zy839971925-zyy/Agent--deep-research-Workflow-Skills / skills/reasoning-workflow
reasoning-workflow
VerifiedDefault silent workflow for everyday questions, research, writing, design and engineering. Match effort to the request, resolve costly ambiguity, find specialist resources and verify the requested outcome. Explicitly selectable with “调用我的 workflow skills”.
tests/results/cli_receipts_2_1_1.json
View on GitHub[
{
"test": "run_regression.Regression.test_02_route_cli_and_cwd",
"argv": [
"python",
"<skill-root>/scripts/route_task.py",
"<temporary-test-directory>/input0.json",
"--signal",
"ultra_requested"
],
"cwd": "temporary directory outside Skill",
"exit": 0,
"stdout": "{\n \"passed\": true,\n \"task_profile\": {\n \"profile_version\": 2,\n \"lane\": \"question\",\n \"depth_class\": \"ultra\",\n \"autonomy_class\": \"A\",\n \"reasoning_breadth\": \"standard\",\n \"evidence_depth\": \"standard\",\n \"challenge_depth\": \"standard\",\n \"verification_depth\": \"standard\",\n \"governance_depth\": \"minimal\",\n \"routing_confidence\": \"high\",\n \"task_modes\": [\n \"research\"\n ],\n \"task_coupling\": \"low\",\n \"persistence\": \"none\",\n \"external_side_effects\": \"none\",\n \"requested_depth\": \"ultra\",\n \"parent_profile_version\": 1,\n \"update_reason\": \"ultra_requested\"\n },\n \"route\": {\n \"profile_fingerprint\": \"sha256:6f7d136c32ac421fa0b700785b0285820a2edda98f1ba0d271b2817509669963\",\n \"index_fingerprint\": \"sha256:6c3dc9a1c98b732fa286593f0ec03e43b574491c730a7038a0723b50b74db954\",\n \"profile_version\": 2,\n \"required_reference_ids\": [\n \"ultra-research\"\n ],\n \"required_families\": [\n \"core-reasoning\",\n \"deep-research\",\n \"audit-verification\"\n ],\n \"optional_families\": [],\n \"verification_mode\": \"dual\",\n \"runtime_level\": \"none\",\n \"swarm_admission\": \"preferred\",\n \"reference_phase_limit\": 4,\n \"progressive_loading\": true,\n \"route_status\": \"current\"\n }\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_05_strict_raw_envelope",
"argv": [
"python",
"<skill-root>/scripts/validate_raw.py",
"<temporary-test-directory>/input0.json",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"RAW_INPUT\",\n \"message\": \"RAW_ENVELOPE: expected array or exactly {records: array}; explicit [] is valid\",\n \"refs\": []\n }\n ]\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_05_strict_raw_envelope",
"argv": [
"python",
"<skill-root>/scripts/validate_raw.py",
"<temporary-test-directory>/input0.json",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"RAW_INPUT\",\n \"message\": \"RAW_ENVELOPE: expected array or exactly {records: array}; explicit [] is valid\",\n \"refs\": []\n }\n ]\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_05_strict_raw_envelope",
"argv": [
"python",
"<skill-root>/scripts/validate_raw.py",
"<temporary-test-directory>/input0.json",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 0,
"stdout": "{\n \"findings\": []\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_06_raw_hash_and_lineage_schema",
"argv": [
"python",
"<skill-root>/scripts/validate_raw.py",
"<temporary-test-directory>/input0.json",
"--root",
"<temporary-test-directory>",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 0,
"stdout": "{\n \"findings\": []\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_06_raw_hash_and_lineage_schema",
"argv": [
"python",
"<skill-root>/scripts/validate_raw.py",
"<temporary-test-directory>/input0.json",
"--root",
"<temporary-test-directory>",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"hash_algorithm: None is not one of ['sha256', 'sha512']\",\n \"refs\": []\n }\n ]\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_06_raw_hash_and_lineage_schema",
"argv": [
"python",
"<skill-root>/scripts/validate_raw.py",
"<temporary-test-directory>/input0.json",
"--root",
"<temporary-test-directory>",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"RAW_HASH_MISMATCH\",\n \"message\": \"R1 sha256 mismatch\",\n \"refs\": [\n \"R1\"\n ]\n }\n ]\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_06_raw_hash_and_lineage_schema",
