[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FJN6B3WH18RS3NRSWHF263":3,"skill-same:01M6FJN6B3WH18RS3NRSWHF263":64},{"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":22,"publishedAt":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M6FJN6B3WH18RS3NRSWHF263","csv-handler",null,"Handle CSV files from construction software exports. Auto-detect delimiters, encodings, and clean messy data.","kbarbel640-del\u002Fskills","kbarbel640-del","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F255315490?v=4","01M6CJPPQGCCESXMG3K7BBGQ5J","01M6CJPPX2PB2BCZERFVM2C2B3",1,"MIT","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdatadrivenconstruction\u002Fcsv-handler\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000004","电子表格","SCENARIO","使用场景",[23,24,25,26,27,28,29,30],"csv","csv handler","data","auto","files","clean","software","detect","2026-11-10 10:12:30",false,"---\r\nslug: \"csv-handler\"\r\ndisplay_name: \"CSV Handler\"\r\ndescription: \"Handle CSV files from construction software exports. Auto-detect delimiters, encodings, and clean messy data.\"\r\n---\r\n\r\n# CSV Handler for Construction Data\r\n\r\n## Overview\r\nCSV is the universal exchange format in construction - from scheduling exports to cost databases. This skill handles encoding issues, delimiter detection, and data cleaning.\r\n\r\n## Python Implementation\r\n\r\n```python\r\nimport pandas as pd\r\nimport csv\r\nfrom typing import Dict, Any, List, Optional, Tuple\r\nfrom pathlib import Path\r\nfrom dataclasses import dataclass\r\nimport chardet\r\n\r\n\r\n@dataclass\r\nclass CSVProfile:\r\n    \"\"\"Profile of CSV file.\"\"\"\r\n    encoding: str\r\n    delimiter: str\r\n    has_header: bool\r\n    row_count: int\r\n    column_count: int\r\n    columns: List[str]\r\n\r\n\r\nclass ConstructionCSVHandler:\r\n    \"\"\"Handle CSV files from construction software.\"\"\"\r\n\r\n    COMMON_DELIMITERS = [',', ';', '\\t', '|']\r\n    COMMON_ENCODINGS = ['utf-8', 'utf-8-sig', 'latin-1', 'cp1252', 'iso-8859-1']\r\n\r\n    def __init__(self):\r\n        self.last_profile: Optional[CSVProfile] = None\r\n\r\n    def detect_encoding(self, file_path: str) -> str:\r\n        \"\"\"Detect file encoding.\"\"\"\r\n        with open(file_path, 'rb') as f:\r\n            raw = f.read(10000)\r\n        result = chardet.detect(raw)\r\n        return result.get('encoding', 'utf-8') or 'utf-8'\r\n\r\n    def detect_delimiter(self, file_path: str, encoding: str) -> str:\r\n        \"\"\"Detect CSV delimiter.\"\"\"\r\n        with open(file_path, 'r', encoding=encoding, errors='replace') as f:\r\n            sample = f.read(5000)\r\n\r\n        # Count occurrences\r\n        counts = {d: sample.count(d) for d in self.COMMON_DELIMITERS}\r\n\r\n        # Return most common that appears consistently\r\n        if counts:\r\n            return max(counts, key=counts.get)\r\n        return ','\r\n\r\n    def profile_csv(self, file_path: str) -> CSVProfile:\r\n        \"\"\"Profile CSV file.\"\"\"\r\n        encoding = self.detect_encoding(file_path)\r\n        delimiter = self.detect_delimiter(file_path, encoding)\r\n\r\n        # Read sample\r\n        df = pd.read_csv(file_path, encoding=encoding, delimiter=delimiter,\r\n                         nrows=10, on_bad_lines='skip')\r\n\r\n        has_header = not df.columns[0].replace('.', '').replace('-', '').isdigit()\r\n\r\n        # Full row count\r\n        with open(file_path, 'r', encoding=encoding, errors='replace') as f:\r\n            row_count = sum(1 for _ in f) - (1 if has_header else 0)\r\n\r\n        profile = CSVProfile(\r\n            encoding=encoding,\r\n            delimiter=delimiter,\r\n            has_header=has_header,\r\n            row_count=row_count,\r\n            column_count=len(df.columns),\r\n            columns=list(df.columns)\r\n        )\r\n        self.last_profile = profile\r\n        return profile\r\n\r\n    def read_csv(self, file_path: str,\r\n                 encoding: Optional[str] = None,\r\n                 delimiter: Optional[str] = None,\r\n                 clean: bool = True) -> pd.DataFrame:\r\n        \"\"\"Read CSV with auto-detection.