-trajectory.prose.md +69 -0
- package/.claude/skills/mutagent-evaluator/references/data-registry.md +43 -0
- package/.claude/skills/mutagent-evaluator/references/eval-layers.md +52 -0
- package/.claude/skills/mutagent-evaluator/references/eval-stage.md +1 -1
- package/.claude/skills/mutagent-evaluator/scripts/aggregate-discover.ts +254 -9
- package/.claude/skills/mutagent-evaluator/scripts/audience.ts +84 -0
- package/.claude/skills/mutagent-evaluator/scripts/code-eval-library.ts +201 -0
- package/.claude/skills/mutagent-evaluator/scripts/contracts/agentspec-evals.ts +101 -39
- package/.claude/skills/mutagent-evaluator/scripts/contracts/eval-matrix.ts +287 -3
- package/.claude/skills/mutagent-evaluator/scripts/contracts/eval-types.ts +30 -4
- package/.claude/skills/mutagent-evaluator/scripts/materialize-dataset.ts +130 -68
- package/.claude/skills/mutagent-evaluator/scripts/matrix-judge.ts +219 -1
- package/.claude/skills/mutagent-evaluator/scripts/merge-criteria.ts +849 -0
- package/.claude/skills/mutagent-evaluator/scripts/render-discover-report-v3.ts +1155 -0
- package/.claude/skills/mutagent-evaluator/scripts/render-eval-report-v3.ts +610 -0
- package/.claude/skills/mutagent-evaluator/scripts/render-eval-report.ts +2 -1
- package/.claude/skills/mutagent-evaluator/scripts/render-review-report-v3.ts +691 -0
- package/.claude/skills/mutagent-evaluator/scripts/route-failures.ts +10 -7
- package/.claude/skills/mutagent-evaluator/scripts/run-evaluate.ts +46 -1
- package/.claude/skills/mutagent-evaluator/scripts/run-review.ts +266 -0
- package/.claude/skills/mutagent-evaluator/scripts/verify-render.ts +728 -0
- package/package.json +2 -2
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@mutagent/evaluator",
|
|
3
|
-
"version": "0.
|
|
4
|
-
"description": "mutagent-evaluator: a generic, subject-agnostic AI-agent auditor
|
|
3
|
+
"version": "0.2.0-alpha.1",
|
|
4
|
+
"description": "mutagent-evaluator: a generic, subject-agnostic AI-agent auditor \u2014 reviewer, never executor. Audits any skill/agent against a generated subject profile and emits a 4-tab master-audit report.",
|
|
5
5
|
"license": "Apache-2.0",
|
|
6
6
|
"type": "module",
|
|
7
7
|
"publishConfig": {
|