"argv": [
"python",
"<skill-root>/scripts/validate_raw.py",
"<temporary-test-directory>/input0.json",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'derived_from' is a required property\",\n \"refs\": []\n }\n ]\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_06_raw_hash_and_lineage_schema",
"argv": [
"python",
"<skill-root>/scripts/validate_raw.py",
"<temporary-test-directory>/input0.json",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"derived_from: [] should be non-empty\",\n \"refs\": []\n }\n ]\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_06_raw_hash_and_lineage_schema",
"argv": [
"python",
"<skill-root>/scripts/validate_raw.py",
"<temporary-test-directory>/input0.json",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 0,
"stdout": "{\n \"findings\": []\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_07_runtime_explicit_empty",
"argv": [
"python",
"<skill-root>/scripts/validate_runtime.py",
"--plan",
"<temporary-test-directory>/plan.json",
"--ledger",
"<temporary-test-directory>/empty.json",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'schema_version' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'plan_id' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'plan_version' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'state_version' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'nodes' is a required property\",\n \"refs\": []\n }\n ]\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_07_runtime_explicit_empty",
"argv": [
"python",
"<skill-root>/scripts/validate_runtime.py",
"--plan",
"<temporary-test-directory>/plan.json",
"--schedule",
"<temporary-test-directory>/empty.json",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'schema_version' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'schedule_id' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'schedule_version' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'plan_id' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'based_on_plan_version' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'mode' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'scope' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'assignments' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'completed_prerequisite_refs' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'deferred_nodes' is a required property\",\n \"refs\": []\n }\n ]\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_08_schedule_legal_and_cycles",
"argv": [
"python",
"<skill-root>/scripts/validate_runtime.py",
"--plan",
"<temporary-test-directory>/plan.json",
"--schedule",
"<temporary-test-directory>/sch.json",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 0,
"stdout": "{\n \"findings\": []\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_08_schedule_legal_and_cycles",
"argv": [
"python",
"<skill-root>/scripts/validate_runtime.py",
"--plan",
"<temporary-test-directory>/plan.json",
"--schedule",
"<temporary-test-directory>/sch.json",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEDULE_WAIT_CYCLE\",\n \"message\": \"combined dependency/wait cycle: A -> A\",\n \"refs\": [\n \"A\",\n \"A\"\n ]\n }\n ]\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_08_schedule_legal_and_cycles",
"argv": [
"python",
"<skill-root>/scripts/validate_runtime.py",
"--plan",
"<temporary-test-directory>/plan.json",
"--schedule",
"<temporary-test-directory>/sch.json",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEDULE_WAIT_CYCLE\",\n \"message\": \"combined dependency/wait cycle: A -> B -> A\",\n \"refs\": [\n \"A\",\n \"B\",\n \"A\"\n ]\n }\n ]\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_08_schedule_legal_and_cycles",
"argv": [
"python",
"<skill-root>/scripts/validate_runtime.py",
"--plan",
"<temporary-test-directory>/plan.json",
"--schedule",