\"\"\"\r\n\r\n        # Auto-detect if not provided\r\n        if encoding is None:\r\n            encoding = self.detect_encoding(file_path)\r\n        if delimiter is None:\r\n            delimiter = self.detect_delimiter(file_path, encoding)\r\n\r\n        # Read with error handling\r\n        df = pd.read_csv(\r\n            file_path,\r\n            encoding=encoding,\r\n            delimiter=delimiter,\r\n            on_bad_lines='skip',\r\n            low_memory=False\r\n        )\r\n\r\n        if clean:\r\n            df = self.clean_dataframe(df)\r\n\r\n        return df\r\n\r\n    def clean_dataframe(self, df: pd.DataFrame) -> pd.DataFrame:\r\n        \"\"\"Clean construction CSV data.\"\"\"\r\n        # Clean column names\r\n        df.columns = [self._clean_column_name(c) for c in df.columns]\r\n\r\n        # Remove empty rows and columns\r\n        df = df.dropna(how='all')\r\n        df = df.dropna(axis=1, how='all')\r\n\r\n        # Strip whitespace from strings\r\n        for col in df.select_dtypes(include=['object']):\r\n            df[col] = df[col].str.strip() if df[col].dtype == 'object' else df[col]\r\n\r\n        return df\r\n\r\n    def _clean_column_name(self, name: str) -> str:\r\n        \"\"\"Clean column name.\"\"\"\r\n        if not isinstance(name, str):\r\n            return str(name)\r\n\r\n        # Remove special characters, replace spaces\r\n        clean = name.strip().lower()\r\n        clean = clean.replace(' ', '_').replace('-', '_')\r\n        clean = ''.join(c for c in clean if c.isalnum() or c == '_')\r\n        return clean\r\n\r\n    def merge_csvs(self, file_paths: List[str],\r\n                   on_column: Optional[str] = None) -> pd.DataFrame:\r\n        \"\"\"Merge multiple CSV files.\"\"\"\r\n        dfs = []\r\n        for path in file_paths:\r\n            df = self.read_csv(path)\r\n            df['_source_file'] = Path(path).name\r\n            dfs.append(df)\r\n\r\n        if not dfs:\r\n            return pd.DataFrame()\r\n\r\n        if on_column and on_column in dfs[0].columns:\r\n            result = dfs[0]\r\n            for df in dfs[1:]:\r\n                result = pd.merge(result, df, on=on_column, how='outer')\r\n            return result\r\n\r\n        return pd.concat(dfs, ignore_index=True)\r\n\r\n    def split_csv(self, df: pd.DataFrame,\r\n                  group_column: str,\r\n                  output_dir: str) -> List[str]:\r\n        \"\"\"Split CSV by column values.\"\"\"\r\n        output_path = Path(output_dir)\r\n        output_path.mkdir(parents=True, exist_ok=True)\r\n\r\n        files = []\r\n        for value in df[group_column].unique():\r\n            subset = df[df[group_column] == value]\r\n            filename = f\"{group_column}_{value}.csv\"\r\n            filepath = output_path \u002F filename\r\n            subset.to_csv(filepath, index=False)\r\n            files.append(str(filepath))\r\n\r\n        return files\r\n\r\n    def convert_types(self, df: pd.DataFrame,\r\n                      type_map: Dict[str, str] = None) -> pd.DataFrame:\r\n        \"\"\"Convert column types intelligently.\"\"\"\r\n        df = df.copy()\r\n\r\n        if type_map:\r\n            for col, dtype in type_map.items():\r\n                if col in df.columns:\r\n                    try:\r\n                        df[col] = df[col].astype(dtype)\r\n                    except:\r\n                        pass\r\n        else:\r\n            # Auto-convert\r\n            for col in df.columns:\r\n                # Try numeric\r\n                try:\r\n                    df[col] = pd.to_numeric(df[col])\r\n                    continue\r\n                except:\r\n                    pass\r\n\r\n                # Try datetime\r\n                try:\r\n                    df[col] = pd.to_datetime(df[col])\r\n                except:\r\n                    pass\r\n\r\n        return df\r\n\r\n    def export_csv(self, df: pd.DataFrame,\r\n                   file_path: str,\r\n                   encoding: str = 'utf-8-sig',\r\n                   delimiter: str = ',') -> str:\r\n        \"\"\"Export DataFrame to CSV.