[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AW0F8YQH21B5VG7ZY1SW0R":3,"skill-same:01M7AW0F8YQH21B5VG7ZY1SW0R":55},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7AW0F8YQH21B5VG7ZY1SW0R","python-dataclass-architect",null,"Design high-performance, memory-efficient, type-safe Python data structures utilizing slots=True, frozen=True, __post_init__ validation, and slotted inheritance. Do not use for mutable state dictionaries or untyped data objects.","SpectreDeath\u002FBrain-Harness","SpectreDeath","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F207463416?v=4","01M7AVGR1D4X8ADT47APKGVH2Z","JL","01M7AVGR2HSGD23BA5DBTJJTVN",0,"MIT","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpython-dataclass-architect\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: python-dataclass-architect\ndescription: Design high-performance, memory-efficient, type-safe Python data structures utilizing slots=True, frozen=True, __post_init__ validation, and slotted inheritance. Do not use for mutable state dictionaries or untyped data objects.\n---\n\n# Python Dataclass Architect\n\n`python-dataclass-architect` is the structural design and memory optimization engine for Python `@dataclass` entity models. It eliminates boilerplate, enforces object immutability, reduces memory overhead by ~75% via `slots=True`, validates domain invariants in `__post_init__`, isolates derived fields, and guarantees slot integrity across inheritance hierarchies.\n\nEvery dataclass architecture session executes this five-stage progression:\n\n```\n[1. Immutability & Hashability Assessment] → [2. Memory Footprint Profiling & Slotting] → [3. Container Isolation & Default Factories] → [4. Invariant Validation & Derived Fields] → [5. Hierarchy Integrity & Representation Tuning]\n```\n\nSee [CARD.md](CARD.md) for the companion summary card, memory benchmarks, and verification invariants.\nConsult `\u002Fcodebase-design` for deep module design principles and `\u002Fdata-topology-mapper` for state topologies.\n\n---\n\n## 1. Immutability & Hashability Assessment\n\nDetermine whether the data structure represents an immutable Value Object or a mutable Entity:\n\n1. **Value Objects (Immutable)**:\n   - Apply `@dataclass(frozen=True)` when the object represents a discrete value that must not change after construction (e.g. coordinates, route segments, configuration snapshots).\n   - *Mechanics*: Generates immutable `__setattr__` and `__delattr__` methods that raise `FrozenInstanceError` upon modification attempts.\n   - *Automatic Hashability*: Frozen dataclasses automatically generate a compatible `__hash__()` based on equality fields, allowing them to serve as dictionary keys and set members.\n2. **Entities (Mutable)**:\n   - Use standard dataclasses only when state mutations during object lifecycle are explicitly required by domain logic.\n\n```python\nfrom dataclasses import dataclass\n\n@dataclass(frozen=True)\nclass RouteSegment:\n    from_hub: str\n    to_hub: str\n    distance_km: float\n    carrier: str\n```\n\n> **Completion criterion**: Mutability profile explicitly decided, with `frozen=True` and automatic `__hash__()` applied to all Value Objects.\n\n---\n\n## 2. Memory Footprint Profiling & Slotting\n\nEliminate per-instance dictionary overhead in data processing and high-volume systems:\n\n```\n┌─────────────────────────────────────────────────────────────┐\n│              PYTHON OBJECT MEMORY ALLOCATION                │\n├──────────────────────────────┬──────────────────────────────┤\n│ Standard Dataclass           │ Slotted Dataclass            │\n│ - Uses instance __dict__     │ - Uses __slots__ descriptor  │\n│ - ~296 bytes overhead        │ - ~72 bytes overhead         │\n│ - Dynamic attribute adding   │ - Fixed, fast attribute slots│\n└──────────────────────────────┴──────────────────────────────┘\n```\n\n1. **Enable Slot Optimization**:\n   - Apply `@dataclass(slots=True)` (Python ≥ 3.10) for high-volume classes, ETL pipelines, or large collections in memory.\n2. **Quantify Memory Savings**:\n   - Standard instance: `sys.getsizeof(instance.