{"owner":"pytorch","repo":"executorch","hasSkills":true,"totalSkillsCount":5,"totalTokensCount":2100,"categories":["claude-rule","root-instruction","mcp-config","marketplace","plugin-manifest"],"hasMcp":true,"mcpConfig":{"mcpServers":{"executorch":{"command":"npx","args":["-y","@modelcontextprotocol/server-executorch"]}}},"found":["CLAUDE.md","AGENTS.md",".cursor/mcp.json",".claude-plugin/marketplace.json",".claude-plugin/plugin.json"],"skills":{"CLAUDE.md":"# ExecuTorch\n\n## Skills\n- `/setup` - Set up environment\n- `/export` - Export model to .pte\n- `/building` - Build runners or C++ libs\n- `/profile` - Profile execution\n- `/cortex-m` - Build, test, or develop the Cortex-M backend\n- `/binary-size` - Analyze and reduce binary size\n- `/pr-review` - Review a pull request\n- `/qualcomm` - Build, test, or develop the QNN (Qualcomm AI Engine Direct) backend\n- `/executorch-kb` - Search tribal knowledge base (known issues, quant recipes, debugging guides)\n\nReference docs in `.claude/`: backends, runtime-api, quantization, llm-export, faq, tokenizers\nTribal knowledge wiki in `.wiki/`: synthesized from 2,200+ GitHub issues\n\nFor error messages, SoC compatibility questions, quantization recipes, and backend-specific debugging, consult the `/executorch-kb` skill (or read `.wiki/index.md` and navigate to the relevant article). The wiki contains tribal knowledge synthesized from 2,200+ GitHub issues with source citations. For build, test, profile, setup, or general API questions, use the dedicated skills above instead — the wiki is scoped to debugging and compatibility knowledge.\n\n## Quick Reference\n\n**Install Python package:**\n```bash\n./install_executorch.sh        # first time (or .bat on Windows)\npip install -e . --no-build-isolation  # subsequent installs\n```\n\n**Build C++ libraries:** see `CMakeLists.txt`; for LLM/ASR runners use `Makefile` and `CMakePresets.json`\n\n**Run tests:** `pytest -n auto` (Python), `ctest --output-on-failure` (C++)\n\n**Lint:** `lintrunner init && lintrunner -a`\n\nDetails: [docs/source/using-executorch-building-from-source.md](docs/source/using-executorch-building-from-source.md)\n\n## Naming\n\n- Use \"executorch\" (lowercase) or \"ExecuTorch\" (camel case)\n- Never \"ExecutorTorch\"\n- \"ET\" only when space-constrained (unofficial)\n\n## Commits\n\n- Only commit when explicitly asked\n- No bullet lists of changes; explain review order for large PRs, or omit for small ones\n- Disclose PR was authored with AI, include tool name.\n\n## Code Style\n\n- Minimal comments; code should be self-documenting\n- Comments only for non-obvious global context\n- No trivial (1-2 LOC) single-use helpers unless significantly improving readability\n- Explicit state management; no dynamic `setattr`/`getattr` patterns\n- Match existing style and architecture\n- Assume reader knows ExecuTorch/PyTorch basics\n\n**When uncertain: choose simpler, more concise.**\n","AGENTS.md":"# ExecuTorch\n\n## Skills\n- `/setup` - Set up environment\n- `/export` - Export model to .pte\n- `/building` - Build runners or C++ libs\n- `/profile` - Profile execution\n- `/cortex-m` - Build, test, or develop the Cortex-M backend\n- `/binary-size` - Analyze and reduce binary size\n- `/pr-review` - Review a pull request\n- `/qualcomm` - Build, test, or develop the QNN (Qualcomm AI Engine Direct) backend\n- `/executorch-kb` - Search tribal knowledge base (known issues, quant recipes, debugging guides)\n\nReference docs in `.claude/`: backends, runtime-api, quantization, llm-export, faq, tokenizers\nTribal knowledge wiki in `.wiki/`: synthesized from 2,200+ GitHub issues\n\nFor error messages, SoC compatibility questions, quantization recipes, and backend-specific debugging, consult the `/executorch-kb` skill (or read `.wiki/index.md` and navigate to the relevant article). The wiki contains tribal knowledge synthesized from 2,200+ GitHub issues with source citations. For build, test, profile, setup, or general API questions, use the dedicated skills above instead — the wiki is scoped to debugging and compatibility knowledge.