[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A0DRA3S4D2V42FE6556BW2":3,"skill-same:01M7A0DRA3S4D2V42FE6556BW2":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7A0DRA3S4D2V42FE6556BW2","CoderOS Cognitive Persistence",null,"Validate, reconcile, and promote records in the Knowledge\u002FEpisodic\u002FWisdom\u002FRuntime-Inference persistence layer.","ChristianV997\u002FCoderOS","ChristianV997","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F227661135?v=4","01M7A0CBPF0W3PYCR02GVS7M59","01M7A0CBQ10CQPW99BNMXC5496",1,"MIT","https:\u002F\u002Fgithub.com\u002FChristianV997\u002FCoderOS\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcoderos-cognitive-persistence\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: CoderOS Cognitive Persistence\ndescription: Validate, reconcile, and promote records in the Knowledge\u002FEpisodic\u002FWisdom\u002FRuntime-Inference persistence layer.\n---\n# CoderOS Cognitive Persistence\n\nProvides rules for working with `repo_dev_runtime.cognitive_persistence`,\n`repo_dev_runtime.knowledge`, `repo_dev_runtime.memory.episodic_trajectory`,\n`repo_dev_runtime.source_truth`, and `repo_dev_runtime.consolidation.claude`:\nthe `cognitive_persistence_cli`'s `validate`, `reconcile`, `promote`,\n`report`, `integration-audit`, and `render` subcommands, plus the\nCanonical Consolidation Authority Graph's `validate-graph`,\n`authority-audit`, `contradiction-report`, and `reconcile` subcommands\n(`python -m repo_dev_runtime.consolidation.claude.cli`).\n\n## Rules\n\n- Never construct a `KnowledgeRecord` with `provenance_status=\"unverified\"`\n  unless both `evidence` and `attested_by` are populated -- knowledge\n  cannot rest on an unverified model statement alone.\n- Never hand-set `WisdomCandidateRecord.wisdom_promotion_status=\"promoted\"`\n  without re-running it through `wisdom.evaluate_wisdom_promotion` first --\n  promotion requires >= 3 independent `(lane_id, work_order_id)` pairs.\n- Never write code that converts a `RuntimeInferenceRecord` directly into a\n  `KnowledgeRecord` or `WisdomCandidateRecord` -- the only path is\n  `adapters.propose_knowledge_from_runtime_inference`, which requires\n  independent evidence and rejects a verbatim-matching statement.\n- Never resolve a `ContradictionRecord` to `confirmed`\u002F`superseded`\u002F`rejected`\n  without `resolution_evidence`, `resolved_event_time`, and `resolver` all\n  populated.\n- Never give an `EvidenceTrustFinding` a free-text `adapted_from` -- it must\n  be a `\"file#record_id\"` pointer to an already-existing record, never a\n  copy of that record's own text.\n- Decay is never a stored field on `EpisodicTrajectoryRecord` -- always\n  compute it at read time via `memory.decay.evaluate_decay`.\n- Supersession is never a mutation of a `KnowledgeRecord` -- always compute\n  it via `knowledge.supersession.compute_effective_status`.\n- `WisdomCandidateRecord.supporting_decision_refs` (distinct from\n  `supporting_trajectory_ids`) is the only way an accepted\n  `ImprovementDecisionRecord` may count toward independent confirmation --\n  never append a decision reference into `supporting_trajectory_ids`, and\n  never write to `improvement_decision_ledger.py` from this layer (read\n  `decision_status` only, via `accepted_decision_confirmation_ref`).\n- `source_truth.SourceTruthLedgerEntry` never carries fact text -- it is a\n  pointer (`knowledge_id`) plus `confidence`\u002F`validity_status`, always\n  produced by `source_truth.ledger.build_source_truth_ledger`, never\n  hand-constructed with a fabricated confidence score.