__dict__)` overhead (~296 bytes per object before data).\n   - Slotted instance: ~72 bytes total object descriptor footprint, saving ~75% overhead per object.\n3. **Combination**:\n   - Combine with immutability when optimal: `@dataclass(slots=True, frozen=True)`.\n\n> **Completion criterion**: `slots=True` declared on high-volume and domain entity models, eliminating `__dict__` overhead.\n\n---\n\n## 3. Container Isolation & Default Factories\n\nPrevent the classic shared mutable default argument vulnerability:\n\n1. **Mandatory `default_factory` for Mutable Containers**:\n   - Never assign mutable literals (`list`, `dict`, `set`) directly as default values: `items: list[str] = []` (forbidden).\n   - Always use `field(default_factory=list)` or `field(default_factory=dict)` to guarantee that every instance receives its own isolated collection.\n2. **Dynamic Value Initialization**:\n   - For timestamps, UUIDs, or dynamic defaults, use `field(default_factory=datetime.utcnow)` or `field(default_factory=uuid.uuid4)`.\n\n```python\nfrom dataclasses import dataclass, field\nfrom datetime import datetime\nimport uuid\n\n@dataclass(slots=True)\nclass OrderBatch:\n    batch_id: str = field(default_factory=lambda: str(uuid.uuid4()))\n    items: list[str] = field(default_factory=list)\n    created_at: datetime = field(default_factory=datetime.utcnow)\n```\n\n> **Completion criterion**: All mutable containers and dynamic defaults encapsulated via `default_factory`, preventing cross-instance reference sharing.\n\n---\n\n## 4. Invariant Validation & Derived Fields\n\nEnforce structural correctness at construction time and encapsulate calculated state:\n\n1. **Encapsulate Derived Fields with `init=False`**:\n   - When a field is computed from other inputs, declare `field(init=False)` to prevent callers from supplying erroneous manual values.\n2. **Execute `__post_init__` Assertions**:\n   - Validate numerical bounds, string formats, and business constraints inside `__post_init__()`.\n   - Raise explicit `ValueError` or `TypeError` on invalid states.\n   - Compute and assign the derived fields.\n3. **Handling `frozen=True` in `__post_init__`**:\n   - If computing derived fields on a frozen dataclass, use `object.__setattr__(self, 'derived_field', computed_value)`.\n\n```python\n@dataclass(slots=True)\nclass Shipment:\n    tracking_id: str\n    weight_kg: float\n    priority: str = \"standard\"\n    freight_cost: float = field(init=False)\n\n    def __post_init__(self) -> None:\n        if self.weight_kg \u003C= 0:\n            raise ValueError(f\"weight_kg must be positive, got {self.weight_kg}\")\n        rates = {\"standard\": 1.85, \"express\": 3.40}\n        if self.priority not in rates:\n            raise ValueError(f\"Invalid priority: {self.priority!r}\")\n        self.freight_cost = round(self.weight_kg * rates[self.priority], 2)\n```\n\n> **Completion criterion**: `__post_init__` validation enforced; derived state isolated with `field(init=False)` and calculated automatically.\n\n---\n\n## 5. Hierarchy Integrity & Representation Tuning\n\nEnsure safe inheritance and tune object serialization and representation:\n\n1. **Enforce Slotted Inheritance Chain**:\n   - In Python, if a subclass uses `slots=True`, all parent classes up the inheritance tree must also use `slots=True` (or explicitly define `__slots__`). Mixing slotted and non-slotted classes breaks memory optimization or throws attribute errors.\n2. **Exclude Private State from Repr and Equality**:\n   - Use `field(repr=False, compare=False)` for internal caches, lock instances, or private audit tags (`_audit_tag`).\n3. **Ecosystem Deserialization Bridges**:\n   - Use `dacite.from_dict()` for nested dictionary-to-dataclass hydration without manual parsing.\n   - Use `marshmallow-dataclass` for automatic schema generation.\n   - Upgrade to `pydantic.dataclasses.dataclass` when external JSON API payload validation is required.\n\n> **Completion criterion**: Inheritance chains uniformly slotted; internal fields hidden from `repr` and `compare`; serialization bridge verified.