[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79814Q3A9WQDGG8PFX6WWFW":3,"skill-same:01M79814Q3A9WQDGG8PFX6WWFW":53},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M79814Q3A9WQDGG8PFX6WWFW","helix-pyinstaller-packager",null,"Package the helix repository into PyInstaller onefile executables with the built-in skills tree embedded. Use when Codex needs to build, repair, validate, or document Windows, Linux, or macOS helix release artifacts; create platform-tagged release archives; explain PyInstaller's per-OS build requirement; or verify that packaged helix can load bundled skills.","Piagari\u002Fhelix","Piagari","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F129916910?v=4","01M7980QB9Y8WK5TSSRJDC7H1X","01M7980QCA2FWSBBSSM695Y10B",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FPiagari\u002Fhelix\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fhelix-pyinstaller-packager\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: helix-pyinstaller-packager\ndescription: Package the helix repository into PyInstaller onefile executables with the built-in skills tree embedded. Use when Codex needs to build, repair, validate, or document Windows, Linux, or macOS helix release artifacts; create platform-tagged release archives; explain PyInstaller's per-OS build requirement; or verify that packaged helix can load bundled skills.\n---\n\n# Helix PyInstaller Packager\n\n## Core Rule\n\nPyInstaller is not a cross-compiler. Build Windows artifacts on Windows, Linux artifacts on Linux, and macOS artifacts on macOS. Do not claim that one host can produce native executables for every OS unless a separate VM\u002Fcontainer\u002FCI runner for each target OS is actually used.\n\n## Expected Repository Shape\n\nUse this skill for a `helix` repository that has:\n\n- `pyproject.toml` managed by `uv`\n- CLI entrypoint `helix.cli:main`\n- source under `src\u002Fhelix\u002F`\n- a top-level `skills\u002F` directory that must be bundled as runtime data\n- a PyInstaller build script at `scripts\u002Fbuild-pyinstaller.py`\n- a PyInstaller spec at `packaging\u002Fhelix.spec`; if it is missing, the build script can create a default one\n\n## Packaging Mode\n\nBuild onefile executables by default. The release output should expose a single executable in each platform artifact directory, for example:\n\n```text\ndist\u002Fpyinstaller\u002Fhelix-windows-x86_64\u002Fhelix.exe\n```\n\nThe built-in `skills\u002F` tree must still be included as PyInstaller data. In onefile mode, do not expect a visible `_internal\u002Fskills` directory in the release output. PyInstaller extracts embedded data to a temporary `_MEI*` directory while the process is running, and `src\u002Fhelix\u002Fresources.py` must resolve frozen resources through `sys._MEIPASS`.\n\nThis mode reduces source exposure in the distributed artifact, but it is not encryption or a hard reverse-engineering boundary.\n\n## Workflow\n\n1. Inspect the repository before editing:\n   - `pyproject.toml`\n   - `packaging\u002Fhelix.spec`\n   - `src\u002Fhelix\u002Fresources.py`\n   - current resource path usage for `skills\u002F`\n2. Ensure `pyinstaller` is available through `uv`:\n   - If missing, add it as a dev dependency with `uv add --dev pyinstaller`.\n3. Ensure runtime resource lookup supports both source and frozen execution:\n   - Source mode should resolve the repository root.\n   - Frozen mode should resolve PyInstaller bundle resources.\n   - All runtime access to bundled `skills\u002F` should flow through one resource helper.\n4. Ensure the spec recursively includes `skills\u002F` as data:\n   - If `packaging\u002Fhelix.spec` is missing, let the build script create its default spec or create an equivalent spec before building.\n   - Include `SKILL.md`, `references\u002F`, `scripts\u002F`, `.json`, and other non-cache skill files.\n   - Exclude `__pycache__` and `.pyc`.\n   - Build a onefile `EXE` by passing `a.binaries` and `a.datas` into `EXE`; do not create a `COLLECT` onedir bundle for the default release path.