[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718VV3BDHRMY5CC23S8P4PX":3,"skill-same:01M718VV3BDHRMY5CC23S8P4PX":81},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":6,"updatedAt":56,"install":57,"resources":70},"01M718VV3BDHRMY5CC23S8P4PX","oma-pdf",null,"Convert PDF files to Markdown using opendataloader-pdf. Extracts text, tables, headings, lists, and images with correct reading order. Use for PDF parsing, PDF to Markdown conversion, document extraction, and AI-ready data preparation.","vasceannie\u002Fslopgate","vasceannie","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F20271133?v=4","01M718RGA8VV2EF22XJEMXVQ0Q","Travis Vasceannie","01M718RGB0GWSXBBZBN67Q6NHQ",1,"MIT","https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-pdf\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"oma pdf","PDF","with","convert","pdf parsing","document","use","correct","for","parsing","tables","data","pdf to markdown","reading","markdown","text","conversion","files","ready","images","2026-11-10 10:12:30",false,"---\nname: oma-pdf\ndescription: >\n  Convert PDF files to Markdown using opendataloader-pdf. Extracts text, tables, headings,\n  lists, and images with correct reading order. Use for PDF parsing, PDF to Markdown conversion,\n  document extraction, and AI-ready data preparation.\n---\n\n# PDF Skill - PDF to Markdown Conversion\n\n## Scheduling\n\n### Goal\nConvert PDF files into structured Markdown or another requested extraction format while preserving readable document structure for LLM context, RAG, or downstream review.\n\n### Intent signature\n- User asks to convert, parse, read, extract, or transform a PDF.\n- User needs PDF text, headings, lists, tables, or images prepared for AI consumption.\n- User mentions \"PDF to markdown\", \"parse PDF\", \"read this PDF\", or equivalent wording.\n\n### When to use\n- Converting PDF documents to Markdown for LLM context or RAG\n- Extracting structured content such as tables, headings, lists, images, footnotes, or hyperlinks\n- Preparing PDF data for AI consumption\n- Checking whether a PDF has a text layer before choosing OCR\n\n### When NOT to use\n- Generating or creating PDFs -> use document-generation tools\n- Editing existing PDFs -> out of scope\n- Reading an already-text file -> use direct file reading\n- Processing HWP, HWPX, DOCX, XLSX, or slide decks -> use the matching document skill\n\n### Expected inputs\n- `input_path`: PDF file or folder path\n- `output_dir`: optional target directory\n- `format`: optional output format, default `markdown`\n- `ocr_languages`: optional OCR language list for scanned or image-based PDFs\n- `extraction_options`: optional flags for tagged structure, image extraction, or hybrid conversion\n\n### Expected outputs\n- Markdown, text, JSON, HTML, or combined extraction output\n- Normalized Markdown when Markdown is produced\n- A short report with output path, page count, and conversion issues\n\n### Dependencies\n- `uvx opendataloader-pdf` for standard conversion\n- `uvx --from \"opendataloader-pdf[hybrid]\" opendataloader-pdf-hybrid` for OCR or hybrid conversion (the hybrid server is a console script of the `[hybrid]` extra, not a standalone package)\n- `uvx mdformat` for Markdown normalization\n- Local filesystem access to input and output paths\n- Optional OCR runtime via the hybrid server\n\n### Control-flow features\n- Branches on text-layer quality, tagged PDF availability, scan\u002FOCR needs, and user-requested output format\n- Calls external CLI tools through `uvx`\n- Reads local files and writes local extraction outputs\n- Uses a hybrid server only when OCR or complex extraction needs justify it\n\n## Structural Flow\n\n### Entry\n1. Confirm that the input path exists and is a PDF file, PDF folder, or supported batch input.\n2. Check file size and warn when the input is large enough to risk slow conversion or memory pressure.\n3. Resolve `output_dir` and the expected output filename.\n\n### Scenes\n1. **PREPARE**: Validate the input path, output target, and requested extraction options.\n2. **ACQUIRE**: Assess whether the PDF has a readable text layer by extracting a text preview.\n3. **ACT**: Convert using standard mode, tagged-structure mode, or hybrid OCR mode.