\n\n## Quick Reference\n\n**Install Python package:**\n```bash\n./install_executorch.sh        # first time (or .bat on Windows)\npip install -e . --no-build-isolation  # subsequent installs\n```\n\n**Build C++ libraries:** see `CMakeLists.txt`; for LLM/ASR runners use `Makefile` and `CMakePresets.json`\n\n**Run tests:** `pytest -n auto` (Python), `ctest --output-on-failure` (C++)\n\n**Lint:** `lintrunner init && lintrunner -a`\n\nDetails: [docs/source/using-executorch-building-from-source.md](docs/source/using-executorch-building-from-source.md)\n\n## Naming\n\n- Use \"executorch\" (lowercase) or \"ExecuTorch\" (camel case)\n- Never \"ExecutorTorch\"\n- \"ET\" only when space-constrained (unofficial)\n\n## Commits\n\n- Only commit when explicitly asked\n- No bullet lists of changes; explain review order for large PRs, or omit for small ones\n- Disclose PR was authored with AI, include tool name.\n\n## Code Style\n\n- Minimal comments; code should be self-documenting\n- Comments only for non-obvious global context\n- No trivial (1-2 LOC) single-use helpers unless significantly improving readability\n- Explicit state management; no dynamic `setattr`/`getattr` patterns\n- Match existing style and architecture\n- Assume reader knows ExecuTorch/PyTorch basics\n\n**When uncertain: choose simpler, more concise.**\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/pytorch/executorch/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/pytorch/executorch/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/pytorch/executorch/HEAD/.claude-plugin/plugin.json)"},"files":{"CLAUDE.md":"# ExecuTorch\n\n## Skills\n- `/setup` - Set up environment\n- `/export` - Export model to .pte\n- `/building` - Build runners or C++ libs\n- `/profile` - Profile execution\n- `/cortex-m` - Build, test, or develop the Cortex-M backend\n- `/binary-size` - Analyze and reduce binary size\n- `/pr-review` - Review a pull request\n- `/qualcomm` - Build, test, or develop the QNN (Qualcomm AI Engine Direct) backend\n- `/executorch-kb` - Search tribal knowledge base (known issues, quant recipes, debugging guides)\n\nReference docs in `.claude/`: backends, runtime-api, quantization, llm-export, faq, tokenizers\nTribal knowledge wiki in `.wiki/`: synthesized from 2,200+ GitHub issues\n\nFor error messages, SoC compatibility questions, quantization recipes, and backend-specific debugging, consult the `/executorch-kb` skill (or read `.wiki/index.md` and navigate to the relevant article). The wiki contains tribal knowledge synthesized from 2,200+ GitHub issues with source citations. For build, test, profile, setup, or general API questions, use the dedicated skills above instead — the wiki is scoped to debugging and compatibility knowledge.\n\n## Quick Reference\n\n**Install Python package:**\n```bash\n./install_executorch.sh        # first time (or .bat on Windows)\npip install -e . --no-build-isolation  # subsequent installs\n```\n\n**Build C++ libraries:** see `CMakeLists.txt`; for LLM/ASR runners use `Makefile` and `CMakePresets.json`\n\n**Run tests:** `pytest -n auto` (Python), `ctest --output-on-failure` (C++)\n\n**Lint:** `lintrunner init && lintrunner -a`\n\nDetails: [docs/source/using-executorch-building-from-source.md](docs/source/using-executorch-building-from-source.md)\n\n## Naming\n\n- Use \"executorch\" (lowercase) or \"ExecuTorch\" (camel case)\n- Never \"ExecutorTorch\"\n- \"ET\" only when space-constrained (unofficial)\n\n## Commits\n\n- Only commit when explicitly asked\n- No bullet lists of changes; explain review order for large PRs, or omit for small ones\n- Disclose PR was authored with AI, include tool name.