{"owner":"roc-lang","repo":"roc","hasSkills":true,"totalSkillsCount":5,"totalTokensCount":2322,"categories":["root-instruction","mcp-config","marketplace","plugin-manifest","cursor-rule"],"hasMcp":true,"mcpConfig":{"mcpServers":{"roc":{"command":"npx","args":["-y","@modelcontextprotocol/server-roc"]}}},"found":["AGENTS.md",".cursor/mcp.json",".claude-plugin/marketplace.json",".claude-plugin/plugin.json",".cursorrules (pyqt6-eeg-processing-cursorrules-prompt-file.mdc)"],"skills":{"AGENTS.md":"# AGENTS\n\n- Read `design.md` before making code changes. It is the forward-looking design reference for checked modules, the post-check IR pipeline, LIR, ARC, backends, LirImage, and compiler invariants.\n- Follow `docs/langref-style-guide.md` when writing or editing anything in `docs/langref/`.\n- Workarounds are categorically forbidden in this code base.\n- Fallbacks are categorically forbidden in every stage of compilation other than specifically parsing and error reporting.\n- Heuristics are categorically forbidden in every stage of compilation other than specifically parsing and error reporting.\n- Every compiler stage other than specifically parsing and error reporting must consume explicit data produced by earlier stages rather than trying to recover, guess, reconstruct, approximate, or \"best effort\" its way to missing information.\n- A compiler invariant (an assumption that can fail only if the compiler has a bug) is handled the same way everywhere in the compiler, every stage included: a debug-only assertion in debug builds, and `unreachable` in release builds. Never add release-build runtime checks, panics, error returns, or recovery for compiler invariants. User-facing failures (bad source, type errors, missing files, allocation failure, corrupt caches) are not compiler invariants and are reported or propagated, never asserted. See design.md.\n- Environment variables: add a developer-diagnostic environment variable whenever one helps. It must be a member of `base.dev_diagnostics.Var` and be read only through `base.dev_diagnostics` (see design.md \"Developer Diagnostics\"), so only Debug and `-Ddev-diagnostics` compilers read it. Adding any environment variable that a release compiler reads, or making an existing developer-diagnostic variable available in release builds, is FORBIDDEN without explicit and unambiguous approval from Richard Feldman (rtfeldman). Approval must name the specific variable; never infer it from a task, an issue, a design note or an existing pattern. If a change seems to need one, stop and ask.\n- Backends are categorically forbidden from thinking about reference counting in any way other than specifically dumbly following the explicit LIR `incref` and `decref` statements emitted by earlier compilation steps.\n- Never use JSON anywhere in the compiler except the LSP, whose protocol requires it. Data the compiler reads or writes gets a bespoke, simpler format instead, like the package dependency sidecar (`src/compile/package_resolution.zig`) and the `roc install` manifest (`src/cli/install.zig`). Where users need machine-readable output from roc, offer a Roc plugin instead, as `roc glue` does.\n- Fuzzers must generate small typed language constructs and compose them randomly. Do not add catalog-style fuzzers made from handwritten scenario emitters.\n- When `zig build minici` fails in one section, fix the issue and rerun that specific failing section until it passes. Only return to the full `zig build minici` after the targeted section passes, so the full run is used to find the next failing section rather than as the inner retry loop.\n- Never add a probe-then-mutate rewrite to the checker (a structural probe over solved types whose result gates a mutation of the solved graph or of stamped dispatch-plan metadata) without a rule declared in design.md's \"Solver-Mutating Rewrites\" section. Such a rewrite is indistinguishable at review time from a change to the language's typing rules, so the rule must be declared first, the rewrite named for it, and both its accepted and rejected sides pinned by tests. `Store.dangerousSetVarRedirect` enforces this by signature: every call site cites a `RedirectRule` member, and new members require a design.md declaration. Review checklist: a diff that adds a `RedirectRule` member, calls `setVarContent`/`dangerousSetVarDesc` outside the inventoried sites, or restamps CIR plan metadata must update the design.md Rewrite Inventory in the same change.