[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69979ENN9XYV6AZACX1RK06":3,"skill-same:01M69979ENN9XYV6AZACX1RK06":74},{"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":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":49,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M69979ENN9XYV6AZACX1RK06","lit-to-bazel",null,"Converts MLIR lit test files to `bazel run` commands. Use when you need to convert a failing MLIR lit test target (containing RUN lines) to a shell command whose flags can be modified for further analysis and debugging.","google\u002Fheir","google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","01M698VYEFDM0VJBZDYYJ2T83S","Google","01M69973GM7GX7K1C2GYBW099F",948,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fheir\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flit_to_bazel\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"lit to bazel","bazel","lit","failing","mlir","when","shell command","for","can","you","commands","files","use","command","convert","shell","analysis","run","debugging","test","2026-11-10 10:12:30",false,"---\nname: lit-to-bazel\ndescription: >-\n  Converts MLIR lit test files to `bazel run` commands. Use when you need to\n  convert a failing MLIR lit test target (containing RUN lines) to a shell\n  command whose flags can be modified for further analysis and debugging.\n---\n\n# Lit To Bazel\n\n## Overview\n\nThis skill guides the agent in using the `lit_to_bazel` tool to convert MLIR\ntest files to executable commands.\n\n## Usage\n\n### Converting a Test File\n\nTo convert a lit test file to a `bazel run` command, use the following command\nrecipes:\n\n```bash\nbazel run \u002F\u002Fthird_party\u002Fheir\u002Fscripts:lit_to_bazel -- {test_file_path}\n```\n\nReplace `{test_file_path}` with the absolute path to the test file. The absolute\npath is necessary because the `bazel run` command runs relative to its runfiles\ndirectory, and so a relative path will not be relative to the VCS root of the\nproject.\n\n## Gotchas\n\n- **Absolute Paths**: The tool replaces `%s` in RUN lines with the absolute path\n  of the test file to ensure it works in the sandbox.\n- **Piped RUN commands**: The tool supports piped RUN lines, such as piping\n  heir-opt into heir-translate.\n- **Complex RUN commands**: Some very complex RUN lines are not supported, such\n  as lit test files with multiple RUN lines that interact via writing to and\n  reading from temporary files. When encountering situations like this, you\n  should stop and warn the user.\n- **Non-lit tests**: Some test targets are not lit tests, and these do not need\n  the `lit_to_bazel` tool.\n\n```markdown\nCopy this checklist and track progress:\n\n- [ ] Step 1: Identify the test file to convert.\n- [ ] Step 2: Run the `lit_to_bazel` tool on the file.\n- [ ] Step 3: Inspect the generated command or run it.\n- [ ] Step 4: Verify execution results.\n```\n\n\u003C!-- mdformat global-off -->\n","# Lit To Bazel\n\n## Overview\n\nThis skill guides the agent in using the `lit_to_bazel` tool to convert MLIR\ntest files to executable commands.\n\n## Usage\n\n### Converting a Test File\n\nTo convert a lit test file to a `bazel run` command, use the following command\nrecipes:\n\n```bash\nbazel run \u002F\u002Fthird_party\u002Fheir\u002Fscripts:lit_to_bazel -- {test_file_path}\n```\n\nReplace `{test_file_path}` with the absolute path to the test file. The absolute\npath is necessary because the `bazel run` command runs relative to its runfiles\ndirectory, and so a relative path will not be relative to the VCS root of the\nproject.\n\n## Gotchas\n\n- **Absolute Paths**: The tool replaces `%s` in RUN lines with the absolute path\n  of the test file to ensure it works in the sandbox.\n- **Piped RUN commands**: The tool supports piped RUN lines, such as piping\n  heir-opt into heir-translate.\n- **Complex RUN commands**: Some very complex RUN lines are not supported, such\n  as lit test files with multiple RUN lines that interact via writing to and\n  reading from temporary files. When encountering situations like this, you\n  should stop and warn the user.\n- **Non-lit tests**: Some test targets are not lit tests, and these do not need\n  the `lit_to_bazel` tool.\n\n```markdown\nCopy this checklist and track progress:\n\n- [ ] Step 1: Identify the test file to convert.\n- [ ] Step 2: Run the `lit_to_bazel` tool on the file.\n- [ ] Step 3: Inspect the generated command or run it.\n- [ ] Step 4: Verify execution results.\n```\n\n\u003C!-- mdformat global-off -->\n",{"name":5,"description":7},"main","016c0b1e281a20df45b81c31ec893cf1198ff10b",".agents\u002Fskills\u002Flit_to_bazel",185,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fheir","https:\u002F\u002Fheir.dev\u002F","https:\u002F\u002Fgithub.com\u002Fgoogle","https:\u002F\u002Fopensource.google\u002F","Google ❤️ Open Source","2026-11-15 00:27:48",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add google\u002Fheir --skill lit-to-bazel",{"tool":60,"command":61},"bunx","bunx skills add google\u002Fheir --skill lit-to-bazel",{"tool":63,"command":64},"pnpm","pnpm dlx skills add google\u002Fheir --skill lit-to-bazel","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fheir\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Flit_to_bazel\u002FSKILL.md",true,[68],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"bmad-skill-manifest.yaml","REFERENCE","参考文档",922,"https:\u002F\u002Fgithub.com\u002Fsherryswift1019-gif\u002FAI-DZHT\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fbmad-agent-architect\u002Fbmad-skill-manifest.yaml",[75,90,109],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":39},"01M6997B7NY7K5V08MMTMAE1ZS","reproduce-failure","Describes a decision tree of steps and skills to utilize when, starting from a test failure or the failure of `bazel run` command using heir-opt, you would like to produce a reproducing input IR that fails on a particular compiler pass.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fheir\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freproduce_failure\u002FSKILL.md",[],[82,83,84,38,36,85,86,20,87,32,88,28,89,24],"reproduce","reproduce failure","opt","produce","compiler","decision","input","tree",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":101,"publishedAt":39},"01M699782STZMR7Y5YT8M2EM4Q","e2e-to-bazel","Converts end-to-end (e2e) test targets or paths to `bazel run` commands for `heir-opt`. Use when you need to convert an e2e test target (where flags are defined in the BUILD file) to a shell command whose flags can be modified for further analysis and debugging.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fheir\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fe2e_to_bazel\u002FSKILL.md",[96],{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[102,20,103,27,28,104,26,105,25,106,24,84,107,38,37,108,35,33,32,31],"e2e to bazel","e2e","build","targets","end","e2e test","file",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":39},"01M69976BPZSY7W3H87Q5ER5R1","dump-intermediate-ir","Augments a `bazel run` CLI command for `heir-opt` with additional flags that dump the IR before each compiler pass, allowing the agent to inspect intermediate IR during compilation, identify a particular pass at which the pipeline fails, or extract the corresponding IR input to a particular pass for further debugging.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fheir\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdump_intermediate_ir\u002FSKILL.md",[],[116,117,118,119,120,37,36,86,20,121,32,122,123,88,124,125,126,26,84],"intermediate","dump","dump intermediate ir","cli","inspect","pipeline","extract","flags","with","which","at"]