\n\n## Code Style\n\n- Minimal comments; code should be self-documenting\n- Comments only for non-obvious global context\n- No trivial (1-2 LOC) single-use helpers unless significantly improving readability\n- Explicit state management; no dynamic `setattr`/`getattr` patterns\n- Match existing style and architecture\n- Assume reader knows ExecuTorch/PyTorch basics\n\n**When uncertain: choose simpler, more concise.**\n","AGENTS.md":"# ExecuTorch\n\n## Skills\n- `/setup` - Set up environment\n- `/export` - Export model to .pte\n- `/building` - Build runners or C++ libs\n- `/profile` - Profile execution\n- `/cortex-m` - Build, test, or develop the Cortex-M backend\n- `/binary-size` - Analyze and reduce binary size\n- `/pr-review` - Review a pull request\n- `/qualcomm` - Build, test, or develop the QNN (Qualcomm AI Engine Direct) backend\n- `/executorch-kb` - Search tribal knowledge base (known issues, quant recipes, debugging guides)\n\nReference docs in `.claude/`: backends, runtime-api, quantization, llm-export, faq, tokenizers\nTribal knowledge wiki in `.wiki/`: synthesized from 2,200+ GitHub issues\n\nFor error messages, SoC compatibility questions, quantization recipes, and backend-specific debugging, consult the `/executorch-kb` skill (or read `.wiki/index.md` and navigate to the relevant article). The wiki contains tribal knowledge synthesized from 2,200+ GitHub issues with source citations. For build, test, profile, setup, or general API questions, use the dedicated skills above instead — the wiki is scoped to debugging and compatibility knowledge.\n\n## Quick Reference\n\n**Install Python package:**\n```bash\n./install_executorch.sh        # first time (or .bat on Windows)\npip install -e . --no-build-isolation  # subsequent installs\n```\n\n**Build C++ libraries:** see `CMakeLists.txt`; for LLM/ASR runners use `Makefile` and `CMakePresets.json`\n\n**Run tests:** `pytest -n auto` (Python), `ctest --output-on-failure` (C++)\n\n**Lint:** `lintrunner init && lintrunner -a`\n\nDetails: [docs/source/using-executorch-building-from-source.md](docs/source/using-executorch-building-from-source.md)\n\n## Naming\n\n- Use \"executorch\" (lowercase) or \"ExecuTorch\" (camel case)\n- Never \"ExecutorTorch\"\n- \"ET\" only when space-constrained (unofficial)\n\n## Commits\n\n- Only commit when explicitly asked\n- No bullet lists of changes; explain review order for large PRs, or omit for small ones\n- Disclose PR was authored with AI, include tool name.\n\n## Code Style\n\n- Minimal comments; code should be self-documenting\n- Comments only for non-obvious global context\n- No trivial (1-2 LOC) single-use helpers unless significantly improving readability\n- Explicit state management; no dynamic `setattr`/`getattr` patterns\n- Match existing style and architecture\n- Assume reader knows ExecuTorch/PyTorch basics\n\n**When uncertain: choose simpler, more concise.**\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/pytorch/executorch/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/pytorch/executorch/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/pytorch/executorch/HEAD/.claude-plugin/plugin.json)"},"items":[{"name":"AGENTS.md","path":"AGENTS.md","rawUrl":"https://raw.githubusercontent.com/pytorch/executorch/HEAD/AGENTS.md","title":"AI Agent Protocol & Instructions","category":"root-instruction","format":"markdown","content":"# ExecuTorch\n\n## Skills\n- `/setup` - Set up environment\n- `/export` - Export model to .pte\n- `/building` - Build runners or C++ libs\n- `/profile` - Profile