\n\n---\n\n## In-File Reference: Production-Grade Dataclass Template\n\n```python\nfrom dataclasses import dataclass, field\nfrom datetime import datetime\nimport uuid\n\n@dataclass(slots=True, frozen=True)\nclass TransactionRecord:\n    account_id: str\n    amount_cents: int\n    currency: str = \"USD\"\n    transaction_id: str = field(default_factory=lambda: str(uuid.uuid4()))\n    timestamp: datetime = field(default_factory=datetime.utcnow)\n    tags: list[str] = field(default_factory=list)\n    fee_cents: int = field(init=False)\n    _audit_hash: str = field(default=\"\", repr=False, compare=False)\n\n    def __post_init__(self) -> None:\n        if self.amount_cents \u003C= 0:\n            raise ValueError(f\"amount_cents must be positive, got {self.amount_cents}\")\n        fee = int(self.amount_cents * 0.02)\n        object.__setattr__(self, \"fee_cents\", fee)\n        object.__setattr__(self, \"_audit_hash\", f\"{self.transaction_id}:{fee}\")\n```\n\n---\n\n## The Three Foundational Pillars\n\n### 1. The Visual Brief\nSynthesize findings, structural matrices, and execution DAGs into a self-contained HTML visual brief written to `%TEMP%\\python-dataclass-architect-\u003Ctimestamp>.html` (or `\u002Ftmp\u002Fpython-dataclass-architect-\u003Ctimestamp>.html` on Unix) loading Tailwind CSS and Mermaid.js via CDN. Present the absolute clickable path to the user for visual review.\n\n### 2. The Mandatory Checkpoint\nWhen proposing structural modifications, refactors, or execution pipelines, always author an `implementation_plan.md` artifact with `RequestFeedback: true`. The agent must **STOP and wait** for explicit human confirmation before executing mutating actions.\n\n### 3. Explicit Anti-Patterns\nRigid behavioral boundaries must be maintained to prevent catastrophic failure modes.\n\n---\n\n## Anti-Patterns\n\n- **Mutable Default Values** — Setting `items: list = []` directly, leading to shared state across all instances of the class.\n- **Unslotted High-Volume Entities** — Creating millions of dataclass instances without `slots=True`, wasting hundreds of megabytes in `__dict__` overhead.\n- **Slotted-Unslotted Hierarchy Collision** — Inheriting a `slots=True` class from an unslotted base class, leading to subtle `__dict__` reappearance or attribute crashes.\n- **Caller-Exposed Derived Fields** — Leaving computed fields in the `__init__` signature instead of declaring `field(init=False)`, allowing callers to pass conflicting derived values.\n- **Post-Init Frozen Mutation without Object Setattr** — Attempting direct assignment `self.cost = x` inside `__post_init__` on a `frozen=True` dataclass, raising `FrozenInstanceError`.\n","# Python Dataclass Architect\n\n`python-dataclass-architect` is the structural design and memory optimization engine for Python `@dataclass` entity models. It eliminates boilerplate, enforces object immutability, reduces memory overhead by ~75% via `slots=True`, validates domain invariants in `__post_init__`, isolates derived fields, and guarantees slot integrity across inheritance hierarchies.\n\nEvery dataclass architecture session executes this five-stage progression:\n\n```\n[1. Immutability & Hashability Assessment] → [2. Memory Footprint Profiling & Slotting] → [3. Container Isolation & Default Factories] → [4. Invariant Validation & Derived Fields] → [5. Hierarchy Integrity & Representation Tuning]\n```\n\nSee [CARD.md](CARD.md) for the companion summary card, memory benchmarks, and verification invariants.\nConsult `\u002Fcodebase-design` for deep module design principles and `\u002Fdata-topology-mapper` for state topologies.\n\n---\n\n## 1. Immutability & Hashability Assessment\n\nDetermine whether the data structure represents an immutable Value Object or a mutable Entity:\n\n1. **Value Objects (Immutable)**:\n   - Apply `@dataclass(frozen=True)` when the object represents a discrete value that must not change after construction (e.g. coordinates, route segments, configuration snapshots).\n   - *Mechanics*: Generates immutable `__setattr__` and `__delattr__` methods that raise `FrozenInstanceError` upon modification attempts.