[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CWE0403J1SZ151MV7KFCF1":3,"skill-same:01M6CWE0403J1SZ151MV7KFCF1":201},{"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":22,"linkOnly":23,"markdownContent":24,"markdownBody":25,"frontMatter":26,"refName":29,"commitSha":30,"skillDirectory":5,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M6CWE0403J1SZ151MV7KFCF1","ai-ethics",null,"AI ethics principles and implementation","ffsshhttiikk\u002Fopencode-agents-skills","ffsshhttiikk","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F226346827?v=4","01M6CWD9RR3Y7VRQX3MXYC8FYH","01M6CWD9WVPYAZW0J82G1VKGHY",3,"MIT","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fai-ethics\u002FSKILL.md",[],[18,19,20,21],"ethics","ai ethics","opencode","implementation","2026-11-10 10:12:30",false,"---\nname: ai-ethics\ndescription: AI ethics principles and implementation\nlicense: MIT\ncompatibility: opencode\nmetadata:\n  audience: developers\n  category: ethics\n---\n\n## What I do\n- Identify ethical issues in AI systems\n- Ensure fairness and bias mitigation\n- Implement transparency and explainability\n- Design for accountability\n- Protect privacy in ML systems\n\n## When to use me\nWhen building AI\u002FML systems that make decisions affecting people.\n\n## Ethical AI Framework\n\n### Fairness\n```python\nfrom typing import List, Dict\nimport numpy as np\n\nclass FairnessAuditor:\n    \"\"\"Audit AI systems for fairness\"\"\"\n    \n    def __init__(self):\n        self.protected_attributes = [\"race\", \"gender\", \"age\", \n                                      \"disability\", \"religion\"]\n    \n    def calculate_disparate_impact(self, predictions: np.ndarray,\n                                   sensitive_attr: np.ndarray,\n                                   threshold: float = 0.8) -> Dict:\n        \"\"\"Calculate disparate impact ratio\"\"\"\n        groups = np.unique(sensitive_attr)\n        \n        if len(groups) \u003C 2:\n            return {\"error\": \"Need multiple groups\"}\n        \n        positive_rates = {}\n        for group in groups:\n            mask = sensitive_attr == group\n            positive_rates[group] = predictions[mask].mean()\n        \n        # Calculate impact ratio\n        reference_rate = positive_rates[groups[0]]\n        ratios = {}\n        \n        for group, rate in positive_rates.items():\n            if reference_rate > 0:\n                ratios[group] = rate \u002F reference_rate\n        \n        return {\n            \"positive_rates\": positive_rates,\n            \"ratios\": ratios,\n            \"fails_disparate_impact\": any(r \u003C threshold for r in ratios.values())\n        }\n    \n    def calculate_equalized_odds(self, predictions: np.ndarray,\n                               labels: np.ndarray,\n                               sensitive_attr: np.ndarray) -> Dict:\n        \"\"\"Check equalized odds (true positive rate equality)\"\"\"\n        groups = np.unique(sensitive_attr)\n        \n        tpr_by_group = {}\n        fpr_by_group = {}\n        \n        for group in groups:\n            mask = sensitive_attr == group\n            tp = ((predictions == 1) & (labels == 1) & mask).sum()\n            fp = ((predictions == 1) & (labels == 0) & mask).sum()\n            tn = ((predictions == 0) & (labels == 0) & mask).sum()\n            fn = ((predictions == 0) & (labels == 1) & mask).sum()\n            \n            tpr_by_group[group] = tp \u002F (tp + fn) if (tp + fn) > 0 else 0\n            fpr_by_group[group] = fp \u002F (fp + tn) if (fp + tn) > 0 else 0\n        \n        return {\n            \"true_positive_rates\": tpr_by_group,\n            \"false_positive_rates\": fpr_by_group,\n            \"equalized\": self._check_equalized(tpr_by_group, fpr_by_group)\n        }\n    \n    def mitigate_bias(self, model, X: np.ndarray, \n                     sensitive_attr: np.ndarray,\n                     method: str = \"reweighting\") -> np.ndarray:\n        \"\"\"Apply bias mitigation technique\"\"\"\n        if method == \"reweighting\":\n            return self._reweighting_mitigation(X, sensitive_attr)\n        elif method == \"threshold\":\n            return self._threshold_adjustment(X, sensitive_attr)\n        else:\n            raise ValueError(f\"Unknown method: {method}\")\n    \n    def _reweighting_mitigation(self, X, sensitive_attr) -> np.ndarray:\n        \"\"\"Reweighting-based fairness intervention\"\"\"\n        # Compute weights to equalize outcomes\n        return X  # Simplified\n```\n\n### Transparency and Explainability\n```python\nclass ModelExplainer:\n    \"\"\"Explain model predictions\"\"\"\n    \n    def __init__(self, model):\n        self.model = model\n    \n    def explain_prediction(self, instance: np.ndarray,\n                          method: str = \"shap\") -> Dict:\n        \"\"\"Explain individual prediction\"\"\"\n        if method == \"shap\":\n            return self._shap_explanation(instance)\n        elif method == \"lime\":\n            return self._lime_explanation(instance)\n        elif method == \"feature_importance\":\n            return self._feature_importance_explanation(instance)\n    \n    def _feature_importance_explanation(self, instance: np.ndarray) -> Dict:\n        \"\"\"Global feature importance explanation\"\"\"\n        if hasattr(self.model, \"feature_importances_\"):\n            importances = self.model.feature_importances_\n            return {\n                \"method\": \"feature_importance\",\n                \"importances\": importances.tolist(),\n                \"top_features\": np.argsort(importances)[-5:][::-1].tolist()\n            }\n        return {\"error\": \"Model does not support feature importance\"}\n    \n    def generate_model_cards(self, model, training_data: Dict,\n                            performance: Dict) -> Dict:\n        \"\"\"Generate model documentation (model card)\"\"\"\n        return {\n            \"model_name\": model.__class__.__name__,\n            \"overview\": \"Description of model purpose\",\n            \"owner\": \"Team responsible\",\n            \"training_data\": {\n                \"dataset\": training_data.get(\"name\"),\n                \"size\": training_data.get(\"size\"),\n                \"sources\": training_data.get(\"sources\")\n            },\n            \"performance\": {\n                \"metrics\": performance.get(\"metrics\"),\n                \"evaluation_data\": performance.get(\"test_size\")\n            },\n            \"fairness\": {\n                \"evaluated_groups\": [],\n                \"known_biases\": []\n            },\n            \"limitations\": \"Known model limitations\",\n            \"use_cases\": \"Intended use cases\",\n            \"caveats\": \"Additional caveats\"\n        }\n```\n\n### Accountability\n```python\nclass AIAccountability:\n    \"\"\"Ensure AI system accountability\"\"\"\n    \n    def __init__(self):\n        self.audit_trail = []\n    \n    def log_decision(self, decision_id: str, input_data: Dict,\n                    prediction: Any, model_version: str,\n                    user_id: str = None):\n        \"\"\"Log AI decision for accountability\"\"\"\n        entry = {\n            \"decision_id\": decision_id,\n            \"timestamp\": datetime.now().isoformat(),\n            \"input_data_hash\": hash(str(input_data)),\n            \"prediction\": prediction,\n            \"model_version\": model_version,\n            \"user_id\": user_id,\n            \"ip_address\": get_client_ip()\n        }\n        \n        self.audit_trail.append(entry)\n        self._write_to_immutable_store(entry)\n    \n    def generate_audit_report(self, start_date: datetime,\n                             end_date: datetime) -> Dict:\n        \"\"\"Generate audit report for date range\"\"\"\n        relevant_entries = [\n            e for e in self.audit_trail\n            if start_date \u003C= e[\"timestamp\"] \u003C= end_date\n        ]\n        \n        return {\n            \"total_decisions\": len(relevant_entries),\n            \"unique_users\": len(set(e[\"user_id\"] for e in relevant_entries)),\n            \"model_versions\": set(e[\"model_version\"] for e in relevant_entries),\n            \"predictions_by_outcome\": self._count_outcomes(relevant_entries)\n        }\n    \n    def implement_human_oversight(self, prediction: Any,\n                                 threshold: float = 0.8) -> Dict:\n        \"\"\"Determine if human review is needed\"\"\"\n        confidence = prediction.get(\"confidence\", 1.0)\n        \n        return {\n            \"requires_human_review\": confidence \u003C threshold,\n            \"confidence\": confidence,\n            \"threshold\": threshold,\n            \"review_reason\": \"Low confidence\" if confidence \u003C threshold else None\n        }\n```\n\n### Privacy Protection\n```python\nclass PrivacyProtection:\n    \"\"\"Privacy-preserving ML techniques\"\"\"\n    \n    def apply_differential_privacy(self, gradients: np.ndarray,\n                                   epsilon: float = 1.0) -> np.ndarray:\n        \"\"\"Add noise for differential privacy\"\"\"\n        sensitivity = np.max(np.linalg.norm(gradients, axis=1))\n        noise = np.random.laplace(0, sensitivity \u002F epsilon, gradients.shape)\n        return gradients + noise\n    \n    def anonymize_data(self, data: pd.DataFrame,\n                      quasi_identifiers: List[str],\n                      sensitive_attributes: List[str]) -> pd.DataFrame:\n        \"\"\"Apply k-anonymity\"\"\"\n        # Generalize quasi-identifiers\n        for col in quasi_identifiers:\n            data[col] = self._generalize(data[col], col)\n        \n        return data\n    \n    def _generalize(self, series, col_name):\n        \"\"\"Generalize values for k-anonymity\"\"\"\n        if col_name == \"age\":\n            return pd.cut(series, bins=[0, 18, 30, 45, 60, 100], \n                        labels=[\"0-17\", \"18-29\", \"30-44\", \"45-59\", \"60+\"])\n        return series\n```\n","## What I do\n- Identify ethical issues in AI systems\n- Ensure fairness and bias mitigation\n- Implement transparency and explainability\n- Design for accountability\n- Protect privacy in ML systems\n\n## When to use me\nWhen building AI\u002FML systems that make decisions affecting people.\n\n## Ethical AI Framework\n\n### Fairness\n```python\nfrom typing import List, Dict\nimport numpy as np\n\nclass FairnessAuditor:\n    \"\"\"Audit AI systems for fairness\"\"\"\n    \n    def __init__(self):\n        self.protected_attributes = [\"race\", \"gender\", \"age\", \n                                      \"disability\", \"religion\"]\n    \n    def calculate_disparate_impact(self, predictions: np.ndarray,\n                                   sensitive_attr: np.ndarray,\n                                   threshold: float = 0.8) -> Dict:\n        \"\"\"Calculate disparate impact ratio\"\"\"\n        groups = np.unique(sensitive_attr)\n        \n        if len(groups) \u003C 2:\n            return {\"error\": \"Need multiple groups\"}\n        \n        positive_rates = {}\n        for group in groups:\n            mask = sensitive_attr == group\n            positive_rates[group] = predictions[mask].mean()\n        \n        # Calculate impact ratio\n        reference_rate = positive_rates[groups[0]]\n        ratios = {}\n        \n        for group, rate in positive_rates.items():\n            if reference_rate > 0:\n                ratios[group] = rate \u002F reference_rate\n        \n        return {\n            \"positive_rates\": positive_rates,\n            \"ratios\": ratios,\n            \"fails_disparate_impact\": any(r \u003C threshold for r in ratios.values())\n        }\n    \n    def calculate_equalized_odds(self, predictions: np.ndarray,\n                               labels: np.ndarray,\n                               sensitive_attr: np.ndarray) -> Dict:\n        \"\"\"Check equalized odds (true positive rate equality)\"\"\"\n        groups = np.unique(sensitive_attr)\n        \n        tpr_by_group = {}\n        fpr_by_group = {}\n        \n        for group in groups:\n            mask = sensitive_attr == group\n            tp = ((predictions == 1) & (labels == 1) & mask).sum()\n            fp = ((predictions == 1) & (labels == 0) & mask).sum()\n            tn = ((predictions == 0) & (labels == 0) & mask).sum()\n            fn = ((predictions == 0) & (labels == 1) & mask).sum()\n            \n            tpr_by_group[group] = tp \u002F (tp + fn) if (tp + fn) > 0 else 0\n            fpr_by_group[group] = fp \u002F (fp + tn) if (fp + tn) > 0 else 0\n        \n        return {\n            \"true_positive_rates\": tpr_by_group,\n            \"false_positive_rates\": fpr_by_group,\n            \"equalized\": self._check_equalized(tpr_by_group, fpr_by_group)\n        }\n    \n    def mitigate_bias(self, model, X: np.ndarray, \n                     sensitive_attr: np.ndarray,\n                     method: str = \"reweighting\") -> np.ndarray:\n        \"\"\"Apply bias mitigation technique\"\"\"\n        if method == \"reweighting\":\n            return self._reweighting_mitigation(X, sensitive_attr)\n        elif method == \"threshold\":\n            return self._threshold_adjustment(X, sensitive_attr)\n        else:\n            raise ValueError(f\"Unknown method: {method}\")\n    \n    def _reweighting_mitigation(self, X, sensitive_attr) -> np.ndarray:\n        \"\"\"Reweighting-based fairness intervention\"\"\"\n        # Compute weights to equalize outcomes\n        return X  # Simplified\n```\n\n### Transparency and Explainability\n```python\nclass ModelExplainer:\n    \"\"\"Explain model predictions\"\"\"\n    \n    def __init__(self, model):\n        self.model = model\n    \n    def explain_prediction(self, instance: np.ndarray,\n                          method: str = \"shap\") -> Dict:\n        \"\"\"Explain individual prediction\"\"\"\n        if method == \"shap\":\n            return self._shap_explanation(instance)\n        elif method == \"lime\":\n            return self._lime_explanation(instance)\n        elif method == \"feature_importance\":\n            return self._feature_importance_explanation(instance)\n    \n    def _feature_importance_explanation(self, instance: np.ndarray) -> Dict:\n        \"\"\"Global feature importance explanation\"\"\"\n        if hasattr(self.model, \"feature_importances_\"):\n            importances = self.model.feature_importances_\n            return {\n                \"method\": \"feature_importance\",\n                \"importances\": importances.tolist(),\n                \"top_features\": np.argsort(importances)[-5:][::-1].tolist()\n            }\n        return {\"error\": \"Model does not support feature importance\"}\n    \n    def generate_model_cards(self, model, training_data: Dict,\n                            performance: Dict) -> Dict:\n        \"\"\"Generate model documentation (model card)\"\"\"\n        return {\n            \"model_name\": model.__class__.__name__,\n            \"overview\": \"Description of model purpose\",\n            \"owner\": \"Team responsible\",\n            \"training_data\": {\n                \"dataset\": training_data.get(\"name\"),\n                \"size\": training_data.get(\"size\"),\n                \"sources\": training_data.get(\"sources\")\n            },\n            \"performance\": {\n                \"metrics\": performance.get(\"metrics\"),\n                \"evaluation_data\": performance.get(\"test_size\")\n            },\n            \"fairness\": {\n                \"evaluated_groups\": [],\n                \"known_biases\": []\n            },\n            \"limitations\": \"Known model limitations\",\n            \"use_cases\": \"Intended use cases\",\n            \"caveats\": \"Additional caveats\"\n        }\n```\n\n### Accountability\n```python\nclass AIAccountability:\n    \"\"\"Ensure AI system accountability\"\"\"\n    \n    def __init__(self):\n        self.audit_trail = []\n    \n    def log_decision(self, decision_id: str, input_data: Dict,\n                    prediction: Any, model_version: str,\n                    user_id: str = None):\n        \"\"\"Log AI decision for accountability\"\"\"\n        entry = {\n            \"decision_id\": decision_id,\n            \"timestamp\": datetime.now().isoformat(),\n            \"input_data_hash\": hash(str(input_data)),\n            \"prediction\": prediction,\n            \"model_version\": model_version,\n            \"user_id\": user_id,\n            \"ip_address\": get_client_ip()\n        }\n        \n        self.audit_trail.append(entry)\n        self._write_to_immutable_store(entry)\n    \n    def generate_audit_report(self, start_date: datetime,\n                             end_date: datetime) -> Dict:\n        \"\"\"Generate audit report for date range\"\"\"\n        relevant_entries = [\n            e for e in self.audit_trail\n            if start_date \u003C= e[\"timestamp\"] \u003C= end_date\n        ]\n        \n        return {\n            \"total_decisions\": len(relevant_entries),\n            \"unique_users\": len(set(e[\"user_id\"] for e in relevant_entries)),\n            \"model_versions\": set(e[\"model_version\"] for e in relevant_entries),\n            \"predictions_by_outcome\": self._count_outcomes(relevant_entries)\n        }\n    \n    def implement_human_oversight(self, prediction: Any,\n                                 threshold: float = 0.8) -> Dict:\n        \"\"\"Determine if human review is needed\"\"\"\n        confidence = prediction.get(\"confidence\", 1.0)\n        \n        return {\n            \"requires_human_review\": confidence \u003C threshold,\n            \"confidence\": confidence,\n            \"threshold\": threshold,\n            \"review_reason\": \"Low confidence\" if confidence \u003C threshold else None\n        }\n```\n\n### Privacy Protection\n```python\nclass PrivacyProtection:\n    \"\"\"Privacy-preserving ML techniques\"\"\"\n    \n    def apply_differential_privacy(self, gradients: np.ndarray,\n                                   epsilon: float = 1.0) -> np.ndarray:\n        \"\"\"Add noise for differential privacy\"\"\"\n        sensitivity = np.max(np.linalg.norm(gradients, axis=1))\n        noise = np.random.laplace(0, sensitivity \u002F epsilon, gradients.shape)\n        return gradients + noise\n    \n    def anonymize_data(self, data: pd.DataFrame,\n                      quasi_identifiers: List[str],\n                      sensitive_attributes: List[str]) -> pd.DataFrame:\n        \"\"\"Apply k-anonymity\"\"\"\n        # Generalize quasi-identifiers\n        for col in quasi_identifiers:\n            data[col] = self._generalize(data[col], col)\n        \n        return data\n    \n    def _generalize(self, series, col_name):\n        \"\"\"Generalize values for k-anonymity\"\"\"\n        if col_name == \"age\":\n            return pd.cut(series, bins=[0, 18, 30, 45, 60, 100], \n                        labels=[\"0-17\", \"18-29\", \"30-44\", \"45-59\", \"60+\"])\n        return series\n```\n",{"name":5,"license":14,"metadata":27,"description":7,"compatibility":20},{"audience":28,"category":18},"developers","main","5f7a3e453c98261f93d19a6a7de44ad8f7b72d41",2,"https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk","2026-03-01 06:55:40",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add ffsshhttiikk\u002Fopencode-agents-skills --skill ai-ethics",{"tool":41,"command":42},"bunx","bunx skills add ffsshhttiikk\u002Fopencode-agents-skills --skill ai-ethics",{"tool":44,"command":45},"pnpm","pnpm dlx skills add ffsshhttiikk\u002Fopencode-agents-skills --skill ai-ethics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fai-ethics\u002FSKILL.md",true,[49,55,59,63,69,73,77,81,85,89,93,97,101,105,109,113,117,121,125,129,133,137,141,145,149,153,157,161,165,169,173,177,181,185,189,193,197],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"BestPractices.md","REFERENCE","参考文档",1541,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FBestPractices.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"CLIReference.md",2267,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FCLIReference.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"Data\u002FDomainPatterns.yaml",4631,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FData\u002FDomainPatterns.yaml",{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"Graders\u002FBase.ts","SCRIPT","脚本",3016,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FGraders\u002FBase.ts",{"path":70,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":71,"sourceHtmlUrl":72},"Graders\u002FCodeBased\u002FBinaryTests.ts",2544,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FGraders\u002FCodeBased\u002FBinaryTests.ts",{"path":74,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":75,"sourceHtmlUrl":76},"Graders\u002FCodeBased\u002Findex.ts",615,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FGraders\u002FCodeBased\u002Findex.ts",{"path":78,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":79,"sourceHtmlUrl":80},"Graders\u002FCodeBased\u002FRegexMatch.ts",1952,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FGraders\u002FCodeBased\u002FRegexMatch.ts",{"path":82,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":83,"sourceHtmlUrl":84},"Graders\u002FCodeBased\u002FStateCheck.ts",4855,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FGraders\u002FCodeBased\u002FStateCheck.ts",{"path":86,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":87,"sourceHtmlUrl":88},"Graders\u002FCodeBased\u002FStaticAnalysis.ts",2966,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FGraders\u002FCodeBased\u002FStaticAnalysis.ts