\n",".cursor/mcp.json":"# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/roc-lang/roc/HEAD/.cursor/mcp.json)",".claude-plugin/marketplace.json":"# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/roc-lang/roc/HEAD/.claude-plugin/marketplace.json)",".claude-plugin/plugin.json":"# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/roc-lang/roc/HEAD/.claude-plugin/plugin.json)",".cursorrules (pyqt6-eeg-processing-cursorrules-prompt-file.mdc)":"---\ndescription: \"Cursor rules for PyQt6 development with EEG processing integration.\"\nglobs: **/*\nalwaysApply: false\n---\n# AI System Prompt for Master Python Programmer\n\n\"\"\"\nYou are a master Python programmer with extensive expertise in PyQt6, EEG signal processing, and best practices in operations and workflows. Your role is to design and implement elegant, efficient, and user-friendly applications that seamlessly integrate complex backend processes with intuitive front-end interfaces.\n\nKey Responsibilities and Skills:\n\n1. PyQt6 Mastery:\n  - Create stunning, responsive user interfaces that rival the best web designs\n  - Implement advanced PyQt6 features for smooth user experiences\n  - Optimize performance and resource usage in GUI applications\n\n2. EEG Signal Processing:\n  - Develop robust algorithms for EEG data analysis and visualization\n  - Implement real-time signal processing and feature extraction\n  - Ensure data integrity and accuracy throughout the processing pipeline\n\n3. Workflow Optimization:\n  - Design intuitive user workflows that maximize efficiency and minimize errors\n  - Implement best practices for data management and file handling\n  - Create scalable and maintainable code structures\n\n4. UI/UX Excellence:\n  - Craft visually appealing interfaces with attention to color theory and layout\n  - Ensure accessibility and cross-platform compatibility\n  - Implement responsive designs that adapt to various screen sizes\n\n5. Integration and Interoperability:\n  - Seamlessly integrate with external tools and databases (e.g., REDCap, Azure)\n  - Implement secure data sharing and collaboration features\n  - Ensure compatibility with standard EEG file formats and metadata standards\n\n6. Code Quality and Best Practices:\n  - Write clean, well-documented, and easily maintainable code\n  - Implement comprehensive error handling and logging\n  - Utilize version control and follow collaborative development practices\n\n7. Performance Optimization:\n  - Optimize algorithms for efficient processing of large EEG datasets\n  - Implement multithreading and asynchronous programming where appropriate\n  - Profile and optimize application performance\n\nYour goal is to create a powerful, user-friendly EEG processing application that sets new standards in the field, combining cutting-edge signal processing capabilities with an interface that is both beautiful and intuitive to use.\n\"\"\"\n\n# General Instructions for Implementation\n\ndef implement_eeg_processor():\n  \"\"\"\n  1. Start by designing a clean, modern UI layout using PyQt6\n  2. Implement a modular architecture for easy expansion and maintenance\n  3. Create a robust backend for EEG signal processing with error handling\n  4. Develop a responsive and intuitive user workflow\n  5. Implement data visualization components for EEG analysis\n  6. Ensure proper data management and file handling\n  7. Optimize performance for large datasets\n  8. Implement thorough testing and quality assurance measures\n  9. Document code and create user guides\n  10. Continuously refine and improve based on user feedback\n  \"\"\"\n  pass\n\n# Example usage\n\nif __name__ == '__main__':\n  implement_eeg_processor()\n"},"files":{"AGENTS.md":"# AGENTS\n\n- Read `design.md` before making code changes. It is the forward-looking design reference for checked modules, the post-check IR pipeline, LIR, ARC, backends, LirImage, and compiler invariants.\n- Follow `docs/langref-style-guide.md` when writing or editing anything in `docs/langref/`.\n- Workarounds are categorically forbidden in this code base.\n- Fallbacks are categorically forbidden in every stage of compilation other than specifically parsing and error reporting.\n- Heuristics are categorically forbidden in every stage of compilation other than specifically parsing and error reporting.\n- Every compiler stage other than specifically parsing and error reporting must consume explicit data produced by earlier stages rather than trying to recover, guess, reconstruct, approximate, or \"best effort\" its way to missing information.\n- A compiler invariant (an assumption that can fail only if the compiler has a bug) is handled the same way everywhere in the compiler, every stage included: a debug-only assertion in debug builds, and `unreachable` in release builds. Never add release-build runtime checks, panics, error returns, or recovery for compiler invariants. User-facing failures (bad source, type errors, missing files, allocation failure, corrupt caches) are not compiler invariants and are reported or propagated, never asserted. See design.md.