{"cases":[{"case_id":"load-evidence-review","expected_skills":[{"name":"evidence-review","status":"matched"}],"gate":"incomplete","goal":"Load the authored evidence-review skill through MCP.","has_rejection":false,"results":[{"accepted":null,"error":null,"evaluator":"goal-review","explanation":"No result for this declared target.","label":null,"revision":"not-run","span_id":null,"status":"missing","trace_id":null,"value":null},{"accepted":null,"error":null,"evaluator":"Builtin.SkillInstructionFollowing","explanation":"No result for this declared target.","label":null,"revision":"not-run","span_id":"481d88f854ae4e7c","status":"missing","trace_id":"7419e7e182a245919fc3c49b1c02b7a7","value":null}],"session_id":"bbc3c08e-7dc7-434a-9c65-8d745bcc8547","skill_calls":[{"identity":"matched","name":"evidence-review","receipt":{"bundle_sha256":"f93102cb0592a462afb43cc6cf78b09096208aa1772bcaa341e75a20c1deffd0","content_sha256":"473876db0cd9579138f1cd7905f6037855bea94c4c3740eb2c7f698aef2ddc0b","declared_tools":["Read"],"load_id":"dff92916-a748-4b3b-aca9-293d0043c6c1","loaded_at":"2026-09-15T16:44:48.892Z","name":"evidence-review","permissions_enforced":false,"provider":"dsh-skills-anywhere","provider_version":"0.12.0","schema":"skills-anywhere-load-1","skill_sha256":"8e08d5d07d0b7f9683145ef435653e4cfe1d8a312d1255ed79a6d0241e5c7542"},"span_id":"481d88f854ae4e7c","trace_id":"7419e7e182a245919fc3c49b1c02b7a7"}],"skill_observation_complete":true,"span_count":1,"trace_ids":["7419e7e182a245919fc3c49b1c02b7a7"]}],"configuration":{"model":"none: local MCP client","model_parameters":{},"prompt_sha256":"e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855","skills":{"evidence-review":"f93102cb0592a462afb43cc6cf78b09096208aa1772bcaa341e75a20c1deffd0"},"tools_sha256":"2c52bc1da3c4285bb25979f13097557ea48d74d978902a278c9d869ab5ff7aa9"},"dataset":{"cases":[{"expected_skills":["evidence-review"],"goal":"Load the authored evidence-review skill through MCP.","id":"load-evidence-review"}],"id":"mcp-delivery-control","version":"1"},"dataset_sha256":"0f45fb24d56ea9e4ccd4834d4aa414cd0db5a45b5b10a833c1f5fc7c126c3cc4","evaluators":[{"id":"goal-review","level":"session","rating":{"kind":"numeric","max":1,"min":0,"pass_at_least":1},"revision":"not-run"},{"id":"Builtin.SkillInstructionFollowing","level":"skill","rating":{"kind":"numeric","max":1,"min":0,"pass_at_least":1},"revision":"not-run"}],"provenance":{"description":"Actual local stdio MCP instruction delivery, collected by scripts/record-load.mjs using an authored skill. No model or AWS evaluation; evaluator results intentionally absent.","kind":"recorded"},"run_id":"mcp-delivery-bbc3c08e-7dc7-434a-9c65-8d745bcc8547","schema_version":"evalarc.trace-review.v1","scope":"Imported evaluator judgments and caller-declared trace coverage. Identity and consistency checks do not authenticate the producer, rerun a judge, enforce permissions or independently verify task completion.","source_bytes":3206,"source_sha256":"0c804eaa82da0a065ada91de792edc89de712b056103ef4fa37d0034bbb02662","summary":{"accepted":0,"incomplete":1,"rejected":0}}