\n4. **VERIFY**: Run `mdformat` for Markdown output and inspect the result for readable structure.\n5. **FINALIZE**: Report output path, page count, format, and any extraction quality issues.\n\n### Transitions\n- If the preview text is readable, use standard conversion.\n- If the PDF is tagged and standard output is garbled, retry with `--use-struct-tree`.\n- If tables are missing or broken, retry with `--table-method cluster` or `--markdown-with-html` before escalating to hybrid mode.\n- If the PDF is scanned or image-based, start or reuse the hybrid OCR server and convert with hybrid mode.\n- If conversion fails because the PDF is encrypted, stop and ask for the password or an unlocked copy.\n- If conversion hits memory or size limits, process smaller page ranges into distinct output directories (or append `--to-stdout`) so repeated runs do not overwrite the same basename.\n\n### Failure and recovery\n| Failure | Recovery |\n|---------|----------|\n| `uvx` unavailable | Ask user to install `uv` before conversion |\n| `opendataloader-pdf-hybrid` not found | Invoke via `uvx --from \"opendataloader-pdf[hybrid]\" opendataloader-pdf-hybrid`; the bare package name does not exist on PyPI |\n| Password-protected PDF | Ask for password or unlocked PDF |\n| Garbled output | Retry with tagged structure or hybrid mode |\n| Missing tables | Retry with `--table-method cluster` or `--markdown-with-html` first; hybrid mode for scanned tables |\n| OCR language mismatch | Retry with explicit OCR languages, for example `ko,en` |\n| Large file or memory pressure | Split into page ranges using distinct output directories or `--to-stdout`; never reuse one output directory for the same basename |\n\n### Exit\n- Success: output file exists, Markdown is formatted when applicable, and extracted structure is readable.\n- Partial success: output exists but quality issues are reported explicitly.\n- Failure: no reliable output is produced and the blocking cause is reported.\n\n## Logical Operations\n\n### Actions\n| Action | SSL primitive | Evidence |\n|--------|---------------|----------|\n| Validate path and options | `VALIDATE` | Input preflight in execution protocol |\n| Probe text layer | `READ` | Text preview extraction |\n| Choose conversion strategy | `SELECT` | Standard, tagged, or hybrid mode decision |\n| Run converter | `CALL_TOOL` | `uvx opendataloader-pdf` |\n| Start OCR server | `CALL_TOOL` | `uvx --from \"opendataloader-pdf[hybrid]\" opendataloader-pdf-hybrid` |\n| Write output artifact | `WRITE` | Markdown, text, JSON, or HTML output |\n| Normalize Markdown | `CALL_TOOL` | `uvx mdformat` |\n| Inspect extraction quality | `VALIDATE` | Structure\u002Freadability verification |\n| Report result | `NOTIFY` | Final user-facing summary |\n\n### Tools and instruments\n- `opendataloader-pdf`: primary PDF extraction CLI\n- `opendataloader-pdf-hybrid`: hybrid OCR and complex extraction path\n- `mdformat`: Markdown normalization\n- Filesystem commands such as `file`, `wc`, or `pdfinfo` may be used for preflight when available\n\n### Canonical command path\n```bash\nuvx opendataloader-pdf \"{input_path}\" -f text --pages 1-3 --to-stdout -q   # text-layer probe (no temp files)\nuvx opendataloader-pdf \"{input_path}\" --format markdown --output-dir \"{output_dir}\"\nuvx mdformat \"{output_path}\"\n```\n\nFor scanned\u002Fimage-based PDFs, start OCR first and then convert through hybrid mode:\n```bash\nuvx --from \"opendataloader-pdf[hybrid]\" opendataloader-pdf-hybrid --port 5002 --force-ocr --ocr-lang \"{languages}\"\nuvx opendataloader-pdf --hybrid docling-fast --hybrid-mode full \"{input_path}\" --format markdown --output-dir \"{output_dir}\"\n```\n\nOn-request flags — `--sanitize` (PII masking), `--pages` (range extraction), `--threads` (parallel pages), `--detect-strikethrough`, hybrid `--enrich-formula` \u002F `--enrich-picture-description` — are detailed in `resources\u002Fexecution-protocol.md`. The two enrichment flags require client-side `--hybrid-mode full`.\n\n### Resource scope\n| Scope | Resource target |\n|-------|-----------------|\n| `LOCAL_FS` | Input PDFs and generated output files |\n| `PROCESS` | `uvx` subprocesses and optional hybrid server |\n| `MEMORY` | Extracted previews and validation notes |\n| `OTHER` | OCR model\u002Fruntime behavior inside hybrid mode |\n\n### Preconditions\n- The input PDF path exists and is readable.