\n- `consolidation.claude.graph.CapabilityGraphNode.module_path` must be a\n  file that actually exists in this repository (or a pinned external\n  commit SHA) -- never a templated\u002Fsequential placeholder path. Before\n  trusting any `projects\u002Fcoderos\u002Fsource_mining\u002F*.json` corpus as an\n  ingestion source, spot-check several rows for exactly this pattern (see\n  `reconciliation.REJECTED_TEMPLATED_SOURCE_FILES` for a real example of\n  four files that failed this check and were rejected as inputs).\n- Every `DuplicateAuthorityFinding` and `ArtifactReconciliationRecord`\n  requires an `adapted_from` `\"file#record_id\"` pointer -- never free text\n  -- exactly like `EvidenceTrustFinding`.\n- `consolidation.claude.mvp_projection` functions prove compatibility with\n  another subsystem's input contract by actually constructing and\n  `.validate()`-ing a real instance of that subsystem's own dataclass --\n  never by assertion. If a real field's value has no valid translation\n  (e.g. a `reuse_mode` absent from `work_order_factory.SOURCE_MODES`),\n  raise; never silently coerce or drop content to force a fake pass.\n  `operator_loop.py` may be imported read-only for its dataclasses in this\n  module -- it is a forbidden-to-modify file for this mission's own\n  allowed-paths, and no code here ever writes to it.\n- Episodic memory's `confidence`, `frequency`, `replay_status`, and\n  `decay_stage` are always computed via\n  `memory.episodic_projection.compute_episodic_memory_projection` --\n  never new stored fields on `EpisodicTrajectoryRecord`, which stays\n  frozen. `frequency` counts cohort records sharing `(lane_id,\n  work_order_id)` -- the same independence unit\n  `wisdom.evaluate_wisdom_promotion` uses -- so the two never disagree\n  about what \"the same attempt context\" means.\n- `consolidation.claude.context_projection` and `feedback_projection`\n  project real records into the pre-existing `context_tiers.ContextNode`\n  and `source_leverage_routing_feedback.ReuseOutcomeSignal`\u002F\n  `CandidateLaneFit` dataclasses -- never a new L0\u002FL1\u002FL2 or\n  feedback\u002Flane-fit schema. `candidate_lane_fit_from_wisdom_candidate`\n  requires an explicit, pre-validated `lane` argument and raises on any\n  value outside `source_leverage_routing_feedback.LANES` -- that enum\n  shares zero members with real `lane_id` values, so never guess a\n  mapping between them.\n- `consolidation.claude.authority.check_no_forbidden_authority_duplication`\n  is the live, `ast`-based self-check proving this subsystem never\n  defines a `Scheduler`, `MergeQueue`, `OperatorLoop`, `SupervisorLoop`,\n  or bare `Queue` name -- re-run it (via `authority-audit`) after adding\n  any new top-level class\u002Ffunction to an owned package, never assume it\n  still passes.\n","# CoderOS Cognitive Persistence\n\nProvides rules for working with `repo_dev_runtime.cognitive_persistence`,\n`repo_dev_runtime.knowledge`, `repo_dev_runtime.memory.episodic_trajectory`,\n`repo_dev_runtime.source_truth`, and `repo_dev_runtime.consolidation.claude`:\nthe `cognitive_persistence_cli`'s `validate`, `reconcile`, `promote`,\n`report`, `integration-audit`, and `render` subcommands, plus the\nCanonical Consolidation Authority Graph's `validate-graph`,\n`authority-audit`, `contradiction-report`, and `reconcile` subcommands\n(`python -m repo_dev_runtime.consolidation.claude.cli`).\n\n## Rules\n\n- Never construct a `KnowledgeRecord` with `provenance_status=\"unverified\"`\n  unless both `evidence` and `attested_by` are populated -- knowledge\n  cannot rest on an unverified model statement alone.\n- Never hand-set `WisdomCandidateRecord.wisdom_promotion_status=\"promoted\"`\n  without re-running it through `wisdom.evaluate_wisdom_promotion` first --\n  promotion requires >= 3 independent `(lane_id, work_order_id)` pairs.\n- Never write code that converts a `RuntimeInferenceRecord` directly into a\n  `KnowledgeRecord` or `WisdomCandidateRecord` -- the only path is\n  `adapters.propose_knowledge_from_runtime_inference`, which requires\n  independent evidence and rejects a verbatim-matching statement.