\"\"\"\r\n        df.to_csv(file_path, encoding=encoding, sep=delimiter, index=False)\r\n        return file_path\r\n\r\n\r\n# Specialized handlers\r\nclass ScheduleCSVHandler(ConstructionCSVHandler):\r\n    \"\"\"Handler for project schedule CSVs.\"\"\"\r\n\r\n    SCHEDULE_COLUMNS = ['task_id', 'task_name', 'start_date', 'end_date',\r\n                        'duration', 'predecessors', 'resources']\r\n\r\n    def parse_schedule(self, file_path: str) -> pd.DataFrame:\r\n        \"\"\"Parse schedule CSV.\"\"\"\r\n        df = self.read_csv(file_path)\r\n\r\n        # Convert date columns\r\n        for col in df.columns:\r\n            if 'date' in col.lower() or 'start' in col.lower() or 'end' in col.lower():\r\n                try:\r\n                    df[col] = pd.to_datetime(df[col])\r\n                except:\r\n                    pass\r\n\r\n        return df\r\n\r\n\r\nclass CostCSVHandler(ConstructionCSVHandler):\r\n    \"\"\"Handler for cost\u002Festimate CSVs.\"\"\"\r\n\r\n    def parse_costs(self, file_path: str) -> pd.DataFrame:\r\n        \"\"\"Parse cost CSV.\"\"\"\r\n        df = self.read_csv(file_path)\r\n\r\n        # Find and convert numeric columns\r\n        for col in df.columns:\r\n            if any(word in col.lower() for word in ['cost', 'price', 'amount', 'total', 'qty', 'quantity']):\r\n                df[col] = pd.to_numeric(df[col].replace(r'[\\$,]', '', regex=True), errors='coerce')\r\n\r\n        return df\r\n```\r\n\r\n## Quick Start\r\n\r\n```python\r\nhandler = ConstructionCSVHandler()\r\n\r\n# Profile CSV first\r\nprofile = handler.profile_csv(\"export.csv\")\r\nprint(f\"Encoding: {profile.encoding}, Delimiter: '{profile.delimiter}'\")\r\n\r\n# Read with auto-detection\r\ndf = handler.read_csv(\"export.csv\")\r\nprint(f\"Loaded {len(df)} rows, {len(df.columns)} columns\")\r\n```\r\n\r\n## Common Use Cases\r\n\r\n### 1. Merge Multiple Exports\r\n```python\r\nfiles = [\"jan_export.csv\", \"feb_export.csv\", \"mar_export.csv\"]\r\nmerged = handler.merge_csvs(files)\r\n```\r\n\r\n### 2. Split by Category\r\n```python\r\nhandler.split_csv(df, group_column='category', output_dir='.\u002Fsplit_files')\r\n```\r\n\r\n### 3. Schedule Import\r\n```python\r\nschedule_handler = ScheduleCSVHandler()\r\nschedule = schedule_handler.parse_schedule(\"p6_export.csv\")\r\n```\r\n\r\n## Resources\r\n- **DDC Book**: Chapter 2.1 - Structured Data\r\n","# CSV Handler for Construction Data\r\n\r\n## Overview\r\nCSV is the universal exchange format in construction - from scheduling exports to cost databases. This skill handles encoding issues, delimiter detection, and data cleaning.\r\n\r\n## Python Implementation\r\n\r\n```python\r\nimport pandas as pd\r\nimport csv\r\nfrom typing import Dict, Any, List, Optional, Tuple\r\nfrom pathlib import Path\r\nfrom dataclasses import dataclass\r\nimport chardet\r\n\r\n\r\n@dataclass\r\nclass CSVProfile:\r\n    \"\"\"Profile of CSV file.\"\"\"\r\n    encoding: str\r\n    delimiter: str\r\n    has_header: bool\r\n    row_count: int\r\n    column_count: int\r\n    columns: List[str]\r\n\r\n\r\nclass ConstructionCSVHandler:\r\n    \"\"\"Handle CSV files from construction software.\"\"\"\r\n\r\n    COMMON_DELIMITERS = [',', ';', '\\t', '|']\r\n    COMMON_ENCODINGS = ['utf-8', 'utf-8-sig', 'latin-1', 'cp1252', 'iso-8859-1']\r\n\r\n    def __init__(self):\r\n        self.last_profile: Optional[CSVProfile] = None\r\n\r\n    def detect_encoding(self, file_path: str) -> str:\r\n        \"\"\"Detect file encoding.\"\"\"\r\n        with open(file_path, 'rb') as f:\r\n            raw = f.read(10000)\r\n        result = chardet.detect(raw)\r\n        return result.get('encoding', 'utf-8') or 'utf-8'\r\n\r\n    def detect_delimiter(self, file_path: str, encoding: str) -> str:\r\n        \"\"\"Detect CSV delimiter.