\n- The output location is writable or can be created.\n- Required CLIs are available through `uvx`.\n- OCR is only attempted when hybrid mode is available or can be started.\n- Defaults come from the `pdf:` section of `.agents\u002Foma-config.yaml`, falling back to `config\u002Fpdf-config.yaml` for unset keys; explicit user options override both, and `output.overwrite: false` requires confirmation before replacing an existing output file.\n\n### Effects and side effects\n- Creates or overwrites extraction output depending on configuration and user intent.\n- May start a local hybrid OCR server on the configured port.\n- May consume significant CPU, memory, or time for large or scanned PDFs.\n- Does not intentionally modify the source PDF.\n\n### Guardrails\n1. Do not invent missing content when extraction is incomplete.\n2. Always report garbled text, missing tables, OCR uncertainty, or partial extraction.\n3. Prefer standard conversion first when the text layer is readable.\n4. Use OCR only when the PDF is scanned, image-based, or standard extraction quality is insufficient.\n5. Keep detailed command sequences in `resources\u002Fexecution-protocol.md` rather than duplicating every variant here.\n\n## References\n- Execution protocol: `resources\u002Fexecution-protocol.md`\n- Configuration: read the `pdf:` section of `.agents\u002Foma-config.yaml` first, then fall back to `config\u002Fpdf-config.yaml` for any key it does not set. User overrides belong in `.agents\u002Foma-config.yaml`, since `oma update` overwrites the skill config.\n- Context loading: `..\u002F_shared\u002Fcore\u002Fcontext-loading.md`\n- Quality principles: `..\u002F_shared\u002Fcore\u002Fquality-principles.md`\n","# PDF Skill - PDF to Markdown Conversion\n\n## Scheduling\n\n### Goal\nConvert PDF files into structured Markdown or another requested extraction format while preserving readable document structure for LLM context, RAG, or downstream review.\n\n### Intent signature\n- User asks to convert, parse, read, extract, or transform a PDF.\n- User needs PDF text, headings, lists, tables, or images prepared for AI consumption.\n- User mentions \"PDF to markdown\", \"parse PDF\", \"read this PDF\", or equivalent wording.\n\n### When to use\n- Converting PDF documents to Markdown for LLM context or RAG\n- Extracting structured content such as tables, headings, lists, images, footnotes, or hyperlinks\n- Preparing PDF data for AI consumption\n- Checking whether a PDF has a text layer before choosing OCR\n\n### When NOT to use\n- Generating or creating PDFs -> use document-generation tools\n- Editing existing PDFs -> out of scope\n- Reading an already-text file -> use direct file reading\n- Processing HWP, HWPX, DOCX, XLSX, or slide decks -> use the matching document skill\n\n### Expected inputs\n- `input_path`: PDF file or folder path\n- `output_dir`: optional target directory\n- `format`: optional output format, default `markdown`\n- `ocr_languages`: optional OCR language list for scanned or image-based PDFs\n- `extraction_options`: optional flags for tagged structure, image extraction, or hybrid conversion\n\n### Expected outputs\n- Markdown, text, JSON, HTML, or combined extraction output\n- Normalized Markdown when Markdown is produced\n- A short report with output path, page count, and conversion issues\n\n### Dependencies\n- `uvx opendataloader-pdf` for standard conversion\n- `uvx --from \"opendataloader-pdf[hybrid]\" opendataloader-pdf-hybrid` for OCR or hybrid conversion (the hybrid server is a console script of the `[hybrid]` extra, not a standalone package)\n- `uvx mdformat` for Markdown normalization\n- Local filesystem access to input and output paths\n- Optional OCR runtime via the hybrid server\n\n### Control-flow features\n- Branches on text-layer quality, tagged PDF availability, scan\u002FOCR needs, and user-requested output format\n- Calls external CLI tools through `uvx`\n- Reads local files and writes local extraction outputs\n- Uses a hybrid server only when OCR or complex extraction needs justify it\n\n## Structural Flow\n\n### Entry\n1. Confirm that the input path exists and is a PDF file, PDF folder, or supported batch input.