\n5. Build the current OS executable with the repository build script:\n   - `uv run python scripts\u002Fbuild-pyinstaller.py --clean`\n6. Validate the artifact:\n   - Run packaged `helix --help`.\n   - Confirm the platform artifact directory contains the onefile executable.\n   - Run one command that loads bundled skill resources, such as `compare-perf` with tiny temp perf files.\n   - For agent-backed commands, use `--verbose` to confirm skill staging into `.codex\u002Fskills`, `.claude\u002Fskills`, or the selected backend directory.\n7. Report produced executable and release archive paths, validation results, and remaining environment limitations.\n\n## Build Script\n\nUse the repository-owned `scripts\u002Fbuild-pyinstaller.py` for the normal build path. The skill does not keep a second packaging implementation; keeping one script avoids drift between manual packaging, CI packaging, and skill-guided packaging.\n\nThe script:\n\n- detects the current OS and CPU architecture\n- creates a default `packaging\u002Fhelix.spec` when the requested spec is missing\n- invokes `uv run pyinstaller`\n- writes platform-tagged output under `dist\u002Fpyinstaller\u002F`\n- validates the expected onefile executable\n- creates a release archive unless `--no-archive` is used: `.zip` on Windows, `.tar.gz` on Linux and macOS\n- includes the onefile executable and `README.md` in the release directory and archive\n\nExamples:\n\n```bash\nuv run python scripts\u002Fbuild-pyinstaller.py --clean\nuv run python scripts\u002Fbuild-pyinstaller.py --clean --no-archive\nuv run python scripts\u002Fbuild-pyinstaller.py --clean --platform-tag linux-aarch64\n```\n\n## Multi-OS Release Procedure\n\nFor a release that needs Windows, Linux, and macOS artifacts:\n\n1. Run the same script on a Windows host.\n2. Run the same script on a Linux host.\n3. Run the same script on a macOS host.\n4. Collect the generated release archives from `dist\u002Fpyinstaller\u002F`.\n\nRead `references\u002Fplatform-builds.md` when explaining this limitation to users or designing CI jobs.\n\n## Validation Notes\n\n- A packaged CLI can be validated without NPU hardware by checking `--help`, bundled skills, and pure parser\u002Fcomparison commands.\n- Real `run-test`, `run-bench`, `verify`, and `optimize` validation requires a Python environment with the target dependencies, often including `torch`, `torch_npu`, `triton`, and Ascend\u002FCANN runtime.\n- A packaged executable does not include external agent CLIs. Users still need `codex`, `claude`, `opencode`, `pi`, or other selected backend tools available on `PATH`.\n- If generated tests or benchmarks are executed by a frozen app, ensure local execution uses an external Python interpreter, typically through `HELIX_PYTHON`.\n","# Helix PyInstaller Packager\n\n## Core Rule\n\nPyInstaller is not a cross-compiler. Build Windows artifacts on Windows, Linux artifacts on Linux, and macOS artifacts on macOS. Do not claim that one host can produce native executables for every OS unless a separate VM\u002Fcontainer\u002FCI runner for each target OS is actually used.\n\n## Expected Repository Shape\n\nUse this skill for a `helix` repository that has:\n\n- `pyproject.toml` managed by `uv`\n- CLI entrypoint `helix.cli:main`\n- source under `src\u002Fhelix\u002F`\n- a top-level `skills\u002F` directory that must be bundled as runtime data\n- a PyInstaller build script at `scripts\u002Fbuild-pyinstaller.py`\n- a PyInstaller spec at `packaging\u002Fhelix.spec`; if it is missing, the build script can create a default one\n\n## Packaging Mode\n\nBuild onefile executables by default. The release output should expose a single executable in each platform artifact directory, for example:\n\n```text\ndist\u002Fpyinstaller\u002Fhelix-windows-x86_64\u002Fhelix.exe\n```\n\nThe built-in `skills\u002F` tree must still be included as PyInstaller data. In onefile mode, do not expect a visible `_internal\u002Fskills` directory in the release output. PyInstaller extracts embedded data to a temporary `_MEI*` directory while the process is running, and `src\u002Fhelix\u002Fresources.py` must resolve frozen resources through `sys._MEIPASS`.