\"\"\"\r\n        with open(file_path, 'r', encoding=encoding, errors='replace') as f:\r\n            sample = f.read(5000)\r\n\r\n        # Count occurrences\r\n        counts = {d: sample.count(d) for d in self.COMMON_DELIMITERS}\r\n\r\n        # Return most common that appears consistently\r\n        if counts:\r\n            return max(counts, key=counts.get)\r\n        return ','\r\n\r\n    def profile_csv(self, file_path: str) -> CSVProfile:\r\n        \"\"\"Profile CSV file.\"\"\"\r\n        encoding = self.detect_encoding(file_path)\r\n        delimiter = self.detect_delimiter(file_path, encoding)\r\n\r\n        # Read sample\r\n        df = pd.read_csv(file_path, encoding=encoding, delimiter=delimiter,\r\n                         nrows=10, on_bad_lines='skip')\r\n\r\n        has_header = not df.columns[0].replace('.', '').replace('-', '').isdigit()\r\n\r\n        # Full row count\r\n        with open(file_path, 'r', encoding=encoding, errors='replace') as f:\r\n            row_count = sum(1 for _ in f) - (1 if has_header else 0)\r\n\r\n        profile = CSVProfile(\r\n            encoding=encoding,\r\n            delimiter=delimiter,\r\n            has_header=has_header,\r\n            row_count=row_count,\r\n            column_count=len(df.columns),\r\n            columns=list(df.columns)\r\n        )\r\n        self.last_profile = profile\r\n        return profile\r\n\r\n    def read_csv(self, file_path: str,\r\n                 encoding: Optional[str] = None,\r\n                 delimiter: Optional[str] = None,\r\n                 clean: bool = True) -> pd.DataFrame:\r\n        \"\"\"Read CSV with auto-detection.\"\"\"\r\n\r\n        # Auto-detect if not provided\r\n        if encoding is None:\r\n            encoding = self.detect_encoding(file_path)\r\n        if delimiter is None:\r\n            delimiter = self.detect_delimiter(file_path, encoding)\r\n\r\n        # Read with error handling\r\n        df = pd.read_csv(\r\n            file_path,\r\n            encoding=encoding,\r\n            delimiter=delimiter,\r\n            on_bad_lines='skip',\r\n            low_memory=False\r\n        )\r\n\r\n        if clean:\r\n            df = self.clean_dataframe(df)\r\n\r\n        return df\r\n\r\n    def clean_dataframe(self, df: pd.DataFrame) -> pd.DataFrame:\r\n        \"\"\"Clean construction CSV data.\"\"\"\r\n        # Clean column names\r\n        df.columns = [self._clean_column_name(c) for c in df.columns]\r\n\r\n        # Remove empty rows and columns\r\n        df = df.dropna(how='all')\r\n        df = df.dropna(axis=1, how='all')\r\n\r\n        # Strip whitespace from strings\r\n        for col in df.select_dtypes(include=['object']):\r\n            df[col] = df[col].str.strip() if df[col].dtype == 'object' else df[col]\r\n\r\n        return df\r\n\r\n    def _clean_column_name(self, name: str) -> str:\r\n        \"\"\"Clean column name.\"\"\"\r\n        if not isinstance(name, str):\r\n            return str(name)\r\n\r\n        # Remove special characters, replace spaces\r\n        clean = name.strip().lower()\r\n        clean = clean.replace(' ', '_').replace('-', '_')\r\n        clean = ''.join(c for c in clean if c.isalnum() or c == '_')\r\n        return clean\r\n\r\n    def merge_csvs(self, file_paths: List[str],\r\n                   on_column: Optional[str] = None) -> pd.DataFrame:\r\n        \"\"\"Merge multiple CSV files.\"\"\"\r\n        dfs = []\r\n        for path in file_paths:\r\n            df = self.read_csv(path)\r\n            df['_source_file'] = Path(path).name\r\n            dfs.append(df)\r\n\r\n        if not dfs:\r\n            return pd.DataFrame()\r\n\r\n        if on_column and on_column in dfs[0].columns:\r\n            result = dfs[0]\r\n            for df in dfs[1:]:\r\n                result = pd.merge(result, df, on=on_column, how='outer')\r\n            return result\r\n\r\n        return pd.concat(dfs, ignore_index=True)\r\n\r\n    def split_csv(self, df: pd.DataFrame,\r\n                  group_column: str,\r\n                  output_dir: str) -> List[str]:\r\n        \"\"\"Split CSV by column values.