"<temporary-test-directory>/sch.json",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEDULE_WAIT_CYCLE\",\n \"message\": \"combined dependency/wait cycle: A -> B -> A\",\n \"refs\": [\n \"A\",\n \"B\",\n \"A\"\n ]\n }\n ]\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_08_schedule_legal_and_cycles",
"argv": [
"python",
"<skill-root>/scripts/validate_runtime.py",
"--plan",
"<temporary-test-directory>/plan.json",
"--schedule",
"<temporary-test-directory>/sch.json",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEDULE_WAIT_CYCLE\",\n \"message\": \"combined dependency/wait cycle: A -> B -> A\",\n \"refs\": [\n \"A\",\n \"B\",\n \"A\"\n ]\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEDULE_WAIT_CYCLE\",\n \"message\": \"combined dependency/wait cycle: A -> B -> A\",\n \"refs\": [\n \"A\",\n \"B\",\n \"A\"\n ]\n }\n ]\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_17_review_valid_is_not_passed",
"argv": [
"python",
"<skill-root>/scripts/validate_dual_verification.py",
"<temporary-test-directory>/input0.json"
],
"cwd": "temporary directory outside Skill",
"exit": 0,
"stdout": "{\n \"passed\": true,\n \"record_valid\": true,\n \"verification_passed\": false,\n \"findings\": []\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_18_learning_intrinsic_rejected",
"argv": [
"python",
"<skill-root>/scripts/validate_learning.py",
"<temporary-test-directory>/input0.json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"passed\": false,\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"INTRINSIC_REFLECTION_NOT_VALIDATION\",\n \"message\": \"same-model intrinsic reflection may create candidate insight only\"\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"VALIDATION_EVIDENCE_REQUIRED\",\n \"message\": \"validated/promoted requires resolvable validation evidence references; host resolves them\"\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"LEARNING_VALIDATION_UNVERIFIED\",\n \"message\": \"validated credit requires trusted validation evidence resolver; record labels alone are insufficient\"\n }\n ]\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_18_learning_intrinsic_rejected",
"argv": [
"python",
"<skill-root>/scripts/retrieve_learnings.py",
"<temporary-test-directory>/input0.json",
"--task-tag",
"deep_research"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"passed\": false,\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"INTRINSIC_REFLECTION_NOT_VALIDATION\",\n \"message\": \"same-model intrinsic reflection may create candidate insight only\"\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"VALIDATION_EVIDENCE_REQUIRED\",\n \"message\": \"validated/promoted requires resolvable validation evidence references; host resolves them\"\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"LEARNING_VALIDATION_UNVERIFIED\",\n \"message\": \"validated credit requires trusted validation evidence resolver; record labels alone are insufficient\"\n }\n ],\n \"advisory_only\": false,\n \"selected\": []\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_19_learning_tiers_and_evidence",
"argv": [
"python",
"<skill-root>/scripts/validate_learning.py",
"<temporary-test-directory>/input0.json",
"--validation-evidence",
"<temporary-test-directory>/evidence_index.json"
],
"cwd": "temporary directory outside Skill",
"exit": 0,
"stdout": "{\n \"passed\": true,\n \"findings\": []\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_19_learning_tiers_and_evidence",
"argv": [
"python",
"<skill-root>/scripts/retrieve_learnings.py",
"<temporary-test-directory>/input0.json",
"--task-tag",
"deep_research",
"--validation-evidence",
"<temporary-test-directory>/evidence_index.json"
],
"cwd": "temporary directory outside Skill",
"exit": 0,
"stdout": "{\n \"passed\": true,\n \"findings\": [],\n \"advisory_only\": false,\n \"selected\": []\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_20_learning_malformed",
"argv": [
"python",
"<skill-root>/scripts/retrieve_learnings.py",