\n\nThis mode reduces source exposure in the distributed artifact, but it is not encryption or a hard reverse-engineering boundary.\n\n## Workflow\n\n1. Inspect the repository before editing:\n   - `pyproject.toml`\n   - `packaging\u002Fhelix.spec`\n   - `src\u002Fhelix\u002Fresources.py`\n   - current resource path usage for `skills\u002F`\n2. Ensure `pyinstaller` is available through `uv`:\n   - If missing, add it as a dev dependency with `uv add --dev pyinstaller`.\n3. Ensure runtime resource lookup supports both source and frozen execution:\n   - Source mode should resolve the repository root.\n   - Frozen mode should resolve PyInstaller bundle resources.\n   - All runtime access to bundled `skills\u002F` should flow through one resource helper.\n4. Ensure the spec recursively includes `skills\u002F` as data:\n   - If `packaging\u002Fhelix.spec` is missing, let the build script create its default spec or create an equivalent spec before building.\n   - Include `SKILL.md`, `references\u002F`, `scripts\u002F`, `.json`, and other non-cache skill files.\n   - Exclude `__pycache__` and `.pyc`.\n   - Build a onefile `EXE` by passing `a.binaries` and `a.datas` into `EXE`; do not create a `COLLECT` onedir bundle for the default release path.\n5. Build the current OS executable with the repository build script:\n   - `uv run python scripts\u002Fbuild-pyinstaller.py --clean`\n6. Validate the artifact:\n   - Run packaged `helix --help`.\n   - Confirm the platform artifact directory contains the onefile executable.\n   - Run one command that loads bundled skill resources, such as `compare-perf` with tiny temp perf files.\n   - For agent-backed commands, use `--verbose` to confirm skill staging into `.codex\u002Fskills`, `.claude\u002Fskills`, or the selected backend directory.\n7. Report produced executable and release archive paths, validation results, and remaining environment limitations.\n\n## Build Script\n\nUse the repository-owned `scripts\u002Fbuild-pyinstaller.py` for the normal build path. The skill does not keep a second packaging implementation; keeping one script avoids drift between manual packaging, CI packaging, and skill-guided packaging.\n\nThe script:\n\n- detects the current OS and CPU architecture\n- creates a default `packaging\u002Fhelix.spec` when the requested spec is missing\n- invokes `uv run pyinstaller`\n- writes platform-tagged output under `dist\u002Fpyinstaller\u002F`\n- validates the expected onefile executable\n- creates a release archive unless `--no-archive` is used: `.zip` on Windows, `.tar.gz` on Linux and macOS\n- includes the onefile executable and `README.md` in the release directory and archive\n\nExamples:\n\n```bash\nuv run python scripts\u002Fbuild-pyinstaller.py --clean\nuv run python scripts\u002Fbuild-pyinstaller.py --clean --no-archive\nuv run python scripts\u002Fbuild-pyinstaller.py --clean --platform-tag linux-aarch64\n```\n\n## Multi-OS Release Procedure\n\nFor a release that needs Windows, Linux, and macOS artifacts:\n\n1. Run the same script on a Windows host.\n2. Run the same script on a Linux host.\n3. Run the same script on a macOS host.\n4. Collect the generated release archives from `dist\u002Fpyinstaller\u002F`.\n\nRead `references\u002Fplatform-builds.md` when explaining this limitation to users or designing CI jobs.\n\n## Validation Notes\n\n- A packaged CLI can be validated without NPU hardware by checking `--help`, bundled skills, and pure parser\u002Fcomparison commands.\n- Real `run-test`, `run-bench`, `verify`, and `optimize` validation requires a Python environment with the target dependencies, often including `torch`, `torch_npu`, `triton`, and Ascend\u002FCANN runtime.\n- A packaged executable does not include external agent CLIs. Users still need `codex`, `claude`, `opencode`, `pi`, or other selected backend tools available on `PATH`.\n- If generated tests or benchmarks are executed by a frozen app, ensure local execution uses an external Python interpreter, typically through `HELIX_PYTHON`.