[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7980SCPYY6XRHX9DFBTK4Y5":3,"skill-same:01M7980SCPYY6XRHX9DFBTK4Y5":43},{"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},"01M7980SCPYY6XRHX9DFBTK4Y5","create-optimize-pattern",null,"Create new optimization pattern cards or symptom cards for the helix optimize knowledge base. Use when adding a new pattern card under skills\u002Ftriton\u002Ftriton-npu-optimize-knowledge\u002Freferences\u002Fpatterns\u002F, skills\u002Ftorch\u002Ftorch-npu-optimize-knowledge\u002Freferences\u002Fpatterns\u002F, skills\u002Ftriton\u002Ftriton-npu-cann-ext-api-patterns\u002Freferences\u002Fpatterns\u002F, or a new symptom card under skills\u002Ftriton\u002Ftriton-npu-optimize-knowledge\u002Freferences\u002Fsymptoms\u002F.","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\u002Fcreate-optimize-pattern\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: create-optimize-pattern\ndescription: Create new optimization pattern cards or symptom cards for the helix optimize knowledge base. Use when adding a new pattern card under skills\u002Ftriton\u002Ftriton-npu-optimize-knowledge\u002Freferences\u002Fpatterns\u002F, skills\u002Ftorch\u002Ftorch-npu-optimize-knowledge\u002Freferences\u002Fpatterns\u002F, skills\u002Ftriton\u002Ftriton-npu-cann-ext-api-patterns\u002Freferences\u002Fpatterns\u002F, or a new symptom card under skills\u002Ftriton\u002Ftriton-npu-optimize-knowledge\u002Freferences\u002Fsymptoms\u002F.\n---\n\n# Create Optimize Pattern \u002F Symptom Card\n\nUse this skill when creating new optimization pattern cards or symptom cards. Do not use for editing existing cards — edit those directly.\n\n## Target Directories\n\nPlace new cards under the appropriate directory:\n\n| Card Type | Skill | Directory |\n|---|---|---|\n| Generic optimize pattern | `triton-npu-optimize-knowledge` | `skills\u002Ftriton\u002Ftriton-npu-optimize-knowledge\u002Freferences\u002Fpatterns\u002F` |\n| Torch NPU optimize pattern | `torch-npu-optimize-knowledge` | `skills\u002Ftorch\u002Ftorch-npu-optimize-knowledge\u002Freferences\u002Fpatterns\u002F` |\n| CANN extension API pattern | `triton-npu-cann-ext-api-patterns` | `skills\u002Ftriton\u002Ftriton-npu-cann-ext-api-patterns\u002Freferences\u002Fpatterns\u002F` |\n| Generic optimize symptom | `triton-npu-optimize-knowledge` | `skills\u002Ftriton\u002Ftriton-npu-optimize-knowledge\u002Freferences\u002Fsymptoms\u002F` |\n\n## Pattern Card Template\n\n```md\n---\npriority: high|normal  # optional — omit to default to normal\n---\n\n# \u003CHuman Title>\n\n## Summary\n\n## Use When\n\n## Avoid When\n\n## Signals\n### Code\n### Profile\n### IR\n\n## Related Patterns\n\n## What To Verify After Applying\n```\n\n### Pattern Card Rules\n\n- **`## Summary` and `## Use When` are required.** All other predefined sections are optional.\n- **`## Summary`** describes WHAT the pattern is\u002Fdoes. Keep it to 1-2 sentences. Do not include signal-like language or usage instructions.\n- **`## Use When`** describes WHEN to apply the pattern — detection conditions. Must be orthogonal to `## Summary`.\n- `priority: high|normal` in frontmatter; omit to default to `normal`. `priority` only affects generated index rendering. The generated `pattern_index.md` must include a `## High Priority Patterns` section that lists cards marked `high`.\n- `## Use When`, `## Avoid When`, and signal subsections work best as bullet lists. Both `- item` and `1. item` list styles are accepted by the generator.\n- Free-form sections are allowed for examples, background, or architecture notes — they are ignored by the index generator but kept in the authored card.\n\n## Symptom Card Template\n\n```md\n# \u003CHuman Title>\n\n## Summary\n\n## Evidence To Confirm\n\n## Candidate Pattern Directions\n\n## Common Non-Matches\n```\n\n### Symptom Card Rules\n\n- **`## Summary`, `## Evidence To Confirm`, and `## Candidate Pattern Directions` are required.**\n- `## Common Non-Matches` is optional.\n- Keep predefined section names exact.\n\n## After Creation\n\n1. Regenerate the affected index files:\n\n```bash\nbash scripts\u002Fupdate-optimize-knowledge-indices.sh\n```\n\n2. **Never hand-edit** `skills\u002F*\u002Freferences\u002Fpattern_index.md` or `skills\u002F*\u002Freferences\u002Fsymptom_index.md` — they are generated.\n\n## Reference\n\nFor detailed authoring notes, see `docs\u002Fnotes\u002F2026-04-29-optimize-pattern-card-authoring.md`.