"<temporary-test-directory>/input0.json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"passed\": false,\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"LEARNING_INPUT\",\n \"message\": \"expected array or exactly {learnings: array}\"\n }\n ],\n \"advisory_only\": false,\n \"selected\": []\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_20_learning_malformed",
"argv": [
"python",
"<skill-root>/scripts/retrieve_learnings.py",
"<temporary-test-directory>/input0.json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"passed\": false,\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'tier' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'source_run_refs' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'source_eval_refs' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'task_signature' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'failure_mode' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'root_cause_class' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'lesson_type' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'heuristic' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'applicability_conditions' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'anti_conditions' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'provenance' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'created_at' is a required property\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"SCHEMA\",\n \"message\": \"$: 'rollback_ref' is a required property\",\n \"refs\": []\n }\n ],\n \"advisory_only\": false,\n \"selected\": []\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_21_strict_bridge",
"argv": [
"python",
"<skill-root>/scripts/validate_workflow.py",
"--profile",
"<temporary-test-directory>/profile.json",
"--route",
"<temporary-test-directory>/route.json",
"--state",
"<temporary-test-directory>/state.json",
"--manifest",
"<temporary-test-directory>/manifest.json",
"--reviews",
"<temporary-test-directory>/reviews.json",
"--root",
"<temporary-test-directory>"
],
"cwd": "temporary directory outside Skill",
"exit": 0,
"stdout": "{\n \"passed\": true,\n \"structural_valid\": true,\n \"computed_delivery_ready\": true,\n \"evidence_authenticated\": false,\n \"orthogonality_verified\": null,\n \"errors\": [],\n \"host_execution_verified\": false\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_25_proposal_cli_no_host_bypass",
"argv": [
"python",
"<skill-root>/scripts/validate_runtime.py",
"--plan",
"<temporary-test-directory>/p.json",
"--worker-proposal",
"<temporary-test-directory>/q.json",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"WORKER_HOST_CONTEXT_REQUIRED\",\n \"message\": \"CLI is static validation only; live submission needs trusted host callback and atomic commit\",\n \"refs\": []\n }\n ]\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_26_resource_cli_other_cwd",
"argv": [
"python",
"<skill-root>/scripts/route_resources.py",
"<temporary-test-directory>/input0.json",
"<temporary-test-directory>/input1.json"
],
"cwd": "temporary directory outside Skill",
"exit": 0,
"stdout": "{\n \"passed\": true,\n \"selected_references\": [\n {\n \"reference_id\": \"problem-framing-and-effort\",\n \"family\": \"core-reasoning\",\n \"path\": \"references/problem-framing-and-effort.md\",\n \"load_reason\": \"family_entry\",\n \"current_gap\": \"family_entry\",\n \"profile_version\": 1,\n \"context_cost_class\": \"medium\"\n },\n {\n \"reference_id\": \"change-governance-and-effectiveness\",\n \"family\": \"audit-verification\",\n \"path\": \"references/change-governance-and-effectiveness.md\",\n \"load_reason\": \"gap_match\",\n \"current_gap\": \"high-consequence\",\n \"profile_version\": 1,\n \"context_cost_class\": \"medium\"\n }\n ]\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_32_manifest_flag_cannot_skip_digest",
"argv": [
"python",
"<skill-root>/scripts/validate_workflow.py",
"--profile",
"<temporary-test-directory>/profile.json",
"--route",
"<temporary-test-directory>/route.json",
"--state",
"<temporary-test-directory>/state.json",
"--manifest",
"<temporary-test-directory>/manifest.json",
"--reviews",
"<temporary-test-directory>/reviews.json",