\n",{"name":5,"description":7},"main","5d6a3de8bf1eb43267adffc8e27a87d85fd81a4b",".codex\u002Fskills\u002Fhelix-pyinstaller-packager","https:\u002F\u002Fgithub.com\u002FPiagari\u002Fhelix","https:\u002F\u002Fgithub.com\u002FPiagari","2026-07-16 20:07:51",{"source":8,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add Piagari\u002Fhelix --skill helix-pyinstaller-packager",{"tool":35,"command":36},"bunx","bunx skills add Piagari\u002Fhelix --skill helix-pyinstaller-packager",{"tool":38,"command":39},"pnpm","pnpm dlx skills add Piagari\u002Fhelix --skill helix-pyinstaller-packager","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPiagari\u002Fhelix\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fhelix-pyinstaller-packager\u002FSKILL.md",true,[43,49],{"path":44,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":47,"sourceHtmlUrl":48},"agents\u002Fopenai.yaml","REFERENCE","参考文档",329,"https:\u002F\u002Fgithub.com\u002FPiagari\u002Fhelix\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fhelix-pyinstaller-packager\u002Fagents\u002Fopenai.yaml",{"path":50,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fplatform-builds.md",3101,"https:\u002F\u002Fgithub.com\u002FPiagari\u002Fhelix\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fhelix-pyinstaller-packager\u002Freferences\u002Fplatform-builds.md",[54,61,68,75,82,87],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":18},"01M7985HE7EHEXX41M79MSZCMJ","triton-npu-repair-guide","Heuristic fixes for Ascend Triton compile\u002FJIT\u002Fkernel errors and numerical precision mismatches when editing or converting the operator. Does not replace ascend-npu-gen-test, ascend-npu-gen-bench, or harness specs.","https:\u002F\u002Fgithub.com\u002FPiagari\u002Fhelix\u002Fblob\u002Fmain\u002Fskills\u002Ftriton\u002Ftriton-npu-repair-guide\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M7985DFYH5RRCDFTWAFYDFGA","triton-npu-optimize","Iteratively optimize a Triton Ascend NPU operator with correctness and performance gates. Use for operator optimization tasks that need repeated correctness validation, benchmark validation, multi-round experiment tracking, reusable optimization notes, and profiler-backed performance analysis when benchmark results need deeper explanation.","https:\u002F\u002Fgithub.com\u002FPiagari\u002Fhelix\u002Fblob\u002Fmain\u002Fskills\u002Ftriton\u002Ftriton-npu-optimize\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M79858YFWE96X7ZA1BJRVDEX","triton-npu-optimize-knowledge","Generic reference-only optimize knowledge for pattern triage and evidence-backed symptom routing. This skill does not define optimize workflow or own round artifacts.","https:\u002F\u002Fgithub.com\u002FPiagari\u002Fhelix\u002Fblob\u002Fmain\u002Fskills\u002Ftriton\u002Ftriton-npu-optimize-knowledge\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M79854BZPJ0XY5PTPQWTCY7Q","triton-npu-optimize-knowledge-v3","Generic reference-only optimize knowledge (v3 working copy) for pattern triage and evidence-backed symptom routing. This skill does not define optimize workflow or own round artifacts; prefer this tree for ongoing knowledge updates.","https:\u002F\u002Fgithub.com\u002FPiagari\u002Fhelix\u002Fblob\u002Fmain\u002Fskills\u002Ftriton\u002Ftriton-npu-optimize-knowledge-v3\u002FSKILL.md",[],[],{"skillNo":83,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M79850QM6QZP8VP6ZRQBQHCT","https:\u002F\u002Fgithub.com\u002FPiagari\u002Fhelix\u002Fblob\u002Fmain\u002Fskills\u002Ftriton\u002Ftriton-npu-optimize-knowledge-v2\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":18},"01M7984W6SW3BZM5EXGRJ1VBXY","triton-npu-convert-pytorch-operator","Convert one PyTorch operator into a Triton NPU-backed PyTorch operator, preserve the trailing input-helper block, and validate the converted output through standalone or differential testing.","https:\u002F\u002Fgithub.com\u002FPiagari\u002Fhelix\u002Fblob\u002Fmain\u002Fskills\u002Ftriton\u002Ftriton-npu-convert-pytorch-operator\u002FSKILL.md",[],[]]