\"\"\"\r\n        output_path = Path(output_dir)\r\n        output_path.mkdir(parents=True, exist_ok=True)\r\n\r\n        files = []\r\n        for value in df[group_column].unique():\r\n            subset = df[df[group_column] == value]\r\n            filename = f\"{group_column}_{value}.csv\"\r\n            filepath = output_path \u002F filename\r\n            subset.to_csv(filepath, index=False)\r\n            files.append(str(filepath))\r\n\r\n        return files\r\n\r\n    def convert_types(self, df: pd.DataFrame,\r\n                      type_map: Dict[str, str] = None) -> pd.DataFrame:\r\n        \"\"\"Convert column types intelligently.\"\"\"\r\n        df = df.copy()\r\n\r\n        if type_map:\r\n            for col, dtype in type_map.items():\r\n                if col in df.columns:\r\n                    try:\r\n                        df[col] = df[col].astype(dtype)\r\n                    except:\r\n                        pass\r\n        else:\r\n            # Auto-convert\r\n            for col in df.columns:\r\n                # Try numeric\r\n                try:\r\n                    df[col] = pd.to_numeric(df[col])\r\n                    continue\r\n                except:\r\n                    pass\r\n\r\n                # Try datetime\r\n                try:\r\n                    df[col] = pd.to_datetime(df[col])\r\n                except:\r\n                    pass\r\n\r\n        return df\r\n\r\n    def export_csv(self, df: pd.DataFrame,\r\n                   file_path: str,\r\n                   encoding: str = 'utf-8-sig',\r\n                   delimiter: str = ',') -> str:\r\n        \"\"\"Export DataFrame to CSV.\"\"\"\r\n        df.to_csv(file_path, encoding=encoding, sep=delimiter, index=False)\r\n        return file_path\r\n\r\n\r\n# Specialized handlers\r\nclass ScheduleCSVHandler(ConstructionCSVHandler):\r\n    \"\"\"Handler for project schedule CSVs.\"\"\"\r\n\r\n    SCHEDULE_COLUMNS = ['task_id', 'task_name', 'start_date', 'end_date',\r\n                        'duration', 'predecessors', 'resources']\r\n\r\n    def parse_schedule(self, file_path: str) -> pd.DataFrame:\r\n        \"\"\"Parse schedule CSV.\"\"\"\r\n        df = self.read_csv(file_path)\r\n\r\n        # Convert date columns\r\n        for col in df.columns:\r\n            if 'date' in col.lower() or 'start' in col.lower() or 'end' in col.lower():\r\n                try:\r\n                    df[col] = pd.to_datetime(df[col])\r\n                except:\r\n                    pass\r\n\r\n        return df\r\n\r\n\r\nclass CostCSVHandler(ConstructionCSVHandler):\r\n    \"\"\"Handler for cost\u002Festimate CSVs.\"\"\"\r\n\r\n    def parse_costs(self, file_path: str) -> pd.DataFrame:\r\n        \"\"\"Parse cost CSV.\"\"\"\r\n        df = self.read_csv(file_path)\r\n\r\n        # Find and convert numeric columns\r\n        for col in df.columns:\r\n            if any(word in col.lower() for word in ['cost', 'price', 'amount', 'total', 'qty', 'quantity']):\r\n                df[col] = pd.to_numeric(df[col].replace(r'[\\$,]', '', regex=True), errors='coerce')\r\n\r\n        return df\r\n```\r\n\r\n## Quick Start\r\n\r\n```python\r\nhandler = ConstructionCSVHandler()\r\n\r\n# Profile CSV first\r\nprofile = handler.profile_csv(\"export.csv\")\r\nprint(f\"Encoding: {profile.encoding}, Delimiter: '{profile.delimiter}'\")\r\n\r\n# Read with auto-detection\r\ndf = handler.read_csv(\"export.csv\")\r\nprint(f\"Loaded {len(df)} rows, {len(df.columns)} columns\")\r\n```\r\n\r\n## Common Use Cases\r\n\r\n### 1. Merge Multiple Exports\r\n```python\r\nfiles = [\"jan_export.csv\", \"feb_export.csv\", \"mar_export.csv\"]\r\nmerged = handler.merge_csvs(files)\r\n```\r\n\r\n### 2. Split by Category\r\n```python\r\nhandler.split_csv(df, group_column='category', output_dir='.