\n2. Check file size and warn when the input is large enough to risk slow conversion or memory pressure.\n3. Resolve `output_dir` and the expected output filename.\n\n### Scenes\n1. **PREPARE**: Validate the input path, output target, and requested extraction options.\n2. **ACQUIRE**: Assess whether the PDF has a readable text layer by extracting a text preview.\n3. **ACT**: Convert using standard mode, tagged-structure mode, or hybrid OCR mode.\n4. **VERIFY**: Run `mdformat` for Markdown output and inspect the result for readable structure.\n5. **FINALIZE**: Report output path, page count, format, and any extraction quality issues.\n\n### Transitions\n- If the preview text is readable, use standard conversion.\n- If the PDF is tagged and standard output is garbled, retry with `--use-struct-tree`.\n- If tables are missing or broken, retry with `--table-method cluster` or `--markdown-with-html` before escalating to hybrid mode.\n- If the PDF is scanned or image-based, start or reuse the hybrid OCR server and convert with hybrid mode.\n- If conversion fails because the PDF is encrypted, stop and ask for the password or an unlocked copy.\n- If conversion hits memory or size limits, process smaller page ranges into distinct output directories (or append `--to-stdout`) so repeated runs do not overwrite the same basename.\n\n### Failure and recovery\n| Failure | Recovery |\n|---------|----------|\n| `uvx` unavailable | Ask user to install `uv` before conversion |\n| `opendataloader-pdf-hybrid` not found | Invoke via `uvx --from \"opendataloader-pdf[hybrid]\" opendataloader-pdf-hybrid`; the bare package name does not exist on PyPI |\n| Password-protected PDF | Ask for password or unlocked PDF |\n| Garbled output | Retry with tagged structure or hybrid mode |\n| Missing tables | Retry with `--table-method cluster` or `--markdown-with-html` first; hybrid mode for scanned tables |\n| OCR language mismatch | Retry with explicit OCR languages, for example `ko,en` |\n| Large file or memory pressure | Split into page ranges using distinct output directories or `--to-stdout`; never reuse one output directory for the same basename |\n\n### Exit\n- Success: output file exists, Markdown is formatted when applicable, and extracted structure is readable.\n- Partial success: output exists but quality issues are reported explicitly.\n- Failure: no reliable output is produced and the blocking cause is reported.\n\n## Logical Operations\n\n### Actions\n| Action | SSL primitive | Evidence |\n|--------|---------------|----------|\n| Validate path and options | `VALIDATE` | Input preflight in execution protocol |\n| Probe text layer | `READ` | Text preview extraction |\n| Choose conversion strategy | `SELECT` | Standard, tagged, or hybrid mode decision |\n| Run converter | `CALL_TOOL` | `uvx opendataloader-pdf` |\n| Start OCR server | `CALL_TOOL` | `uvx --from \"opendataloader-pdf[hybrid]\" opendataloader-pdf-hybrid` |\n| Write output artifact | `WRITE` | Markdown, text, JSON, or HTML output |\n| Normalize Markdown | `CALL_TOOL` | `uvx mdformat` |\n| Inspect extraction quality | `VALIDATE` | Structure\u002Freadability verification |\n| Report result | `NOTIFY` | Final user-facing summary |\n\n### Tools and instruments\n- `opendataloader-pdf`: primary PDF extraction CLI\n- `opendataloader-pdf-hybrid`: hybrid OCR and complex extraction path\n- `mdformat`: Markdown normalization\n- Filesystem commands such as `file`, `wc`, or `pdfinfo` may be used for preflight when available\n\n### Canonical command path\n```bash\nuvx opendataloader-pdf \"{input_path}\" -f text --pages 1-3 --to-stdout -q   # text-layer probe (no temp files)\nuvx opendataloader-pdf \"{input_path}\" --format markdown --output-dir \"{output_dir}\"\nuvx mdformat \"{output_path}\"\n```\n\nFor scanned\u002Fimage-based PDFs, start OCR first and then convert through hybrid mode:\n```bash\nuvx --from \"opendataloader-pdf[hybrid]\" opendataloader-pdf-hybrid --port 5002 --force-ocr --ocr-lang \"{languages}\"\nuvx opendataloader-pdf --hybrid docling-fast --hybrid-mode full \"{input_path}\" --format markdown --output-dir \"{output_dir}\"\n```\n\nOn-request flags — `--sanitize` (PII masking), `--pages` (range extraction), `--threads` (parallel pages), `--detect-strikethrough`, hybrid `--enrich-formula` \u002F `--enrich-picture-description` — are detailed in `resources\u002Fexecution-protocol.md`. The two enrichment flags require client-side `--hybrid-mode full`.