\n- Never resolve a `ContradictionRecord` to `confirmed`\u002F`superseded`\u002F`rejected`\n  without `resolution_evidence`, `resolved_event_time`, and `resolver` all\n  populated.\n- Never give an `EvidenceTrustFinding` a free-text `adapted_from` -- it must\n  be a `\"file#record_id\"` pointer to an already-existing record, never a\n  copy of that record's own text.\n- Decay is never a stored field on `EpisodicTrajectoryRecord` -- always\n  compute it at read time via `memory.decay.evaluate_decay`.\n- Supersession is never a mutation of a `KnowledgeRecord` -- always compute\n  it via `knowledge.supersession.compute_effective_status`.\n- `WisdomCandidateRecord.supporting_decision_refs` (distinct from\n  `supporting_trajectory_ids`) is the only way an accepted\n  `ImprovementDecisionRecord` may count toward independent confirmation --\n  never append a decision reference into `supporting_trajectory_ids`, and\n  never write to `improvement_decision_ledger.py` from this layer (read\n  `decision_status` only, via `accepted_decision_confirmation_ref`).\n- `source_truth.SourceTruthLedgerEntry` never carries fact text -- it is a\n  pointer (`knowledge_id`) plus `confidence`\u002F`validity_status`, always\n  produced by `source_truth.ledger.build_source_truth_ledger`, never\n  hand-constructed with a fabricated confidence score.\n- `consolidation.claude.graph.CapabilityGraphNode.module_path` must be a\n  file that actually exists in this repository (or a pinned external\n  commit SHA) -- never a templated\u002Fsequential placeholder path. Before\n  trusting any `projects\u002Fcoderos\u002Fsource_mining\u002F*.json` corpus as an\n  ingestion source, spot-check several rows for exactly this pattern (see\n  `reconciliation.REJECTED_TEMPLATED_SOURCE_FILES` for a real example of\n  four files that failed this check and were rejected as inputs).\n- Every `DuplicateAuthorityFinding` and `ArtifactReconciliationRecord`\n  requires an `adapted_from` `\"file#record_id\"` pointer -- never free text\n  -- exactly like `EvidenceTrustFinding`.\n- `consolidation.claude.mvp_projection` functions prove compatibility with\n  another subsystem's input contract by actually constructing and\n  `.validate()`-ing a real instance of that subsystem's own dataclass --\n  never by assertion. If a real field's value has no valid translation\n  (e.g. a `reuse_mode` absent from `work_order_factory.SOURCE_MODES`),\n  raise; never silently coerce or drop content to force a fake pass.\n  `operator_loop.py` may be imported read-only for its dataclasses in this\n  module -- it is a forbidden-to-modify file for this mission's own\n  allowed-paths, and no code here ever writes to it.\n- Episodic memory's `confidence`, `frequency`, `replay_status`, and\n  `decay_stage` are always computed via\n  `memory.episodic_projection.compute_episodic_memory_projection` --\n  never new stored fields on `EpisodicTrajectoryRecord`, which stays\n  frozen. `frequency` counts cohort records sharing `(lane_id,\n  work_order_id)` -- the same independence unit\n  `wisdom.evaluate_wisdom_promotion` uses -- so the two never disagree\n  about what \"the same attempt context\" means.\n- `consolidation.claude.context_projection` and `feedback_projection`\n  project real records into the pre-existing `context_tiers.ContextNode`\n  and `source_leverage_routing_feedback.ReuseOutcomeSignal`\u002F\n  `CandidateLaneFit` dataclasses -- never a new L0\u002FL1\u002FL2 or\n  feedback\u002Flane-fit schema. `candidate_lane_fit_from_wisdom_candidate`\n  requires an explicit, pre-validated `lane` argument and raises on any\n  value outside `source_leverage_routing_feedback.LANES` -- that enum\n  shares zero members with real `lane_id` values, so never guess a\n  mapping between them.