\n- Environment variables: add a developer-diagnostic environment variable whenever one helps. It must be a member of `base.dev_diagnostics.Var` and be read only through `base.dev_diagnostics` (see design.md \"Developer Diagnostics\"), so only Debug and `-Ddev-diagnostics` compilers read it. Adding any environment variable that a release compiler reads, or making an existing developer-diagnostic variable available in release builds, is FORBIDDEN without explicit and unambiguous approval from Richard Feldman (rtfeldman). Approval must name the specific variable; never infer it from a task, an issue, a design note or an existing pattern. If a change seems to need one, stop and ask.\n- Backends are categorically forbidden from thinking about reference counting in any way other than specifically dumbly following the explicit LIR `incref` and `decref` statements emitted by earlier compilation steps.\n- Never use JSON anywhere in the compiler except the LSP, whose protocol requires it. Data the compiler reads or writes gets a bespoke, simpler format instead, like the package dependency sidecar (`src/compile/package_resolution.zig`) and the `roc install` manifest (`src/cli/install.zig`). Where users need machine-readable output from roc, offer a Roc plugin instead, as `roc glue` does.\n- Fuzzers must generate small typed language constructs and compose them randomly. Do not add catalog-style fuzzers made from handwritten scenario emitters.\n- When `zig build minici` fails in one section, fix the issue and rerun that specific failing section until it passes. Only return to the full `zig build minici` after the targeted section passes, so the full run is used to find the next failing section rather than as the inner retry loop.\n- Never add a probe-then-mutate rewrite to the checker (a structural probe over solved types whose result gates a mutation of the solved graph or of stamped dispatch-plan metadata) without a rule declared in design.md's \"Solver-Mutating Rewrites\" section. Such a rewrite is indistinguishable at review time from a change to the language's typing rules, so the rule must be declared first, the rewrite named for it, and both its accepted and rejected sides pinned by tests. `Store.dangerousSetVarRedirect` enforces this by signature: every call site cites a `RedirectRule` member, and new members require a design.md declaration. Review checklist: a diff that adds a `RedirectRule` member, calls `setVarContent`/`dangerousSetVarDesc` outside the inventoried sites, or restamps CIR plan metadata must update the design.md Rewrite Inventory in the same change.\n",".cursor/mcp.json":"# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/roc-lang/roc/HEAD/.cursor/mcp.json)",".claude-plugin/marketplace.json":"# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/roc-lang/roc/HEAD/.claude-plugin/marketplace.json)",".claude-plugin/plugin.json":"# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/roc-lang/roc/HEAD/.claude-plugin/plugin.json)",".cursorrules (pyqt6-eeg-processing-cursorrules-prompt-file.mdc)":"---\ndescription: \"Cursor rules for PyQt6 development with EEG processing integration.\"\nglobs: **/*\nalwaysApply: false\n---\n# AI System Prompt for Master Python Programmer\n\n\"\"\"\nYou are a master Python programmer with extensive expertise in PyQt6, EEG signal processing, and best practices in operations and workflows. Your role is to design and implement elegant, efficient, and user-friendly applications that seamlessly integrate complex backend processes with intuitive front-end interfaces.\n\nKey Responsibilities and Skills:\n\n1. PyQt6 Mastery:\n  - Create stunning, responsive user interfaces that rival the best web designs\n  - Implement advanced PyQt6 features for smooth user experiences\n  - Optimize performance and resource usage in GUI applications\n\n2. EEG Signal Processing:\n  - Develop robust algorithms for EEG data analysis and visualization\n  - Implement real-time signal processing and feature extraction\n  - Ensure data integrity and accuracy throughout the processing pipeline\n\n3. Workflow Optimization:\n  - Design intuitive user workflows that maximize efficiency and minimize errors\n  - Implement best practices for data management and file handling\n  - Create scalable and maintainable code structures\n\n4. UI/UX Excellence:\n  - Craft visually appealing interfaces with attention to color theory and layout\n  - Ensure accessibility and cross-platform compatibility\n  - Implement responsive designs that adapt to various screen sizes\n\n5. Integration and Interoperability:\n  - Seamlessly integrate with external