\u002Fsplit_files')\r\n```\r\n\r\n### 3. Schedule Import\r\n```python\r\nschedule_handler = ScheduleCSVHandler()\r\nschedule = schedule_handler.parse_schedule(\"p6_export.csv\")\r\n```\r\n\r\n## Resources\r\n- **DDC Book**: Chapter 2.1 - Structured Data\r\n",{"slug":5,"description":7,"display_name":36},"CSV Handler","main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Fdatadrivenconstruction\u002Fcsv-handler",0,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del","2026-08-23 22:39:37",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add kbarbel640-del\u002Fskills --skill csv-handler",{"tool":50,"command":51},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill csv-handler",{"tool":53,"command":54},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill csv-handler","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdatadrivenconstruction\u002Fcsv-handler\u002FSKILL.md",true,[58],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"_meta.json","REFERENCE","参考文档",290,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fdatadrivenconstruction\u002Fcsv-handler\u002F_meta.json",[65,96,123,144,150,170],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":76,"publishedAt":31},"01M6G8J55967D6281ACMKAKTEQ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[71],{"categoryNo":72,"categoryName":73,"taxonomyType":74,"taxonomyTypeDesc":75},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95],"crowd prompting","prompting","api","with","tokens","domain","world","prompts","operations","instructions","text","tool","system","improve","productivity","marketplace","https","content","ai agents",{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":105,"publishedAt":31},"01M6G8J0PKPAYVET6BWE8W4C26","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[102],{"categoryNo":103,"categoryName":104,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[106,79,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,84,122],"dilemm ai","arena","analyze","browser","openclaw agent","create","automation","browser automation","bot","openclaw","design","strategy","headless","compete","submit","matchmaking","use",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":132,"publishedAt":31},"01M6G8HWAF3K9SW7NP3Z83CPJ6","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, and submit comments. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, or submitting paper reviews via API at http:\u002F\u002F150.158.152.82:8000.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Fweak-accept\u002FSKILL.md",[129],{"categoryNo":130,"categoryName":131,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[133,134,135,136,137,138,139,80,140,120,122,141,79,142,143],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","read","http","via",{"skillNo":145,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":149,"publishedAt":31},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[148],{"categoryNo":130,"categoryName":131,"taxonomyType":20,"taxonomyTypeDesc":21},[136,135,134,133,143,138,139,80,137,120,122,140,141,79,142],{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":156,"publishedAt":31},"01M6G8HM95Y64JNVFC2HN4E2BG","git-summary","Get a quick summary of the current Git repository including status, recent commits, branches, and contributors.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzweack\u002Fgit-summary\u002FSKILL.md",[],[157,158,159,160,161,162,163,164,165,166,167,168,169],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","get","branches",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":180,"publishedAt":31},"01M6G8HGEGF05CNEJCGVYFSC4R","agent-constitution","Interact with AgentConstitution governance contracts on Base Sepolia. Check compliance, read rules, log actions, query governance state.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fztsalexey\u002Fagent-constitution\u002FSKILL.md",[176,177],{"categoryNo":103,"categoryName":104,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":178,"categoryName":179,"taxonomyType":74,"taxonomyTypeDesc":75},"01JBSEEDCAT000000000000037","律师与法务",[181,182,183,184,80,185,186,37,187,141,188,189,190,191,192,93,193,194,195],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]