\n\n### Resource scope\n| Scope | Resource target |\n|-------|-----------------|\n| `LOCAL_FS` | Input PDFs and generated output files |\n| `PROCESS` | `uvx` subprocesses and optional hybrid server |\n| `MEMORY` | Extracted previews and validation notes |\n| `OTHER` | OCR model\u002Fruntime behavior inside hybrid mode |\n\n### Preconditions\n- The input PDF path exists and is readable.\n- The output location is writable or can be created.\n- Required CLIs are available through `uvx`.\n- OCR is only attempted when hybrid mode is available or can be started.\n- Defaults come from the `pdf:` section of `.agents\u002Foma-config.yaml`, falling back to `config\u002Fpdf-config.yaml` for unset keys; explicit user options override both, and `output.overwrite: false` requires confirmation before replacing an existing output file.\n\n### Effects and side effects\n- Creates or overwrites extraction output depending on configuration and user intent.\n- May start a local hybrid OCR server on the configured port.\n- May consume significant CPU, memory, or time for large or scanned PDFs.\n- Does not intentionally modify the source PDF.\n\n### Guardrails\n1. Do not invent missing content when extraction is incomplete.\n2. Always report garbled text, missing tables, OCR uncertainty, or partial extraction.\n3. Prefer standard conversion first when the text layer is readable.\n4. Use OCR only when the PDF is scanned, image-based, or standard extraction quality is insufficient.\n5. Keep detailed command sequences in `resources\u002Fexecution-protocol.md` rather than duplicating every variant here.\n\n## References\n- Execution protocol: `resources\u002Fexecution-protocol.md`\n- Configuration: read the `pdf:` section of `.agents\u002Foma-config.yaml` first, then fall back to `config\u002Fpdf-config.yaml` for any key it does not set. User overrides belong in `.agents\u002Foma-config.yaml`, since `oma update` overwrites the skill config.\n- Context loading: `..\u002F_shared\u002Fcore\u002Fcontext-loading.md`\n- Quality principles: `..\u002F_shared\u002Fcore\u002Fquality-principles.md`\n",{"name":5,"description":7},"master","5fab8004af1390aa17b3447f2780766c8bf2482c",".agents\u002Fskills\u002Foma-pdf",0,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate","https:\u002F\u002Fgithub.com\u002Fvasceannie","thingswithstuff.io","2026-11-12 20:22:46",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add vasceannie\u002Fslopgate --skill oma-pdf",{"tool":63,"command":64},"bunx","bunx skills add vasceannie\u002Fslopgate --skill oma-pdf",{"tool":66,"command":67},"pnpm","pnpm dlx skills add vasceannie\u002Fslopgate --skill oma-pdf","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-pdf\u002FSKILL.md",true,[71,77],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"config\u002Fpdf-config.yaml","REFERENCE","参考文档",975,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-pdf\u002Fconfig\u002Fpdf-config.yaml",{"path":78,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":79,"sourceHtmlUrl":80},"resources\u002Fexecution-protocol.md",5550,"https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Foma-pdf\u002Fresources\u002Fexecution-protocol.md",[82,112,139,176,200,221],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":91,"publishedAt":44},"01M71951JDWCYMS8GDC2C7395D","type-strictness","Enforce strict type compliance by eliminating `Any` types and `# type: ignore` comments. Use when:\n(1) Editing code that contains `Any` as a type annotation\n(2) Code has `# type: ignore` or `# pyright: ignore` comments\n(3) User requests type fixes or type strictness enforcement\n(4) Importing from untyped third-party libraries\n(5) User asks to \"fix types\", \"remove Any\", or \"add proper typing\"\n(6) Pyrefly or mypy reports type errors that need resolution\n(7) Code review reveals weak typing patterns\nFollows hierarchical resolution: codebase inference → type