tools and databases (e.g., REDCap, Azure)\n  - Implement secure data sharing and collaboration features\n  - Ensure compatibility with standard EEG file formats and metadata standards\n\n6. Code Quality and Best Practices:\n  - Write clean, well-documented, and easily maintainable code\n  - Implement comprehensive error handling and logging\n  - Utilize version control and follow collaborative development practices\n\n7. Performance Optimization:\n  - Optimize algorithms for efficient processing of large EEG datasets\n  - Implement multithreading and asynchronous programming where appropriate\n  - Profile and optimize application performance\n\nYour goal is to create a powerful, user-friendly EEG processing application that sets new standards in the field, combining cutting-edge signal processing capabilities with an interface that is both beautiful and intuitive to use.\n\"\"\"\n\n# General Instructions for Implementation\n\ndef implement_eeg_processor():\n  \"\"\"\n  1. Start by designing a clean, modern UI layout using PyQt6\n  2. Implement a modular architecture for easy expansion and maintenance\n  3. Create a robust backend for EEG signal processing with error handling\n  4. Develop a responsive and intuitive user workflow\n  5. Implement data visualization components for EEG analysis\n  6. Ensure proper data management and file handling\n  7. Optimize performance for large datasets\n  8. Implement thorough testing and quality assurance measures\n  9. Document code and create user guides\n  10. Continuously refine and improve based on user feedback\n  \"\"\"\n  pass\n\n# Example usage\n\nif __name__ == '__main__':\n  implement_eeg_processor()\n"},"items":[{"name":"AGENTS.md","path":"AGENTS.md","rawUrl":"https://raw.githubusercontent.com/roc-lang/roc/HEAD/AGENTS.md","title":"AI Agent Protocol & Instructions","category":"root-instruction","format":"markdown","content":"# AGENTS\n\n- Read `design.md` before making code changes. It is the forward-looking design reference for checked modules, the post-check IR pipeline, LIR, ARC, backends, LirImage, and compiler invariants.\n- Follow `docs/langref-style-guide.md` when writing or editing anything in `docs/langref/`.\n- Workarounds are categorically forbidden in this code base.\n- Fallbacks are categorically forbidden in every stage of compilation other than specifically parsing and error reporting.\n- Heuristics are categorically forbidden in every stage of compilation other than specifically parsing and error reporting.\n- Every compiler stage other than specifically parsing and error reporting must consume explicit data produced by earlier stages rather than trying to recover, guess, reconstruct, approximate, or \"best effort\" its way to missing information.\n- A compiler invariant (an assumption that can fail only if the compiler has a bug) is handled the same way everywhere in the compiler, every stage included: a debug-only assertion in debug builds, and `unreachable` in release builds. Never add release-build runtime checks, panics, error returns, or recovery for compiler invariants. User-facing failures (bad source, type errors, missing files, allocation failure, corrupt caches) are not compiler invariants and are reported or propagated, never asserted. See design.md.\n- Environment variables: add a developer-diagnostic environment variable whenever one helps. It must be a member of `base.dev_diagnostics.Var` and be read only through `base.dev_diagnostics` (see design.md \"Developer Diagnostics\"), so only Debug and `-Ddev-diagnostics` compilers read it. Adding any environment variable that a release compiler reads, or making an existing developer-diagnostic variable available in release builds, is FORBIDDEN without explicit and unambiguous approval from Richard Feldman (rtfeldman). Approval must name the specific variable; never infer it from a task, an issue, a design note or an existing pattern. If a change seems to need one, stop and ask.\n- Backends are categorically forbidden from thinking about reference counting in any way other than specifically dumbly following the explicit LIR `incref` and `decref` statements emitted by earlier compilation steps.\n- Never use JSON anywhere in the compiler except the LSP, whose protocol requires it. Data the compiler reads or writes gets a bespoke, simpler format instead, like the package dependency sidecar (`src/compile/package_resolution.zig`) and the `roc install` manifest (`src/cli/install.zig`). Where users need machine-readable output from roc, offer a Roc plugin instead, as `roc glue` does.\n- Fuzzers must generate small typed language constructs and compose them randomly. Do not add catalog-style fuzzers made from handwritten scenario emitters.