",{"path":90,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":91,"sourceHtmlUrl":92},"Graders\u002FCodeBased\u002FStringMatch.ts",1690,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FGraders\u002FCodeBased\u002FStringMatch.ts",{"path":94,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":95,"sourceHtmlUrl":96},"Graders\u002FCodeBased\u002FToolCallVerification.ts",3712,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FGraders\u002FCodeBased\u002FToolCallVerification.ts",{"path":98,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":99,"sourceHtmlUrl":100},"Graders\u002Findex.ts",322,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FGraders\u002Findex.ts",{"path":102,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":103,"sourceHtmlUrl":104},"Graders\u002FModelBased\u002Findex.ts",403,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FGraders\u002FModelBased\u002Findex.ts",{"path":106,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":107,"sourceHtmlUrl":108},"Graders\u002FModelBased\u002FLLMRubric.ts",5446,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FGraders\u002FModelBased\u002FLLMRubric.ts",{"path":110,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":111,"sourceHtmlUrl":112},"Graders\u002FModelBased\u002FNaturalLanguageAssert.ts",3842,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FGraders\u002FModelBased\u002FNaturalLanguageAssert.ts",{"path":114,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":115,"sourceHtmlUrl":116},"Graders\u002FModelBased\u002FPairwiseComparison.ts",4937,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FGraders\u002FModelBased\u002FPairwiseComparison.ts",{"path":118,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":119,"sourceHtmlUrl":120},"PROJECT.md",21452,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FPROJECT.md",{"path":122,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":123,"sourceHtmlUrl":124},"ScienceMapping.md",1998,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FScienceMapping.md",{"path":126,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":127,"sourceHtmlUrl":128},"ScorerTypes.md",1751,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FScorerTypes.md",{"path":130,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":131,"sourceHtmlUrl":132},"Suites\u002FRegression\u002Fcore-behaviors.yaml",428,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FSuites\u002FRegression\u002Fcore-behaviors.yaml",{"path":134,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":135,"sourceHtmlUrl":136},"TemplateIntegration.md",1772,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FTemplateIntegration.md",{"path":138,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":139,"sourceHtmlUrl":140},"Tools\u002FAlgorithmBridge.ts",7010,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FTools\u002FAlgorithmBridge.ts",{"path":142,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":143,"sourceHtmlUrl":144},"Tools\u002FFailureToTask.ts",10639,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FTools\u002FFailureToTask.ts",{"path":146,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":147,"sourceHtmlUrl":148},"Tools\u002FSuiteManager.ts",11417,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FTools\u002FSuiteManager.ts",{"path":150,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":151,"sourceHtmlUrl":152},"Tools\u002FTranscriptCapture.ts",6064,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FTools\u002FTranscriptCapture.ts",{"path":154,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":155,"sourceHtmlUrl":156},"Tools\u002FTrialRunner.ts",8374,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FTools\u002FTrialRunner.ts",{"path":158,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":159,"sourceHtmlUrl":160},"Types\u002Findex.ts",9235,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FTypes\u002Findex.ts",{"path":162,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":163,"sourceHtmlUrl":164},"UseCases\u002FRegression\u002Ftask_file_targeting_basic.yaml",1238,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FUseCases\u002FRegression\u002Ftask_file_targeting_basic.yaml",{"path":166,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":167,"sourceHtmlUrl":168},"UseCases\u002FRegression\u002Ftask_no_hallucinated_paths.yaml",1312,