\n   - *Automatic Hashability*: Frozen dataclasses automatically generate a compatible `__hash__()` based on equality fields, allowing them to serve as dictionary keys and set members.\n2. **Entities (Mutable)**:\n   - Use standard dataclasses only when state mutations during object lifecycle are explicitly required by domain logic.\n\n```python\nfrom dataclasses import dataclass\n\n@dataclass(frozen=True)\nclass RouteSegment:\n    from_hub: str\n    to_hub: str\n    distance_km: float\n    carrier: str\n```\n\n> **Completion criterion**: Mutability profile explicitly decided, with `frozen=True` and automatic `__hash__()` applied to all Value Objects.\n\n---\n\n## 2. Memory Footprint Profiling & Slotting\n\nEliminate per-instance dictionary overhead in data processing and high-volume systems:\n\n```\n┌─────────────────────────────────────────────────────────────┐\n│              PYTHON OBJECT MEMORY ALLOCATION                │\n├──────────────────────────────┬──────────────────────────────┤\n│ Standard Dataclass           │ Slotted Dataclass            │\n│ - Uses instance __dict__     │ - Uses __slots__ descriptor  │\n│ - ~296 bytes overhead        │ - ~72 bytes overhead         │\n│ - Dynamic attribute adding   │ - Fixed, fast attribute slots│\n└──────────────────────────────┴──────────────────────────────┘\n```\n\n1. **Enable Slot Optimization**:\n   - Apply `@dataclass(slots=True)` (Python ≥ 3.10) for high-volume classes, ETL pipelines, or large collections in memory.\n2. **Quantify Memory Savings**:\n   - Standard instance: `sys.getsizeof(instance.__dict__)` overhead (~296 bytes per object before data).\n   - Slotted instance: ~72 bytes total object descriptor footprint, saving ~75% overhead per object.\n3. **Combination**:\n   - Combine with immutability when optimal: `@dataclass(slots=True, frozen=True)`.\n\n> **Completion criterion**: `slots=True` declared on high-volume and domain entity models, eliminating `__dict__` overhead.\n\n---\n\n## 3. Container Isolation & Default Factories\n\nPrevent the classic shared mutable default argument vulnerability:\n\n1. **Mandatory `default_factory` for Mutable Containers**:\n   - Never assign mutable literals (`list`, `dict`, `set`) directly as default values: `items: list[str] = []` (forbidden).\n   - Always use `field(default_factory=list)` or `field(default_factory=dict)` to guarantee that every instance receives its own isolated collection.\n2. **Dynamic Value Initialization**:\n   - For timestamps, UUIDs, or dynamic defaults, use `field(default_factory=datetime.utcnow)` or `field(default_factory=uuid.uuid4)`.\n\n```python\nfrom dataclasses import dataclass, field\nfrom datetime import datetime\nimport uuid\n\n@dataclass(slots=True)\nclass OrderBatch:\n    batch_id: str = field(default_factory=lambda: str(uuid.uuid4()))\n    items: list[str] = field(default_factory=list)\n    created_at: datetime = field(default_factory=datetime.utcnow)\n```\n\n> **Completion criterion**: All mutable containers and dynamic defaults encapsulated via `default_factory`, preventing cross-instance reference sharing.\n\n---\n\n## 4. Invariant Validation & Derived Fields\n\nEnforce structural correctness at construction time and encapsulate calculated state:\n\n1. **Encapsulate Derived Fields with `init=False`**:\n   - When a field is computed from other inputs, declare `field(init=False)` to prevent callers from supplying erroneous manual values.\n2. **Execute `__post_init__` Assertions**:\n   - Validate numerical bounds, string formats, and business constraints inside `__post_init__()`.\n   - Raise explicit `ValueError` or `TypeError` on invalid states.\n   - Compute and assign the derived fields.\n3. **Handling `frozen=True` in `__post_init__`**:\n   - If computing derived fields on a frozen dataclass, use `object.__setattr__(self, 'derived_field', computed_value)`.