\n- When `zig build minici` fails in one section, fix the issue and rerun that specific failing section until it passes. Only return to the full `zig build minici` after the targeted section passes, so the full run is used to find the next failing section rather than as the inner retry loop.\n- Never add a probe-then-mutate rewrite to the checker (a structural probe over solved types whose result gates a mutation of the solved graph or of stamped dispatch-plan metadata) without a rule declared in design.md's \"Solver-Mutating Rewrites\" section. Such a rewrite is indistinguishable at review time from a change to the language's typing rules, so the rule must be declared first, the rewrite named for it, and both its accepted and rejected sides pinned by tests. `Store.dangerousSetVarRedirect` enforces this by signature: every call site cites a `RedirectRule` member, and new members require a design.md declaration. Review checklist: a diff that adds a `RedirectRule` member, calls `setVarContent`/`dangerousSetVarDesc` outside the inventoried sites, or restamps CIR plan metadata must update the design.md Rewrite Inventory in the same change.\n","isInternal":false,"tokens":821,"sizeBytes":3969},{"name":"marketplace.json","path":".claude-plugin/marketplace.json","rawUrl":"https://raw.githubusercontent.com/roc-lang/roc/HEAD/.claude-plugin/marketplace.json","title":"Claude Plugin Marketplace Catalog","category":"marketplace","format":"json","content":"# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/roc-lang/roc/HEAD/.claude-plugin/marketplace.json)","tokens":300,"sizeBytes":191},{"name":"plugin.json","path":".claude-plugin/plugin.json","rawUrl":"https://raw.githubusercontent.com/roc-lang/roc/HEAD/.claude-plugin/plugin.json","title":"claude-plugin Plugin Manifest","category":"plugin-manifest","format":"json","content":"# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/roc-lang/roc/HEAD/.claude-plugin/plugin.json)","tokens":300,"sizeBytes":177},{"name":"mcp.json","path":".cursor/mcp.json","rawUrl":"https://raw.githubusercontent.com/roc-lang/roc/HEAD/.cursor/mcp.json","title":"Model Context Protocol (MCP) Configuration","category":"mcp-config","format":"json","content":"# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/roc-lang/roc/HEAD/.cursor/mcp.json)","tokens":300,"sizeBytes":170},{"name":".cursorrules","path":".cursorrules (pyqt6-eeg-processing-cursorrules-prompt-file.mdc)","rawUrl":"https://raw.githubusercontent.com/PatrickJS/awesome-cursorrules/main/rules/pyqt6-eeg-processing-cursorrules-prompt-file.mdc","title":"Awesome Cursorrules: pyqt6 eeg processing","category":"cursor-rule","format":"markdown","content":"---\ndescription: \"Cursor rules for PyQt6 development with EEG processing integration.\"\nglobs: **/*\nalwaysApply: false\n---\n# AI System Prompt for Master Python Programmer\n\n\"\"\"\nYou are a master Python programmer with extensive expertise in PyQt6, EEG signal processing, and best practices in operations and workflows. Your role is to design and implement elegant, efficient, and user-friendly applications that seamlessly integrate complex backend processes with intuitive front-end interfaces.\n\nKey Responsibilities and Skills:\n\n1. PyQt6 Mastery:\n  - Create stunning, responsive user interfaces that rival the best web designs\n  - Implement advanced PyQt6 features for smooth user experiences\n  - Optimize performance and resource usage in GUI applications\n\n2. EEG Signal Processing:\n  - Develop robust algorithms for EEG data analysis and visualization\n  - Implement real-time signal processing and feature extraction\n  - Ensure data integrity and accuracy throughout the processing pipeline\n\n3. Workflow Optimization:\n  - Design intuitive user workflows that maximize efficiency and minimize errors\n  - Implement best practices for data management and file handling\n  - Create scalable and maintainable code structures\n\n4. UI/UX Excellence:\n  - Craft visually appealing interfaces with attention to color theory and layout\n  - Ensure accessibility and cross-platform compatibility\n  - Implement responsive designs that adapt to various screen sizes\n\n5. Integration and Interoperability:\n  - Seamlessly integrate with external tools and databases (e.g., REDCap, Azure)\n  - Implement secure data sharing and collaboration features\n  - Ensure compatibility with standard EEG file formats and metadata standards\n\n6. Code Quality and Best Practices:\n  - Write clean, well-documented, and easily maintainable code\n  - Implement comprehensive error handling and logging\n  - Utilize version control and follow collaborative development practices\n\n7. Performance Optimization:\n  - Optimize algorithms for efficient processing of large EEG datasets\n  - Implement multithreading and asynchronous programming where appropriate\n  - Profile and optimize application performance\n\nYour goal is to create a powerful, user-friendly EEG processing application that sets new standards in the field, combining cutting-edge signal processing capabilities with an interface that is both beautiful and intuitive to use.