execution\n- `/cortex-m` - Build, test, or develop the Cortex-M backend\n- `/binary-size` - Analyze and reduce binary size\n- `/pr-review` - Review a pull request\n- `/qualcomm` - Build, test, or develop the QNN (Qualcomm AI Engine Direct) backend\n- `/executorch-kb` - Search tribal knowledge base (known issues, quant recipes, debugging guides)\n\nReference docs in `.claude/`: backends, runtime-api, quantization, llm-export, faq, tokenizers\nTribal knowledge wiki in `.wiki/`: synthesized from 2,200+ GitHub issues\n\nFor error messages, SoC compatibility questions, quantization recipes, and backend-specific debugging, consult the `/executorch-kb` skill (or read `.wiki/index.md` and navigate to the relevant article). The wiki contains tribal knowledge synthesized from 2,200+ GitHub issues with source citations. For build, test, profile, setup, or general API questions, use the dedicated skills above instead — the wiki is scoped to debugging and compatibility knowledge.\n\n## Quick Reference\n\n**Install Python package:**\n```bash\n./install_executorch.sh        # first time (or .bat on Windows)\npip install -e . --no-build-isolation  # subsequent installs\n```\n\n**Build C++ libraries:** see `CMakeLists.txt`; for LLM/ASR runners use `Makefile` and `CMakePresets.json`\n\n**Run tests:** `pytest -n auto` (Python), `ctest --output-on-failure` (C++)\n\n**Lint:** `lintrunner init && lintrunner -a`\n\nDetails: [docs/source/using-executorch-building-from-source.md](docs/source/using-executorch-building-from-source.md)\n\n## Naming\n\n- Use \"executorch\" (lowercase) or \"ExecuTorch\" (camel case)\n- Never \"ExecutorTorch\"\n- \"ET\" only when space-constrained (unofficial)\n\n## Commits\n\n- Only commit when explicitly asked\n- No bullet lists of changes; explain review order for large PRs, or omit for small ones\n- Disclose PR was authored with AI, include tool name.\n\n## Code Style\n\n- Minimal comments; code should be self-documenting\n- Comments only for non-obvious global context\n- No trivial (1-2 LOC) single-use helpers unless significantly improving readability\n- Explicit state management; no dynamic `setattr`/`getattr` patterns\n- Match existing style and architecture\n- Assume reader knows ExecuTorch/PyTorch basics\n\n**When uncertain: choose simpler, more concise.**\n","isInternal":false,"tokens":600,"sizeBytes":2411},{"name":"CLAUDE.md","path":"CLAUDE.md","rawUrl":"https://raw.githubusercontent.com/pytorch/executorch/HEAD/CLAUDE.md","title":"Claude Agent Guidelines & System Prompt","category":"claude-rule","format":"markdown","content":"# ExecuTorch\n\n## Skills\n- `/setup` - Set up environment\n- `/export` - Export model to .pte\n- `/building` - Build runners or C++ libs\n- `/profile` - Profile execution\n- `/cortex-m` - Build, test, or develop the Cortex-M backend\n- `/binary-size` - Analyze and reduce binary size\n- `/pr-review` - Review a pull request\n- `/qualcomm` - Build, test, or develop the QNN (Qualcomm AI Engine Direct) backend\n- `/executorch-kb` - Search tribal knowledge base (known issues, quant recipes, debugging guides)\n\nReference docs in `.claude/`: backends, runtime-api, quantization, llm-export, faq, tokenizers\nTribal knowledge wiki in `.wiki/`: synthesized from 2,200+ GitHub issues\n\nFor error messages, SoC compatibility questions, quantization recipes, and backend-specific debugging, consult the `/executorch-kb` skill (or read `.wiki/index.md` and navigate to the relevant article). The wiki contains tribal knowledge synthesized from 2,200+ GitHub issues with source citations. For build, test, profile, setup, or general API questions, use the dedicated skills above instead — the wiki is scoped to debugging and compatibility knowledge.