\n\n```python\n@dataclass(slots=True)\nclass Shipment:\n    tracking_id: str\n    weight_kg: float\n    priority: str = \"standard\"\n    freight_cost: float = field(init=False)\n\n    def __post_init__(self) -> None:\n        if self.weight_kg \u003C= 0:\n            raise ValueError(f\"weight_kg must be positive, got {self.weight_kg}\")\n        rates = {\"standard\": 1.85, \"express\": 3.40}\n        if self.priority not in rates:\n            raise ValueError(f\"Invalid priority: {self.priority!r}\")\n        self.freight_cost = round(self.weight_kg * rates[self.priority], 2)\n```\n\n> **Completion criterion**: `__post_init__` validation enforced; derived state isolated with `field(init=False)` and calculated automatically.\n\n---\n\n## 5. Hierarchy Integrity & Representation Tuning\n\nEnsure safe inheritance and tune object serialization and representation:\n\n1. **Enforce Slotted Inheritance Chain**:\n   - In Python, if a subclass uses `slots=True`, all parent classes up the inheritance tree must also use `slots=True` (or explicitly define `__slots__`). Mixing slotted and non-slotted classes breaks memory optimization or throws attribute errors.\n2. **Exclude Private State from Repr and Equality**:\n   - Use `field(repr=False, compare=False)` for internal caches, lock instances, or private audit tags (`_audit_tag`).\n3. **Ecosystem Deserialization Bridges**:\n   - Use `dacite.from_dict()` for nested dictionary-to-dataclass hydration without manual parsing.\n   - Use `marshmallow-dataclass` for automatic schema generation.\n   - Upgrade to `pydantic.dataclasses.dataclass` when external JSON API payload validation is required.\n\n> **Completion criterion**: Inheritance chains uniformly slotted; internal fields hidden from `repr` and `compare`; serialization bridge verified.\n\n---\n\n## In-File Reference: Production-Grade Dataclass Template\n\n```python\nfrom dataclasses import dataclass, field\nfrom datetime import datetime\nimport uuid\n\n@dataclass(slots=True, frozen=True)\nclass TransactionRecord:\n    account_id: str\n    amount_cents: int\n    currency: str = \"USD\"\n    transaction_id: str = field(default_factory=lambda: str(uuid.uuid4()))\n    timestamp: datetime = field(default_factory=datetime.utcnow)\n    tags: list[str] = field(default_factory=list)\n    fee_cents: int = field(init=False)\n    _audit_hash: str = field(default=\"\", repr=False, compare=False)\n\n    def __post_init__(self) -> None:\n        if self.amount_cents \u003C= 0:\n            raise ValueError(f\"amount_cents must be positive, got {self.amount_cents}\")\n        fee = int(self.amount_cents * 0.02)\n        object.__setattr__(self, \"fee_cents\", fee)\n        object.__setattr__(self, \"_audit_hash\", f\"{self.transaction_id}:{fee}\")\n```\n\n---\n\n## The Three Foundational Pillars\n\n### 1. The Visual Brief\nSynthesize findings, structural matrices, and execution DAGs into a self-contained HTML visual brief written to `%TEMP%\\python-dataclass-architect-\u003Ctimestamp>.html` (or `\u002Ftmp\u002Fpython-dataclass-architect-\u003Ctimestamp>.html` on Unix) loading Tailwind CSS and Mermaid.js via CDN. Present the absolute clickable path to the user for visual review.\n\n### 2. The Mandatory Checkpoint\nWhen proposing structural modifications, refactors, or execution pipelines, always author an `implementation_plan.md` artifact with `RequestFeedback: true`. The agent must **STOP and wait** for explicit human confirmation before executing mutating actions.\n\n### 3. Explicit Anti-Patterns\nRigid behavioral boundaries must be maintained to prevent catastrophic failure modes.\n\n---\n\n## Anti-Patterns\n\n- **Mutable Default Values** — Setting `items: list = []` directly, leading to shared state across all instances of the class.\n- **Unslotted High-Volume Entities** — Creating millions of dataclass instances without `slots=True`, wasting hundreds of megabytes in `__dict__` overhead.\n- **Slotted-Unslotted Hierarchy Collision** — Inheriting a `slots=True` class from an unslotted base class, leading to subtle `__dict__` reappearance or attribute crashes.\n- **Caller-Exposed Derived Fields** — Leaving computed fields in the `__init__` signature instead of declaring `field(init=False)`, allowing callers to pass conflicting derived values.