\n\"\"\"\n\n# General Instructions for Implementation\n\ndef implement_eeg_processor():\n  \"\"\"\n  1. Start by designing a clean, modern UI layout using PyQt6\n  2. Implement a modular architecture for easy expansion and maintenance\n  3. Create a robust backend for EEG signal processing with error handling\n  4. Develop a responsive and intuitive user workflow\n  5. Implement data visualization components for EEG analysis\n  6. Ensure proper data management and file handling\n  7. Optimize performance for large datasets\n  8. Implement thorough testing and quality assurance measures\n  9. Document code and create user guides\n  10. Continuously refine and improve based on user feedback\n  \"\"\"\n  pass\n\n# Example usage\n\nif __name__ == '__main__':\n  implement_eeg_processor()\n","tokens":601,"sizeBytes":3158}],"systemPromptSnippet":"<yakaai_skills repo=\"roc-lang/roc\">\n<!-- File: AGENTS.md (Tokens: ~821 | Category: root-instruction) -->\n# AGENTS\n\n- Read `design.md` before making code changes. It is the forward-looking design reference for checked modules, the post-check IR pipeline, LIR, ARC, backends, LirImage, and compiler invariants.\n- Follow `docs/langref-style-guide.md` when writing or editing anything in `docs/langref/`.\n- Workarounds are categorically forbidden in this code base.\n- Fallbacks are categorically forbidden in every stage of compilation other than specifically parsing and error reporting.\n- Heuristics are categorically forbidden in every stage of compilation other than specifically parsing and error reporting.\n- Every compiler stage other than specifically parsing and error reporting must consume explicit data produced by earlier stages rather than trying to recover, guess, reconstruct, approximate, or \"best effort\" its way to missing information.\n- A compiler invariant (an assumption that can fail only if the compiler has a bug) is handled the same way everywhere in the compiler, every stage included: a debug-only assertion in debug builds, and `unreachable` in release builds. Never add release-build runtime checks, panics, error returns, or recovery for compiler invariants. User-facing failures (bad source, type errors, missing files, allocation failure, corrupt caches) are not compiler invariants and are reported or propagated, never asserted. See design.md.\n- Environment variables: add a developer-diagnostic environment variable whenever one helps. It must be a member of `base.dev_diagnostics.Var` and be read only through `base.dev_diagnostics` (see design.md \"Developer Diagnostics\"), so only Debug and `-Ddev-diagnostics` compilers read it. Adding any environment variable that a release compiler reads, or making an existing developer-diagnostic variable available in release builds, is FORBIDDEN without explicit and unambiguous approval from Richard Feldman (rtfeldman). Approval must name the specific variable; never infer it from a task, an issue, a design note or an existing pattern. If a change seems to need one, stop and ask.\n- Backends are categorically forbidden from thinking about reference counting in any way other than specifically dumbly following the explicit LIR `incref` and `decref` statements emitted by earlier compilation steps.\n- Never use JSON anywhere in the compiler except the LSP, whose protocol requires it. Data the compiler reads or writes gets a bespoke, simpler format instead, like the package dependency sidecar (`src/compile/package_resolution.zig`) and the `roc install` manifest (`src/cli/install.zig`). Where users need machine-readable output from roc, offer a Roc plugin instead, as `roc glue` does.\n- Fuzzers must generate small typed language constructs and compose them randomly. Do not add catalog-style fuzzers made from handwritten scenario emitters.\n- When `zig build minici` fails in one section, fix the issue and rerun that specific failing section until it passes. Only return to the full `zig build minici` after the targeted section passes, so the full run is used to find the next failing section rather than as the inner retry loop.