"--root",
"<temporary-test-directory>"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"passed\": false,\n \"structural_valid\": false,\n \"computed_delivery_ready\": false,\n \"evidence_authenticated\": false,\n \"orthogonality_verified\": null,\n \"errors\": [\n \"ART_CURRENT_DOWNGRADE: art1 canonical current/required artifact cannot be downgraded by manifest flag\",\n \"DECLARED_READY_FALSE: declared_delivery_ready=true but computed_delivery_ready=false\",\n \"current/required artifact missing or downgraded art1\"\n ],\n \"host_execution_verified\": false\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_34_explicit_depth_api_cli_consistency",
"argv": [
"python",
"<skill-root>/scripts/route_task.py",
"<temporary-test-directory>/input0.json"
],
"cwd": "temporary directory outside Skill",
"exit": 0,
"stdout": "{\n \"passed\": true,\n \"task_profile\": {\n \"profile_version\": 2,\n \"lane\": \"question\",\n \"depth_class\": \"ultra\",\n \"autonomy_class\": \"A\",\n \"reasoning_breadth\": \"standard\",\n \"evidence_depth\": \"standard\",\n \"challenge_depth\": \"standard\",\n \"verification_depth\": \"standard\",\n \"governance_depth\": \"minimal\",\n \"routing_confidence\": \"high\",\n \"task_modes\": [\n \"research\"\n ],\n \"task_coupling\": \"low\",\n \"persistence\": \"none\",\n \"external_side_effects\": \"none\",\n \"requested_depth\": \"ultra\",\n \"parent_profile_version\": 1,\n \"update_reason\": \"ultra_requested\"\n },\n \"route\": {\n \"profile_fingerprint\": \"sha256:6f7d136c32ac421fa0b700785b0285820a2edda98f1ba0d271b2817509669963\",\n \"index_fingerprint\": \"sha256:6c3dc9a1c98b732fa286593f0ec03e43b574491c730a7038a0723b50b74db954\",\n \"profile_version\": 2,\n \"required_reference_ids\": [\n \"ultra-research\"\n ],\n \"required_families\": [\n \"core-reasoning\",\n \"deep-research\",\n \"audit-verification\"\n ],\n \"optional_families\": [],\n \"verification_mode\": \"dual\",\n \"runtime_level\": \"none\",\n \"swarm_admission\": \"preferred\",\n \"reference_phase_limit\": 4,\n \"progressive_loading\": true,\n \"route_status\": \"current\"\n }\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_35_bridge_refuses_unnormalized_explicit_depth",
"argv": [
"python",
"<skill-root>/scripts/validate_workflow.py",
"--profile",
"<temporary-test-directory>/profile.json",
"--route",
"<temporary-test-directory>/route.json",
"--state",
"<temporary-test-directory>/state.json",
"--manifest",
"<temporary-test-directory>/manifest.json",
"--reviews",
"<temporary-test-directory>/reviews.json",
"--root",
"<temporary-test-directory>"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"passed\": false,\n \"structural_valid\": false,\n \"computed_delivery_ready\": false,\n \"evidence_authenticated\": false,\n \"orthogonality_verified\": null,\n \"errors\": [\n \"PROFILE_RECHECK_REQUIRED: normalize explicit depth and use the resulting profile/version and route\"\n ],\n \"host_execution_verified\": false\n}\n",
"stderr": ""
},
{
"test": "run_regression.Regression.test_38_orthogonal_cli_without_host_receipt",
"argv": [
"python",
"<skill-root>/scripts/validate_workflow.py",
"--profile",
"<temporary-test-directory>/profile.json",
"--route",
"<temporary-test-directory>/route.json",
"--state",
"<temporary-test-directory>/state.json",
"--manifest",
"<temporary-test-directory>/manifest.json",
"--reviews",
"<temporary-test-directory>/reviews.json",
"--root",
"<temporary-test-directory>"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"passed\": false,\n \"structural_valid\": true,\n \"computed_delivery_ready\": false,\n \"evidence_authenticated\": false,\n \"orthogonality_verified\": false,\n \"errors\": [\n \"ORTHOGONALITY_UNVERIFIED: trusted host evidence/method receipt and two bound layer verifications required v1\",\n \"ORTHOGONALITY_UNVERIFIED: trusted host evidence/method receipt and two bound layer verifications required v2\"\n ],\n \"host_execution_verified\": false\n}\n",
"stderr": ""
},
{
"test": "test_2_1_1.PatchRegression.test_45_question_hard_obligation_blocks",