\n- `consolidation.claude.authority.check_no_forbidden_authority_duplication`\n  is the live, `ast`-based self-check proving this subsystem never\n  defines a `Scheduler`, `MergeQueue`, `OperatorLoop`, `SupervisorLoop`,\n  or bare `Queue` name -- re-run it (via `authority-audit`) after adding\n  any new top-level class\u002Ffunction to an owned package, never assume it\n  still passes.\n",{"name":5,"description":7},"main","b980e90b49ea7c0639094f3060ced5aaf772a571",".agents\u002Fskills\u002Fcoderos-cognitive-persistence",0,"https:\u002F\u002Fgithub.com\u002FChristianV997\u002FCoderOS","https:\u002F\u002Fgithub.com\u002FChristianV997","2026-10-07 15:44:03",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add ChristianV997\u002FCoderOS --skill \"CoderOS Cognitive Persistence\"",{"tool":36,"command":37},"bunx","bunx skills add ChristianV997\u002FCoderOS --skill \"CoderOS Cognitive Persistence\"",{"tool":39,"command":40},"pnpm","pnpm dlx skills add ChristianV997\u002FCoderOS --skill \"CoderOS Cognitive Persistence\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FChristianV997\u002FCoderOS\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcoderos-cognitive-persistence\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M7A0MH3MZXKX7B9AWKFNM5DB","coderos","Workspace-native skill for operating, extending, and safe parallel implementation on CoderOS itself. Use when selecting non-overlapping implementation slices, navigating CoderOS governance, scout, work-order, sandbox, and skill-pack seams, and executing safe changes.","https:\u002F\u002Fgithub.com\u002FChristianV997\u002FCoderOS\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcoderos\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M7A0ME1KR3V3M79FXR0FHM9Q","coderos-workspace-operator","Skill for interacting with the local CoderOS Operator Workspace to coordinate tasks and prevent collisions.","https:\u002F\u002Fgithub.com\u002FChristianV997\u002FCoderOS\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcoderos-workspace-operator\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M7A0M9GV17YZCTWS23Y9SY1K","coderos-workorder","Workspace-native skill for drafting valid typed CoderOS WorkOrder JSON payloads and exercising dry-run work-order dispatch safely without live execution or runtime mutation.","https:\u002F\u002Fgithub.com\u002FChristianV997\u002FCoderOS\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcoderos-workorder\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M7A0M6H61K6K6C8FKKVP0F29","coderos-worker-adapters","Generates deterministic safe command packets for various workers","https:\u002F\u002Fgithub.com\u002FChristianV997\u002FCoderOS\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcoderos-worker-adapters\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M7A0M4DY9PCD2D0NTH2Q8WC0","coderos-work-order-factory","Draft and validate deterministic CoderOS work-order factory artifacts without dispatch or provider activation.","https:\u002F\u002Fgithub.com\u002FChristianV997\u002FCoderOS\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcoderos-work-order-factory\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M7A0KZ6PWAB5FKA7P502AP1P","coderos-source-reuse-auditor","Apply the Source Reuse Acceptance Auditor rubric before opening, and before merging, any PR that copies, adapts, mines, vendors, clean-room-reimplements, sidecar-wraps, or references a public repository -- the acceptance gate that sits above the license\u002Fsecurity boundary, not a substitute for it.","https:\u002F\u002Fgithub.com\u002FChristianV997\u002FCoderOS\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcoderos-source-reuse-auditor\u002FSKILL.md",[],[]]