\n- **Post-Init Frozen Mutation without Object Setattr** — Attempting direct assignment `self.cost = x` inside `__post_init__` on a `frozen=True` dataclass, raising `FrozenInstanceError`.\n",{"name":5,"description":7},"main","eff3b00e36d1d233ad4a4389605c82fbfa0326d3",".agents\u002Fskills\u002Fpython-dataclass-architect","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness","https:\u002F\u002Fgithub.com\u002FSpectreDeath","I'm here to manage stress so I wouldn't expect earth shattering break throughs I'm just an enthusiast that likes making stuff. ","2026-11-15 05:32:58",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add SpectreDeath\u002FBrain-Harness --skill python-dataclass-architect",{"tool":37,"command":38},"bunx","bunx skills add SpectreDeath\u002FBrain-Harness --skill python-dataclass-architect",{"tool":40,"command":41},"pnpm","pnpm dlx skills add SpectreDeath\u002FBrain-Harness --skill python-dataclass-architect","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpython-dataclass-architect\u002FSKILL.md",true,[45,51],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"CARD.md","REFERENCE","参考文档",3958,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpython-dataclass-architect\u002FCARD.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"config.default.yaml",302,"https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpython-dataclass-architect\u002Fconfig.default.yaml",[56,63,70,77,84,91],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7E0W6FR68J2N9CXCZTAQJFX","ui-behavior-primitive-architect","Architect, audit, and verify zero-dependency headless UI behavior primitives, WebMCP agent bridges, WAI-ARIA\u002FSSR\u002FRTL tri-modal checks, and framework expert routing. Do not use for static CSS theme styling or backend database migrations.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fui-behavior-primitive-architect\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7E0VZ7JQNW34G271DENFGYP","trustgraph-ontology-governor","Govern knowledge graphs, SHACL-AF triple policies, OntologyRAG subclass validation, PROV-O dual named graphs, and Laya entropy decision scoring. Do not use for relational SQL queries or generic web scraping.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftrustgraph-ontology-governor\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7E0VQ6Z7R45Q8QAZ4MT39EK","shim-harness-governor","Govern universal CLI agent loops, 4-tier tool permissions, ancestor-symlink workspace sandboxes, deterministic-first command routing, collision-safe MCP namespacing, and layered skill loading. Do not use for static UI styling or external SQL analytics.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fshim-harness-governor\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7E0VC18NMP1QBSRJ3TPQ7MB","graphiti-zep-memory-governor","Govern bi-temporal knowledge graphs with Graphiti future-edge clamping, MinHash\u002FLSH entity dedup, RRF\u002FMMR reranking, and Zep typed ontologies. Do not use for static SQL joins or generic web crawling.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgraphiti-zep-memory-governor\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7E0V12ABE1RW3ZRCST8VH5Z","agora-mcp-workbench-architect","Architect, audit, and orchestrate Agora Workbench MCP servers, loopback sidecars, unified state graphs, gateway\u002Fdispatcher connectors, and policy-enforced data lakes. Do not use for static frontend CSS styling or non-MCP desktop GUI automation.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fagora-mcp-workbench-architect\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7BFYG6QT3484VC57TZ19V7P","skill-eval-assurance-runner","Evaluate and assure agent skills using small-N Wilson confidence intervals, unbiased pass^k reliability, deterministic trajectory graders, preflight boundary honesty, and sealed digest verification. Do not use for subjective prose review or unconstrained production deployment.","https:\u002F\u002Fgithub.com\u002FSpectreDeath\u002FBrain-Harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-eval-assurance-runner\u002FSKILL.md",[],[]]