\n\n## Quick Reference\n\n**Install Python package:**\n```bash\n./install_executorch.sh        # first time (or .bat on Windows)\npip install -e . --no-build-isolation  # subsequent installs\n```\n\n**Build C++ libraries:** see `CMakeLists.txt`; for LLM/ASR runners use `Makefile` and `CMakePresets.json`\n\n**Run tests:** `pytest -n auto` (Python), `ctest --output-on-failure` (C++)\n\n**Lint:** `lintrunner init && lintrunner -a`\n\nDetails: [docs/source/using-executorch-building-from-source.md](docs/source/using-executorch-building-from-source.md)\n\n## Naming\n\n- Use \"executorch\" (lowercase) or \"ExecuTorch\" (camel case)\n- Never \"ExecutorTorch\"\n- \"ET\" only when space-constrained (unofficial)\n\n## Commits\n\n- Only commit when explicitly asked\n- No bullet lists of changes; explain review order for large PRs, or omit for small ones\n- Disclose PR was authored with AI, include tool name.\n\n## Code Style\n\n- Minimal comments; code should be self-documenting\n- Comments only for non-obvious global context\n- No trivial (1-2 LOC) single-use helpers unless significantly improving readability\n- Explicit state management; no dynamic `setattr`/`getattr` patterns\n- Match existing style and architecture\n- Assume reader knows ExecuTorch/PyTorch basics\n\n**When uncertain: choose simpler, more concise.**\n","isInternal":false,"tokens":600,"sizeBytes":2411},{"name":"marketplace.json","path":".claude-plugin/marketplace.json","rawUrl":"https://raw.githubusercontent.com/pytorch/executorch/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/pytorch/executorch/HEAD/.claude-plugin/marketplace.json)","tokens":300,"sizeBytes":197},{"name":"plugin.json","path":".claude-plugin/plugin.json","rawUrl":"https://raw.githubusercontent.com/pytorch/executorch/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/pytorch/executorch/HEAD/.claude-plugin/plugin.json)","tokens":300,"sizeBytes":183},{"name":"mcp.json","path":".cursor/mcp.json","rawUrl":"https://raw.githubusercontent.com/pytorch/executorch/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/pytorch/executorch/HEAD/.cursor/mcp.json)","tokens":300,"sizeBytes":176}],"systemPromptSnippet":"<yakaai_skills repo=\"pytorch/executorch\">\n<!-- File: AGENTS.md (Tokens: ~600 | Category: root-instruction) -->\n# ExecuTorch\n\n## Skills\n- `/setup` - Set up environment\n- `/export` - Export model to .pte\n- `/building` - Build runners or C++ libs\n- `/profile` - Profile execution\n- `/cortex-m` - Build, test, or develop the Cortex-M backend\n- `/binary-size` - Analyze and reduce binary size\n- `/pr-review` - Review a pull request\n- `/qualcomm` - Build, test, or develop the QNN (Qualcomm AI Engine Direct) backend\n- `/executorch-kb` - Search tribal knowledge base (known issues, quant recipes, debugging guides)\n\nReference docs in `.claude/`: backends, runtime-api, quantization, llm-export, faq, tokenizers\nTribal knowledge wiki in `.wiki/`: synthesized from 2,200+ GitHub issues\n\nFor error messages, SoC compatibility questions, quantization recipes, and backend-specific debugging, consult the `/executorch-kb` skill (or read `.wiki/index.md` and navigate to the relevant article). The wiki contains tribal knowledge synthesized from 2,200+ GitHub issues with source citations. For build, test, profile, setup, or general API questions, use the dedicated skills above instead — the wiki is scoped to debugging and compatibility knowledge.