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FUseCases\u002FRegression\u002Ftask_no_hallucinated_paths.yaml",{"path":170,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":171,"sourceHtmlUrl":172},"UseCases\u002FRegression\u002Ftask_tool_sequence_read_before_edit.yaml",1338,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FUseCases\u002FRegression\u002Ftask_tool_sequence_read_before_edit.yaml",{"path":174,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":175,"sourceHtmlUrl":176},"UseCases\u002FRegression\u002Ftask_verification_before_done.yaml",1348,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FUseCases\u002FRegression\u002Ftask_verification_before_done.yaml",{"path":178,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":179,"sourceHtmlUrl":180},"Workflows\u002FCompareModels.md",7285,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FWorkflows\u002FCompareModels.md",{"path":182,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":183,"sourceHtmlUrl":184},"Workflows\u002FComparePrompts.md",8927,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FWorkflows\u002FComparePrompts.md",{"path":186,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":187,"sourceHtmlUrl":188},"Workflows\u002FCreateJudge.md",4654,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FWorkflows\u002FCreateJudge.md",{"path":190,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":191,"sourceHtmlUrl":192},"Workflows\u002FCreateUseCase.md",6529,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FWorkflows\u002FCreateUseCase.md",{"path":194,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":195,"sourceHtmlUrl":196},"Workflows\u002FRunEval.md",2339,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FWorkflows\u002FRunEval.md",{"path":198,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":199,"sourceHtmlUrl":200},"Workflows\u002FViewResults.md",7618,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002FPersonal_AI_Infrastructure\u002FReleases\u002Fv4.0.3\u002F.claude\u002Fskills\u002FUtilities\u002FEvals\u002FWorkflows\u002FViewResults.md",[202,213,223,232,242,251],{"skillNo":203,"name":204,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":208,"publishedAt":22},"01M6CXT9TXDF79BWJTMQAPB49G","xamarin","Xamarin cross-platform development","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fxamarin\u002FSKILL.md",[],[204,209,210,211,20,212],"platform","cross-platform","mobile","development",{"skillNo":214,"name":215,"nameZh":6,"description":216,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":217,"categories":218,"keywords":219,"publishedAt":22},"01M6CXT8AD04MFYDA32VW3FKAG","wrangling","Data wrangling fundamentals","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwrangling\u002FSKILL.md",[],[215,220,20,221,222],"data wrangling","science","data",{"skillNo":224,"name":225,"nameZh":6,"description":226,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":227,"categories":228,"keywords":229,"publishedAt":22},"01M6CXT717GCN7SRRNPBDP4508","windows","Windows operating system administration and scripting","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwindows\u002FSKILL.md",[],[225,230,20,231],"system","scripting",{"skillNo":233,"name":234,"nameZh":6,"description":235,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":236,"categories":237,"keywords":238,"publishedAt":22},"01M6CXT54K794NMEM3XAPZZDKT","wide-column","Wide-column data model","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwide-column\u002FSKILL.md",[],[239,240,20,241,222],"wide column","databases","model",{"skillNo":243,"name":244,"nameZh":6,"description":245,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":246,"categories":247,"keywords":248,"publishedAt":22},"01M6CXT28FMT2P4V9GZE67WA8E","wide-column-stores","Wide-column database stores","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwide-column-stores\u002FSKILL.md",[],[249,240,20,250],"wide column stores","database",{"skillNo":252,"name":253,"nameZh":6,"description":254,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":255,"categories":256,"keywords":257,"publishedAt":22},"01M6CXT0D0M0Q4T2N7C2RX7DSN","websockets","WebSocket implementation and best practices","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwebsockets\u002FSKILL.md",[],[253,258,259,260,20,261,21],"websocket","real-time","time","best practices"]