"argv": [
"python",
"<skill-root>/scripts/validate_delivery.py",
"<temporary-test-directory>/input0.json",
"<temporary-test-directory>/input1.json",
"--root",
"<temporary-test-directory>",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"DELIVERY_CLOSURE_BLOCKED\",\n \"message\": \"runtime closure is unresolved: ['req1 material requirement is blocked.', 'acc1 material acceptance_criterion is blocked.']\",\n \"refs\": []\n },\n {\n \"severity\": \"ERROR\",\n \"code\": \"DECLARED_READY_FALSE\",\n \"message\": \"declared_delivery_ready=true but computed_delivery_ready=false\",\n \"refs\": []\n }\n ],\n \"computed_delivery_ready\": false,\n \"computed_task_complete\": false,\n \"computed_partial_ready\": false,\n \"epistemic_closure\": {\n \"epistemic\": {\n \"applicable\": true,\n \"computed_epistemic_closed\": true,\n \"blockers\": [],\n \"warnings\": []\n },\n \"runtime\": {\n \"applicable\": true,\n \"computed_runtime_closed\": false,\n \"blockers\": [\n \"req1 material requirement is blocked.\",\n \"acc1 material acceptance_criterion is blocked.\"\n ],\n \"warnings\": []\n }\n }\n}\n",
"stderr": ""
},
{
"test": "test_2_1_1.PatchRegression.test_48_partial_handoff_never_complete",
"argv": [
"python",
"<skill-root>/scripts/validate_delivery.py",
"<temporary-test-directory>/input0.json",
"<temporary-test-directory>/input1.json",
"--root",
"<temporary-test-directory>",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 0,
"stdout": "{\n \"findings\": [\n {\n \"severity\": \"WARNING\",\n \"code\": \"DELIVERY_CLOSURE_BLOCKED\",\n \"message\": \"runtime closure is unresolved: ['req1 material requirement is blocked.', 'acc1 material acceptance_criterion is blocked.']\",\n \"refs\": []\n }\n ],\n \"computed_delivery_ready\": false,\n \"computed_task_complete\": false,\n \"computed_partial_ready\": true,\n \"epistemic_closure\": {\n \"epistemic\": {\n \"applicable\": true,\n \"computed_epistemic_closed\": true,\n \"blockers\": [],\n \"warnings\": []\n },\n \"runtime\": {\n \"applicable\": true,\n \"computed_runtime_closed\": false,\n \"blockers\": [\n \"req1 material requirement is blocked.\",\n \"acc1 material acceptance_criterion is blocked.\"\n ],\n \"warnings\": []\n }\n }\n}\n",
"stderr": ""
},
{
"test": "test_2_1_1.PatchRegression.test_51_forbidden_without_group_rejected",
"argv": [
"python",
"<skill-root>/scripts/validate_runtime.py",
"--plan",
"<temporary-test-directory>/plan.json",
"--schedule",
"<temporary-test-directory>/schedule.json",
"--json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"PARALLEL_FORBIDDEN\",\n \"message\": \"potential overlap between A and B; forbidden nodes require explicit sequencing\",\n \"refs\": [\n \"A\",\n \"B\"\n ]\n }\n ]\n}\n",
"stderr": ""
},
{
"test": "test_2_1_1.PatchRegression.test_57_prepare_profile_route_resources_cli",
"argv": [
"python",
"<skill-root>/scripts/prepare_task.py",
"<temporary-test-directory>/input0.json",
"--signal",
"ultra_requested"
],
"cwd": "temporary directory outside Skill",
"exit": 0,
"stdout": "{\n \"passed\": true,\n \"status\": \"prepared\",\n \"task_profile\": {\n \"profile_version\": 2,\n \"lane\": \"question\",\n \"depth_class\": \"ultra\",\n \"autonomy_class\": \"A\",\n \"reasoning_breadth\": \"standard\",\n \"evidence_depth\": \"standard\",\n \"challenge_depth\": \"standard\",\n \"verification_depth\": \"standard\",\n \"governance_depth\": \"minimal\",\n \"routing_confidence\": \"high\",\n \"task_modes\": [\n \"research\"\n ],\n \"task_coupling\": \"low\",\n \"persistence\": \"none\",\n \"external_side_effects\": \"none\",\n \"requested_depth\": \"ultra\",\n \"parent_profile_version\": 1,\n \"update_reason\": \"ultra_requested\"\n },\n \"route\": {\n \"profile_fingerprint\": \"sha256:6f7d136c32ac421fa0b700785b0285820a2edda98f1ba0d271b2817509669963\",\n \"index_fingerprint\": \"sha256:6c3dc9a1c98b732fa286593f0ec03e43b574491c730a7038a0723b50b74db954\",\n \"profile_version\": 2,\n \"required_reference_ids\": [\n \"ultra-research\"\n ],\n \"required_families\": [\n \"core-reasoning\",\n \"deep-research\",\n \"audit-verification\"\n ],\n \"optional_families\": [],\n \"verification_mode\": \"dual\",\n \"runtime_level\": \"none\",\n \"swarm_admission\": \"preferred\",\n \"reference_phase_limit\": 4,\n \"progressive_loading\": true,\n \"route_status\": \"current\"\n },\n \"selected_references\": [\n {\n \"reference_id\": \"ultra-research\",\n \"family\": \"deep-research\",\n \"path\": \"references/ultra-research.md\",\n \"load_reason\": \"mandatory_method\",\n \"current_gap\": \"family_entry\",\n \"profile_version\": 2,\n \"context_cost_class\": \"high\"\n },\n {\n \"reference_id\": \"problem-framing-and-effort\",\n \"family\": \"core-reasoning\",\n \"path\": \"references/problem-framing-and-effort.md\",\n \"load_reason\": \"family_entry\",\n \"current_gap\": \"family_entry\",\n \"profile_version\": 2,\n \"context_cost_class\": \"medium\"\n },\n {\n \"reference_id\": \"information-target-navigation\",\n \"family\": \"deep-research\",\n \"path\": \"references/information-target-navigation.md\",\n \"load_reason\": \"family_entry\",\n \"current_gap\": \"family_entry\",\n \"profile_version\": 2,\n \"context_cost_class\": \"medium\"\n },\n {\n \"reference_id\": \"formal-review-and-audit\",\n \"family\": \"audit-verification\",\n \"path\": \"references/formal-review-and-audit.md\",\n \"load_reason\": \"family_entry\",\n \"current_gap\": \"family_entry\",\n \"profile_version\": 2,\n \"context_cost_class\": \"high\"\n }\n ],\n \"deferred_references\": [],\n \"task_executed\": false,\n \"authority_granted\": false\n}\n",
"stderr": ""
},
{
"test": "test_2_1_1.PatchRegression.test_61_unresolved_gate_rejected_with_good_source",
"argv": [
"python",
"<skill-root>/scripts/validate_learning.py",
"<temporary-test-directory>/input0.json",
"--validation-evidence",
"<temporary-test-directory>/index.json"
],
"cwd": "temporary directory outside Skill",
"exit": 1,
"stdout": "{\n \"passed\": false,\n \"findings\": [\n {\n \"severity\": \"ERROR\",\n \"code\": \"LEARNING_PROMOTION_EVIDENCE_UNVERIFIED\",\n \"message\": \"held_out_eval_refs requires typed, applicable, passing host evidence, not a nonempty reference\"\n }\n ]\n}\n",
"stderr": ""
},
{
"test": "test_2_1_1.PatchRegression.test_62_all_typed_scoped_gates_pass",
"argv": [
"python",
"<skill-root>/scripts/validate_learning.py",
"<temporary-test-directory>/input0.json",
"--validation-evidence",
"<temporary-test-directory>/index.json"
],
"cwd": "temporary directory outside Skill",
"exit": 0,
"stdout": "{\n \"passed\": true,\n \"findings\": []\n}\n",
"stderr": ""
},
{
"test": "test_2_1_1.PatchRegression.test_62_all_typed_scoped_gates_pass",
"argv": [
"python",
"<skill-root>/scripts/retrieve_learnings.py",
"<temporary-test-directory>/input0.json",
"--task-tag",
"deep_research",
"--maintenance",
"--validation-evidence",
"<temporary-test-directory>/index.json"
],
"cwd": "temporary directory outside Skill",
"exit": 0,
"stdout": "{\n \"passed\": true,\n \"findings\": [],\n \"advisory_only\": true,\n \"selected\": [\n {\n \"learning_id\": \"synthetic:contradictory-intrinsic\",\n \"tier\": 3,\n \"source_run_refs\": [\n \"synthetic:run\"\n ],\n \"source_eval_refs\": [\n \"eval\"\n ],\n \"task_signature\": [\n \"deep_research\"\n ],\n \"failure_mode\": \"synthetic source selection failure\",\n \"root_cause_class\": \"evidence_failure\",\n \"lesson_type\": \"strategy\",\n \"heuristic\": \"Synthetic inert text: inspect primary evidence.\",\n \"applicability_conditions\": [\n \"deep_research\"\n ],\n \"anti_conditions\": [],\n \"provenance\": {\n \"feedback_types\": [\n \"deterministic_verifier\"\n ],\n \"intrinsic_reflection_only\": false\n },\n \"status\": \"promoted\",\n \"created_at\": \"2026-10-21T00:00:00Z\",\n \"rollback_ref\": \"rollback\",\n \"regression_refs\": [\n \"reg\"\n ],\n \"held_out_eval_refs\": [\n \"held\"\n ],\n \"baseline_comparison_ref\": \"baseline\",\n \"dual_review_ref\": \"review\"\n }\n ]\n}\n",
"stderr": ""
}
]Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |