[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6990A2REHS7ZK5FND1NPE34":3,"skill-same:01M6990A2REHS7ZK5FND1NPE34":96},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":58,"ownerHtmlUrl":59,"ownerBlogUrl":60,"ownerDescription":61,"updatedAt":62,"install":63,"resources":75},"01M6990A2REHS7ZK5FND1NPE34","egm-drift-report",null,"Runs drift detection on all design documents to check for document and code consistency. Produces an actionable report with differences. Use when the user asks to detect drift or check for consistency across all design documents or READMEs in a directory.","google\u002Felephant-goldfish-model","google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","01M698VYEFDM0VJBZDYYJ2T83S","Google","01M698ZCD81WA4TBED15ZT6D76",19058,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Felephant-goldfish-model\u002Fblob\u002Fmain\u002Fskills\u002Fegm-drift-report\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000034","行政与办公人员",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"egm drift report","report","drift","when","design","drift detection","for","true","consistency","with","actionable","detect","across","document","use","check","detection","code","documents","directory","2026-11-10 10:12:30",false,"---\nname: egm-drift-report\nlicense: Apache-2.0\ndisable-model-invocation: true\ndescription: >-\n  Runs drift detection on all design documents to check for document and\n  code consistency. Produces an actionable report with differences. Use when the\n  user asks to detect drift or check for consistency across all design documents\n  or READMEs in a directory.\n---\n\n# Detect Drift In Designs and Code\n\nWhen running in Codex or ChatGPT Work, first read [Codex integration](..\u002F..\u002Fdocs\u002Fcodex.md).\nIn Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}\u002Fdocs\u002Fclaude.md` first.\n\nWhen the user asks to detect drift across all designs or a set of READMEs, the\ngoal is to identify all instances where the codebase has diverged or failed to\nimplement the specifications described by those designs or READMEs.\n\n1.  **Check Input**: Verify a directory containing design documents or READMEs\n    is provided. If not provided, ask the user to specify the target directory.\n2.  **List Documents**: List all files in the design directory.\n3.  **Analyze**: For EACH design document:\n\n    *   **Contextualize**: Read the design document. Identify the intent,\n        proposed changes, and specific filenames\u002Fsymbols mentioned.\n    *   **Locate Source**: Find the corresponding source code files in the\n        source tree. If paths aren't explicit, use code search or grep to\n        locate the relevant classes, functions, or API endpoints mentioned in\n        the doc. Prompt the user to add missing links to the document to make\n        future detection cheaper.\n    *   **Verify**: Read the current state of those source files.\n    *   **Detect Drift**: Compare the design vs. reality. Look specifically for:\n        *   Missing Features: Logic described in the doc but absent in the code.\n        *   Incomplete Models: Dataclasses\u002FClasses\u002FStructs\u002FProtos missing fields\n            specified in the design.\n        *   Logic Shortcuts: Hardcoded values where dynamic logic was planned.\n        *   Architectural Divergence: Implementation using different\n            patterns\u002Flibraries than proposed.\n    *   **Filter**: Report ONLY the differences. Do not describe what is working\n        or what matches. If the code matches the design perfectly, output \"No\n        drift detected.\"\n\n4.  **Report**: Produce a single report listing all discrepancies found.\n\n    *   Append the analysis for each file to `{YYYY-MM-DD}_DRIFT_REPORT.md`\n        using your file-writing tool.\n    *   Strict Format:\n\n        ```markdown\n        ## \u003CDESIGN_DOC_NAME>\n\n        \u003CBulleted list of specific divergences found>\n        \u003COr \"No drift detected\">\n        ```\n\n5.  **Guidance**\n\n    -   Be rigorous. If a design doc mentions a specific object, field or file\n        name and the code doesn't have it, that is a reportable drift. Double\n        check for coverage. If there is some part of the logic that is not\n        referenced in a design or README, this is a reportable drift.\n    -   Read files liberally to ensure you are looking at the current state\n        of the code, not relying on memory.\n    -   Process the files sequentially to ensure the tool output buffer doesn't\n        overflow.\n","# Detect Drift In Designs and Code\n\nWhen running in Codex or ChatGPT Work, first read [Codex integration](..\u002F..\u002Fdocs\u002Fcodex.md).\nIn Claude Code or Cowork, read `${CLAUDE_PLUGIN_ROOT}\u002Fdocs\u002Fclaude.md` first.\n\nWhen the user asks to detect drift across all designs or a set of READMEs, the\ngoal is to identify all instances where the codebase has diverged or failed to\nimplement the specifications described by those designs or READMEs.\n\n1.  **Check Input**: Verify a directory containing design documents or READMEs\n    is provided. If not provided, ask the user to specify the target directory.\n2.  **List Documents**: List all files in the design directory.\n3.  **Analyze**: For EACH design document:\n\n    *   **Contextualize**: Read the design document. Identify the intent,\n        proposed changes, and specific filenames\u002Fsymbols mentioned.\n    *   **Locate Source**: Find the corresponding source code files in the\n        source tree. If paths aren't explicit, use code search or grep to\n        locate the relevant classes, functions, or API endpoints mentioned in\n        the doc. Prompt the user to add missing links to the document to make\n        future detection cheaper.\n    *   **Verify**: Read the current state of those source files.\n    *   **Detect Drift**: Compare the design vs. reality. Look specifically for:\n        *   Missing Features: Logic described in the doc but absent in the code.\n        *   Incomplete Models: Dataclasses\u002FClasses\u002FStructs\u002FProtos missing fields\n            specified in the design.\n        *   Logic Shortcuts: Hardcoded values where dynamic logic was planned.\n        *   Architectural Divergence: Implementation using different\n            patterns\u002Flibraries than proposed.\n    *   **Filter**: Report ONLY the differences. Do not describe what is working\n        or what matches. If the code matches the design perfectly, output \"No\n        drift detected.\"\n\n4.  **Report**: Produce a single report listing all discrepancies found.\n\n    *   Append the analysis for each file to `{YYYY-MM-DD}_DRIFT_REPORT.md`\n        using your file-writing tool.\n    *   Strict Format:\n\n        ```markdown\n        ## \u003CDESIGN_DOC_NAME>\n\n        \u003CBulleted list of specific divergences found>\n        \u003COr \"No drift detected\">\n        ```\n\n5.  **Guidance**\n\n    -   Be rigorous. If a design doc mentions a specific object, field or file\n        name and the code doesn't have it, that is a reportable drift. Double\n        check for coverage. If there is some part of the logic that is not\n        referenced in a design or README, this is a reportable drift.\n    -   Read files liberally to ensure you are looking at the current state\n        of the code, not relying on memory.\n    -   Process the files sequentially to ensure the tool output buffer doesn't\n        overflow.\n",{"name":5,"license":15,"description":7,"disable-model-invocation":52},true,"main","403d8881d62022490637d740657b33f01e321ea8","skills\u002Fegm-drift-report",1416,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Felephant-goldfish-model","https:\u002F\u002Fegm.dev","https:\u002F\u002Fgithub.com\u002Fgoogle","https:\u002F\u002Fopensource.google\u002F","Google ❤️ Open Source","2026-11-14 17:40:03",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":52},[65,68,71],{"tool":66,"command":67},"npx","npx skills add google\u002Felephant-goldfish-model --skill egm-drift-report",{"tool":69,"command":70},"bunx","bunx skills add google\u002Felephant-goldfish-model --skill egm-drift-report",{"tool":72,"command":73},"pnpm","pnpm dlx skills add google\u002Felephant-goldfish-model --skill egm-drift-report","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgoogle\u002Felephant-goldfish-model\u002Fblob\u002Fmain\u002Fskills\u002Fegm-drift-report\u002FSKILL.md",[76,82,88,92],{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"agents\u002Fopenai.yaml","REFERENCE","参考文档",204,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Felephant-goldfish-model\u002Fblob\u002Fmain\u002Fskills\u002Fegm-drift-report\u002Fagents\u002Fopenai.yaml",{"path":83,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":86,"sourceHtmlUrl":87},"assets\u002Ficon.svg","ASSET","资产文件",281,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Felephant-goldfish-model\u002Fblob\u002Fmain\u002Fskills\u002Fegm-drift-report\u002Fassets\u002Ficon.svg",{"path":89,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":90,"sourceHtmlUrl":91},"test_scenarios.yaml",1327,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Felephant-goldfish-model\u002Fblob\u002Fmain\u002Fskills\u002Fegm-drift-report\u002Ftest_scenarios.yaml",{"path":93,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":94,"sourceHtmlUrl":95},"TEST.md",130,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Felephant-goldfish-model\u002Fblob\u002Fmain\u002Fskills\u002Fegm-drift-report\u002FTEST.md",[97,118,143,165,195,212],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":47},"01M6990JCG2ES0P7VY8THHMZK7","egm-review","Orchestrates the EGM Goldfish Review Protocol. Used as part of the EGM process to perform design document reviews. Executes five review phases: Initial Zoom Out Review, Comprehension Review, Design Critique, Intermediate Zoom Out Review, and Implementation Readiness.