\n","# Create Optimize Pattern \u002F Symptom Card\n\nUse this skill when creating new optimization pattern cards or symptom cards. Do not use for editing existing cards — edit those directly.\n\n## Target Directories\n\nPlace new cards under the appropriate directory:\n\n| Card Type | Skill | Directory |\n|---|---|---|\n| Generic optimize pattern | `triton-npu-optimize-knowledge` | `skills\u002Ftriton\u002Ftriton-npu-optimize-knowledge\u002Freferences\u002Fpatterns\u002F` |\n| Torch NPU optimize pattern | `torch-npu-optimize-knowledge` | `skills\u002Ftorch\u002Ftorch-npu-optimize-knowledge\u002Freferences\u002Fpatterns\u002F` |\n| CANN extension API pattern | `triton-npu-cann-ext-api-patterns` | `skills\u002Ftriton\u002Ftriton-npu-cann-ext-api-patterns\u002Freferences\u002Fpatterns\u002F` |\n| Generic optimize symptom | `triton-npu-optimize-knowledge` | `skills\u002Ftriton\u002Ftriton-npu-optimize-knowledge\u002Freferences\u002Fsymptoms\u002F` |\n\n## Pattern Card Template\n\n```md\n---\npriority: high|normal  # optional — omit to default to normal\n---\n\n# \u003CHuman Title>\n\n## Summary\n\n## Use When\n\n## Avoid When\n\n## Signals\n### Code\n### Profile\n### IR\n\n## Related Patterns\n\n## What To Verify After Applying\n```\n\n### Pattern Card Rules\n\n- **`## Summary` and `## Use When` are required.** All other predefined sections are optional.\n- **`## Summary`** describes WHAT the pattern is\u002Fdoes. Keep it to 1-2 sentences. Do not include signal-like language or usage instructions.\n- **`## Use When`** describes WHEN to apply the pattern — detection conditions. Must be orthogonal to `## Summary`.\n- `priority: high|normal` in frontmatter; omit to default to `normal`. `priority` only affects generated index rendering. The generated `pattern_index.md` must include a `## High Priority Patterns` section that lists cards marked `high`.\n- `## Use When`, `## Avoid When`, and signal subsections work best as bullet lists. Both `- item` and `1. item` list styles are accepted by the generator.\n- Free-form sections are allowed for examples, background, or architecture notes — they are ignored by the index generator but kept in the authored card.\n\n## Symptom Card Template\n\n```md\n# \u003CHuman Title>\n\n## Summary\n\n## Evidence To Confirm\n\n## Candidate Pattern Directions\n\n## Common Non-Matches\n```\n\n### Symptom Card Rules\n\n- **`## Summary`, `## Evidence To Confirm`, and `## Candidate Pattern Directions` are required.**\n- `## Common Non-Matches` is optional.\n- Keep predefined section names exact.\n\n## After Creation\n\n1. Regenerate the affected index files:\n\n```bash\nbash scripts\u002Fupdate-optimize-knowledge-indices.sh\n```\n\n2. **Never hand-edit** `skills\u002F*\u002Freferences\u002Fpattern_index.md` or `skills\u002F*\u002Freferences\u002Fsymptom_index.md` — they are generated.\n\n## Reference\n\nFor detailed authoring notes, see `docs\u002Fnotes\u002F2026-04-29-optimize-pattern-card-authoring.md`.\n",{"name":5,"description":7},"main","5d6a3de8bf1eb43267adffc8e27a87d85fd81a4b",".codex\u002Fskills\u002Fcreate-optimize-pattern","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 create-optimize-pattern",{"tool":35,"command":36},"bunx","bunx skills add Piagari\u002Fhelix --skill create-optimize-pattern",{"tool":38,"command":39},"pnpm","pnpm dlx skills add Piagari\u002Fhelix --skill create-optimize-pattern","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPiagari\u002Fhelix\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fcreate-optimize-pattern\u002FSKILL.md",true,[],[44,51,58,65,72,77],{"skillNo":45,"name":46,"nameZh":6,"description":47,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":48,"categories":49,"keywords":50,"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":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"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":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"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":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"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":73,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":18},"01M79850QM6QZP8VP6ZRQBQHCT","https:\u002F\u002Fgithub.com\u002FPiagari\u002Fhelix\u002Fblob\u002Fmain\u002Fskills\u002Ftriton\u002Ftriton-npu-optimize-knowledge-v2\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"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",[],[]]