stubs → library inspection → type guards → casting (last resort).","https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002Fbundle\u002Fshared\u002Fskills\u002Ftype-strictness\u002FSKILL.md",[88],{"categoryNo":89,"categoryName":90,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",[92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111],"type","type strictness","typing","types","remove","code review","fix","errors","inspection","when","code","review","reports","libraries","casting","pyrefly","mypy","pyright","library","patterns",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":122,"publishedAt":44},"01M7194XGBQXSE7Y5BZ4K5CSTK","slopgate-test-extender","Extend Python test suites with parametrization, fixture reuse, and quality enforcement. Use when asked to add tests, extend existing tests, improve test coverage, consolidate duplicate tests, fix test quality issues, or when Slopgate reports untested-production-code, missing test references, or coverage gaps. Triggers on requests like \"add tests for X\", \"extend these tests\", \"parametrize tests\", \"consolidate tests\", \"fix test quality\", \"improve test coverage\", \"write tests for this function\", \"test this module\", \"behavior tests\", \"integration tests\", \"missing tests\", \"coverage holes\", \"untested code\", or when a hook denies with test-related findings.","https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002Fbundle\u002Fshared\u002Fskills\u002Fslopgate-test-extender\u002FSKILL.md",[118,119],{"categoryNo":89,"categoryName":90,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":120,"categoryName":121,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[123,124,125,126,127,98,128,129,130,131,132,133,101,102,134,135,104,136,137,138],"slopgate test extender","test","coverage","fixture","testing","issues","write tests","improve","only","cleanup","loop","candidate","consolidate","references","opencode","orchestrator",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":160,"publishedAt":44},"01M7194RMVQS5YJJ4ZEFXX20VS","slopgate-intelligent-coding-patterns","Pattern-selection playbook for agents editing code with complex branching, stateful parsers\u002Fworkflows, duplicated skeletons, policy checks, or ordered transforms. Load before refactoring if\u002Felif dispatch chains, boolean-flag state machines, repeated validation predicates, parallel provider\u002Flanguage implementations, or regex\u002Fcontent transformation pipelines. Also load when asked to \"apply a design pattern\", \"which pattern should I use here\", \"refactor this switch statement\", \"replace if-elif chain\", \"state machine pattern\", \"strategy pattern\", \"template method\", \"pipeline pattern\", \"specification pattern\", \"dispatch table\", \"guard clause refactor\", \"reduce cyclomatic complexity\", or when Slopgate fires PY-CODE-014, PY-CODE-017, PY-CODE-018, QUALITY-LINT-001, or PY-QUALITY-010. Use with behavior-locking tests and avoid pattern theater for simple one-off code.","https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002Fbundle\u002Fshared\u002Fskills\u002Fslopgate-intelligent-coding-patterns\u002FSKILL.md",[145,146,149,152,157],{"categoryNo":89,"categoryName":90,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":147,"categoryName":148,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":150,"categoryName":151,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":153,"categoryName":154,"taxonomyType":155,"taxonomyTypeDesc":156},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":158,"categoryName":159,"taxonomyType":155,"taxonomyTypeDesc":156},"01JBSEEDCAT000000000000032","设计师",[161,162,111,163,164,165,166,167,168,169,170,171,172,131,132,173,174,101,175,102],"coding patterns","slopgate intelligent coding patterns","coding","stateful","complexity","branch","which","chain","parsers","pipeline","selection","design","utility","workflows","reduce",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":184,"publishedAt":44},"01M7194KTXBM85GB0W7JKFQD55","slopgate-hygiene-orchestrator","Orchestrate systematic elimination of linter warnings and errors across Python, TypeScript, and Rust codebases. Use when asked to \"clean up lints\", \"fix all warnings\", \"run