\n\n## Quick Reference\n\n**Install Python package:**\n```bash\n./install_executorch.sh        # first time (or .bat on Windows)\npip install -e . --no-build-isolation  # subsequent installs\n```\n\n**Build C++ libraries:** see `CMakeLists.txt`; for LLM/ASR runners use `Makefile` and `CMakePresets.json`\n\n**Run tests:** `pytest -n auto` (Python), `ctest --output-on-failure` (C++)\n\n**Lint:** `lintrunner init && lintrunner -a`\n\nDetails: [docs/source/using-executorch-building-from-source.md](docs/source/using-executorch-building-from-source.md)\n\n## Naming\n\n- Use \"executorch\" (lowercase) or \"ExecuTorch\" (camel case)\n- Never \"ExecutorTorch\"\n- \"ET\" only when space-constrained (unofficial)\n\n## Commits\n\n- Only commit when explicitly asked\n- No bullet lists of changes; explain review order for large PRs, or omit for small ones\n- Disclose PR was authored with AI, include tool name.\n\n## Code Style\n\n- Minimal comments; code should be self-documenting\n- Comments only for non-obvious global context\n- No trivial (1-2 LOC) single-use helpers unless significantly improving readability\n- Explicit state management; no dynamic `setattr`/`getattr` patterns\n- Match existing style and architecture\n- Assume reader knows ExecuTorch/PyTorch basics\n\n**When uncertain: choose simpler, more concise.**\n\n<!-- File: CLAUDE.md (Tokens: ~600 | Category: claude-rule) -->\n# ExecuTorch\n\n## Skills\n- `/setup` - Set up environment\n- `/export` - Export model to .pte\n- `/building` - Build runners or C++ libs\n- `/profile` - Profile execution\n- `/cortex-m` - Build, test, or develop the Cortex-M backend\n- `/binary-size` - Analyze and reduce binary size\n- `/pr-review` - Review a pull request\n- `/qualcomm` - Build, test, or develop the QNN (Qualcomm AI Engine Direct) backend\n- `/executorch-kb` - Search tribal knowledge base (known issues, quant recipes, debugging guides)\n\nReference docs in `.claude/`: backends, runtime-api, quantization, llm-export, faq, tokenizers\nTribal knowledge wiki in `.wiki/`: synthesized from 2,200+ GitHub issues\n\nFor error messages, SoC compatibility questions, quantization recipes, and backend-specific debugging, consult the `/executorch-kb` skill (or read `.wiki/index.md` and navigate to the relevant article). The wiki contains tribal knowledge synthesized from 2,200+ GitHub issues with source citations. For build, test, profile, setup, or general API questions, use the dedicated skills above instead — the wiki is scoped to debugging and compatibility knowledge.\n\n## Quick Reference\n\n**Install Python package:**\n```bash\n./install_executorch.sh        # first time (or .bat on Windows)\npip install -e . --no-build-isolation  # subsequent installs\n```\n\n**Build C++ libraries:** see `CMakeLists.txt`; for LLM/ASR runners use `Makefile` and `CMakePresets.json`\n\n**Run tests:** `pytest -n auto` (Python), `ctest --output-on-failure` (C++)\n\n**Lint:** `lintrunner init && lintrunner -a`\n\nDetails: [docs/source/using-executorch-building-from-source.md](docs/source/using-executorch-building-from-source.md)\n\n## Naming\n\n- Use \"executorch\" (lowercase) or \"ExecuTorch\" (camel case)\n- Never \"ExecutorTorch\"\n- \"ET\" only when space-constrained (unofficial)\n\n## Commits\n\n- Only commit when explicitly asked\n- No bullet lists of changes; explain review order for large PRs, or omit for small ones\n- Disclose PR was authored with AI, include tool name.\n\n## Code Style\n\n- Minimal comments; code should be self-documenting\n- Comments only for non-obvious global context\n- No trivial (1-2 LOC) single-use helpers unless significantly improving readability\n- Explicit state management; no dynamic `setattr`/`getattr` patterns\n- Match existing style and architecture\n- Assume reader knows ExecuTorch/PyTorch basics\n\n**When uncertain: choose simpler, more concise.**\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/pytorch/executorch/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/pytorch/executorch/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/pytorch/executorch/HEAD/.cursor/mcp.json)\n</yakaai_skills>"}