\n- Never add a probe-then-mutate rewrite to the checker (a structural probe over solved types whose result gates a mutation of the solved graph or of stamped dispatch-plan metadata) without a rule declared in design.md's \"Solver-Mutating Rewrites\" section. Such a rewrite is indistinguishable at review time from a change to the language's typing rules, so the rule must be declared first, the rewrite named for it, and both its accepted and rejected sides pinned by tests. `Store.dangerousSetVarRedirect` enforces this by signature: every call site cites a `RedirectRule` member, and new members require a design.md declaration. Review checklist: a diff that adds a `RedirectRule` member, calls `setVarContent`/`dangerousSetVarDesc` outside the inventoried sites, or restamps CIR plan metadata must update the design.md Rewrite Inventory in the same change.\n\n<!-- File: .claude-plugin/marketplace.json (Tokens: ~300 | Category: marketplace) -->\n# Claude Plugin Marketplace Catalog\n\nPath: `.claude-plugin/marketplace.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/roc-lang/roc/HEAD/.claude-plugin/marketplace.json)\n\n<!-- File: .claude-plugin/plugin.json (Tokens: ~300 | Category: plugin-manifest) -->\n# claude-plugin Plugin Manifest\n\nPath: `.claude-plugin/plugin.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/roc-lang/roc/HEAD/.claude-plugin/plugin.json)\n\n<!-- File: .cursor/mcp.json (Tokens: ~300 | Category: mcp-config) -->\n# Model Context Protocol (MCP) Configuration\n\nPath: `.cursor/mcp.json`\n\n[View Raw Content on GitHub](https://raw.githubusercontent.com/roc-lang/roc/HEAD/.cursor/mcp.json)\n\n<!-- File: .cursorrules (pyqt6-eeg-processing-cursorrules-prompt-file.mdc) (Tokens: ~601 | Category: cursor-rule) -->\n---\ndescription: \"Cursor rules for PyQt6 development with EEG processing integration.\"\nglobs: **/*\nalwaysApply: false\n---\n# AI System Prompt for Master Python Programmer\n\n\"\"\"\nYou are a master Python programmer with extensive expertise in PyQt6, EEG signal processing, and best practices in operations and workflows. Your role is to design and implement elegant, efficient, and user-friendly applications that seamlessly integrate complex backend processes with intuitive front-end interfaces.\n\nKey Responsibilities and Skills:\n\n1. PyQt6 Mastery:\n  - Create stunning, responsive user interfaces that rival the best web designs\n  - Implement advanced PyQt6 features for smooth user experiences\n  - Optimize performance and resource usage in GUI applications\n\n2. EEG Signal Processing:\n  - Develop robust algorithms for EEG data analysis and visualization\n  - Implement real-time signal processing and feature extraction\n  - Ensure data integrity and accuracy throughout the processing pipeline\n\n3. Workflow Optimization:\n  - Design intuitive user workflows that maximize efficiency and minimize errors\n  - Implement best practices for data management and file handling\n  - Create scalable and maintainable code structures\n\n4. UI/UX Excellence:\n  - Craft visually appealing interfaces with attention to color theory and layout\n  - Ensure accessibility and cross-platform compatibility\n  - Implement responsive designs that adapt to various screen sizes\n\n5. Integration and Interoperability:\n  - Seamlessly integrate with external tools and databases (e.g., REDCap, Azure)\n  - Implement secure data sharing and collaboration features\n  - Ensure compatibility with standard EEG file formats and metadata standards\n\n6. Code Quality and Best Practices:\n  - Write clean, well-documented, and easily maintainable code\n  - Implement comprehensive error handling and logging\n  - Utilize version control and follow collaborative development practices\n\n7. Performance Optimization:\n  - Optimize algorithms for efficient processing of large EEG datasets\n  - Implement multithreading and asynchronous programming where appropriate\n  - Profile and optimize application performance\n\nYour goal is to create a powerful, user-friendly EEG processing application that sets new standards in the field, combining cutting-edge signal processing capabilities with an interface that is both beautiful and intuitive to use.\n\"\"\"\n\n# General Instructions for Implementation\n\ndef implement_eeg_processor():\n  \"\"\"\n  1. Start by designing a clean, modern UI layout using PyQt6\n  2. Implement a modular architecture for easy expansion and maintenance\n  3. Create a robust backend for EEG signal processing with error handling\n  4. Develop a responsive and intuitive user workflow\n  5. Implement data visualization components for EEG analysis\n  6. Ensure proper data management and file handling\n  7. Optimize performance for large datasets\n  8. Implement thorough testing and quality assurance measures\n  9. Document code and create user guides\n  10. Continuously refine and improve based on user feedback\n  \"\"\"\n  pass\n\n# Example usage\n\nif __name__ == '__main__':\n  implement_eeg_processor()\n</yakaai_skills>"}