hygiene\", \"eliminate type errors\", \"orchestrate code quality fixes\", \"fix lint errors\", \"resolve quality gate failures\", \"pass CI checks\", \"reduce tech debt\", \"refactor to pass hooks\", or when a Slopgate hook denies with QUALITY-LINT-001, PY-CODE-017, PY-CODE-018, or any collector finding. This skill coordinates multiple code-hygiene-enforcer agents working in parallel on non-conflicting file groupings, tracks progress persistently via JSON exports, and loops until all issues are resolved. CRITICAL: Never run linters directly—always use `slopgate lint check` as the primary gate, discover project-specific tools from config files, and export findings to JSON for tracking.","https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002Fbundle\u002Fshared\u002Fskills\u002Fslopgate-hygiene-orchestrator\u002FSKILL.md",[182,183],{"categoryNo":89,"categoryName":90,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":150,"categoryName":151,"taxonomyType":21,"taxonomyTypeDesc":22},[185,186,138,187,98,188,189,190,191,41,132,175,192,193,194,195,196,197,198,199],"slopgate hygiene orchestrator","hygiene","project","ci","local","clean","never run","run","lint check","systematic","config","typescript","debt","quality-gates","hook",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":208,"publishedAt":44},"01M7194G50FZYXXT8VNK360RPA","slopgate-code-smell-utility-locator","Autoactivate when code-smell hooks or reviews mention feature envy, thin wrappers, duplicate helpers, duplicate code,\nscattered helpers, builders\u002Ffactories\u002Fconfig\u002Fconstants\u002Fdataclass reuse, PY-CODE-012, PY-CODE-013, QUALITY-LINT-001,\nor repeated slopgate code-quality denials. Also load when asked to \"find existing helpers\", \"consolidate utilities\",\n\"search for duplicate code\", \"where is this already implemented\", \"reuse existing logic\", \"don't duplicate this\",\n\"find similar functions\", \"utility inventory\", \"code smell radar\", or before adding new helpers\u002Fwrappers so agents can\nfind existing shared utilities and consolidate instead of duplicating.","https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002Fbundle\u002Fshared\u002Fskills\u002Fslopgate-code-smell-utility-locator\u002FSKILL.md",[206,207],{"categoryNo":89,"categoryName":90,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":153,"categoryName":154,"taxonomyType":155,"taxonomyTypeDesc":156},[173,209,102,210,125,211,212,213,214,131,215,101,216,135,137,217,218,195,219,220],"slopgate code smell utility locator","shared","reviews","inventory","search","hooks","new","coordination","radar","code-quality","Utilities","dataclass",{"skillNo":222,"name":223,"nameZh":6,"description":224,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":225,"categories":226,"keywords":229,"publishedAt":44},"01M7194AWG1Q37F9756H4SFDH9","slopgate-code-hygiene-refactor","Recovery playbook for Slopgate and project quality failures. Load after hook\u002Flint denials such as PY-CODE-017 flat sibling modules, PY-CODE-018 oversized modules, QUALITY-LINT-001 post-edit quality backstops, PY-QUALITY-010 magic numbers \u002F repeated literals, PY-CODE-012\u002FPY-CODE-013 smell findings, type-suppression bans, duplicate helpers, or repeated hygiene retry loops. Also load when asked to \"refactor this module\", \"split this file\", \"extract a class\", \"reduce complexity\", \"fix god class\", \"flatten module hierarchy\", \"move code to a package\", \"extract helpers\", \"consolidate duplicates\", \"replace magic numbers with constants\", or when a hook blocks an edit with structural complaints. Focuses on preserving public APIs while refactoring toward packages, cohesive modules, typed seams, and focused tests.","https:\u002F\u002Fgithub.com\u002Fvasceannie\u002Fslopgate\u002Fblob\u002Fmaster\u002Fbundle\u002Fshared\u002Fskills\u002Fslopgate-code-hygiene-refactor\u002FSKILL.md",[227,228],{"categoryNo":89,"categoryName":90,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":153,"categoryName":154,"taxonomyType":155,"taxonomyTypeDesc":156},[230,231,102,232,186,233,165,234,235,187,236,212,237,98,131,173,101,175,216,135],"code hygiene","slopgate code hygiene refactor","refactor","modules","duplicates","retry","move","structural"]