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Felephant-goldfish-model\u002Fblob\u002Fmain\u002Fskills\u002Fegm-review\u002FSKILL.md",[],[104,105,31,106,107,108,109,34,40,110,111,112,113,114,115,116,117],"egm review","review","reviews","critique","design critique","as","zoom","readiness","zoom out","Implementation Readiness","process","protocol","implementation","intermediate",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":129,"publishedAt":47},"01M6990F8C4RFVX08PD65ECC05","egm-review-loop","Executes the Antagonistic-Review process from the Elephant-Goldfish Model (EGM) via an automated multi-agent review loop to audit documents against qualitative standards and structural templates, and automatically apply approved fixes. Use when reviewing design docs, READMEs, feature specifications, implementation plans, or verifying document completeness and tone.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Felephant-goldfish-model\u002Fblob\u002Fmain\u002Fskills\u002Fegm-review-loop\u002FSKILL.md",[124],{"categoryNo":125,"categoryName":126,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[130,104,105,131,132,31,133,134,45,135,136,137,138,139,140,141,34,142,41,40,30],"egm review loop","loop","review loop","model","structural","review process","audit","design docs","multi-agent","standards","feature","fixes","plans",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":150,"publishedAt":47},"01M6990CSJDAFJ1KN9SZQPH3QC","egm-resolve","The Elephant resolution skill. Ingests flat deficiency reports from concurrent Goldfish reviewers, applies automated fixes for PROPOSE FIX items via UI multiple-choice gates, and presents interactive negotiation\u002Fre-sync checkpoints.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Felephant-goldfish-model\u002Fblob\u002Fmain\u002Fskills\u002Fegm-resolve\u002FSKILL.md",[149],{"categoryNo":125,"categoryName":126,"taxonomyType":127,"taxonomyTypeDesc":128},[151,152,153,154,155,156,157,158,141,33,34,159,160,161,162,163,164],"egm resolve","re","fix","choice","reports","sync","ui","checkpoints","interactive","gates","resolution","via","negotiation","propose fix",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":177,"publishedAt":47},"01M699071AZREBMBPMTHH4KQ7P","egm-draft","Drafts a design document section-by-section using the concepts brief from egm-brainstorm (or user notes). This is the second step in the Elephant-Goldfish (EGM) feature flow. Use when you are ready to write a design doc after aligning on requirements + solution.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Felephant-goldfish-model\u002Fblob\u002Fmain\u002Fskills\u002Fegm-draft\u002FSKILL.md",[171,174],{"categoryNo":172,"categoryName":173,"taxonomyType":127,"taxonomyTypeDesc":128},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":175,"categoryName":176,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000032","设计师",[178,179,31,180,181,182,183,184,185,186,187,188,189,190,191,140,34,41,40,192,30,193,194],"egm draft","draft","brief","ready","brainstorm","write a design doc","you","notes","design doc","write","drafts","flow","doc","concepts","requirements","second","section",{"skillNo":196,"name":197,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":202,"publishedAt":47},"01M699044ADR4VC11T4ZR8JS42","egm-brainstorm","Interactive ideation and brainstorming skill for the Elephant & Goldfish Model (EGM). Helps turn half-baked concepts into structured hypotheses via clarifying questions, review, and iterative refinement. Produces an RFC summary for human review or more detailed design with egm-draft.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Felephant-goldfish-model\u002Fblob\u002Fmain\u002Fskills\u002Fegm-brainstorm\u002FSKILL.md",[201],{"categoryNo":125,"categoryName":126,"taxonomyType":127,"taxonomyTypeDesc":128},[203,182,31,105,133,204,205,191,33,34,206,159,207,179,36,208,209,162,210,211],"egm brainstorm","brainstorming skill","human","more","human review","ideation","brainstorming","questions","refinement",{"skillNo":213,"name":214,"nameZh":6,"description":215,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":216,"categories":217,"keywords":218,"publishedAt":47},"01M69901MTC4QDKVFXZV3EVWKW","egm-bootstrap","Bootstrap directory README.md files across a repository subtree.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Felephant-goldfish-model\u002Fblob\u002Fmain\u002Fskills\u002Fegm-bootstrap\u002FSKILL.md",[],[219,220,46,221,39,222,223,34],"egm bootstrap","bootstrap","files","repository","README"]