[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75DNDWXT7APP196JA0FHAEN":3,"skill-same:01M75DNDWXT7APP196JA0FHAEN":47},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M75DNDWXT7APP196JA0FHAEN","harness_delivery_loop",null,"Guides agents through a file-backed Plan -> Work -> Review -> Release loop with explicit specs, Plans.md task contracts, verification evidence, independent review, and bounded long-running execution. Use for substantial SEOSONA work that must stay auditable across sessions or agents.","LongLeo287\u002FSEOSONA-OS","LongLeo287","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F141803367?v=4","01M6JK75C62VCNZKR5BRZ386YV","LongLeo","01M75CK60XQGYJY3YDGGFJQDYT",2,"MIT","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fframeworks\u002Fagentic_workflows\u002Fharness_delivery_loop\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: harness_delivery_loop\ndescription: Guides agents through a file-backed Plan -> Work -> Review -> Release loop with explicit specs, Plans.md task contracts, verification evidence, independent review, and bounded long-running execution. Use for substantial SEOSONA work that must stay auditable across sessions or agents.\n---\n\n# Harness Delivery Loop\n\n## Overview\n\nUse this skill when chat memory is not enough. The loop converts a request into durable files, bounded work slices, independent review, and evidence packages that survive context resets.\n\n## When To Use\n\n- Multi-step implementation or ingestion work.\n- Work that may span sessions.\n- Work with high risk of scope drift.\n- Work where review must be separate from implementation.\n\nDo not use this for one-line fixes or simple questions.\n\n## Operating Loop\n\n1. Investigate.\n   - Read the current repository state.\n   - Reuse existing memory and KI items.\n   - Keep unobserved facts marked as `unknown`.\n\n2. Plan.\n   - Write or update a spec when behavior, architecture, or scope is non-trivial.\n   - Write or update `Plans.md` or an equivalent task checklist.\n   - Include acceptance criteria, dependencies, stop conditions, and validation commands.\n\n3. Work.\n   - Execute one approved slice at a time.\n   - Keep edits scoped to the active task.\n   - Add tests or evidence proportional to risk.\n\n4. Verify.\n   - Run focused tests first.\n   - Run broader gates when shared behavior, routing, or publication surfaces change.\n   - Record exact commands and outcomes.\n\n5. Review.\n   - Review separately from implementation.\n   - Check spec alignment, plan alignment, security, regressions, UX, and test evidence.\n   - Major findings block completion.\n\n6. Release or handoff.\n   - Package evidence.\n   - Commit\u002Fpush only when explicitly requested or already authorized by the task.\n   - Log memory\u002FKI updates for durable learning.\n\n## Long-Running Loop\n\nFor long-running work:\n\n1. Reload the active plan at each re-entry.\n2. Resolve the next incomplete task.\n3. Verify the task contract before acting.\n4. Recover memory\u002Fcontext.\n5. Execute a bounded slice.\n6. Record evidence and status.\n7. Continue, schedule, or stop based on the plan.\n\n## Common Rationalizations\n\n| Rationalization | Reality |\n| --- | --- |\n| \"The plan is in the conversation.\" | Chat context is volatile; file-backed plans are inspectable and resumable. |\n| \"Review can happen at the end.\" | Late review makes scope drift expensive. |\n| \"Unknown probably means absent.\" | Unknown means not observed; do not promote it to a claim. |\n| \"One big pass is faster.\" | Bounded slices reduce rollback cost and make verification meaningful. |\n\n## Red Flags\n\n- Work starts before the task boundary is clear.\n- Plans list tasks without acceptance criteria.\n- Verification evidence is reconstructed from memory.\n- Review approves changes without command output or file references.\n- The agent pushes changes without explicit publish intent.\n\n## Verification\n\n- [ ] Current scope is recorded.\n- [ ] Each completed task has evidence.\n- [ ] Review is separate from implementation.\n- [ ] Remaining risks are explicit.\n- [ ] Memory logging was run for major outcomes.\n","# Harness Delivery Loop\n\n## Overview\n\nUse this skill when chat memory is not enough. The loop converts a request into durable files, bounded work slices, independent review, and evidence packages that survive context resets.\n\n## When To Use\n\n- Multi-step implementation or ingestion work.\n- Work that may span sessions.\n- Work with high risk of scope drift.\n- Work where review must be separate from implementation.\n\nDo not use this for one-line fixes or simple questions.\n\n## Operating Loop\n\n1. Investigate.\n   - Read the current repository state.\n   - Reuse existing memory and KI items.\n   - Keep unobserved facts marked as `unknown`.\n\n2. Plan.\n   - Write or update a spec when behavior, architecture, or scope is non-trivial.\n   - Write or update `Plans.md` or an equivalent task checklist.\n   - Include acceptance criteria, dependencies, stop conditions, and validation commands.\n\n3. Work.\n   - Execute one approved slice at a time.\n   - Keep edits scoped to the active task.\n   - Add tests or evidence proportional to risk.\n\n4. Verify.\n   - Run focused tests first.\n   - Run broader gates when shared behavior, routing, or publication surfaces change.\n   - Record exact commands and outcomes.\n\n5. Review.\n   - Review separately from implementation.\n   - Check spec alignment, plan alignment, security, regressions, UX, and test evidence.\n   - Major findings block completion.\n\n6. Release or handoff.\n   - Package evidence.\n   - Commit\u002Fpush only when explicitly requested or already authorized by the task.\n   - Log memory\u002FKI updates for durable learning.\n\n## Long-Running Loop\n\nFor long-running work:\n\n1. Reload the active plan at each re-entry.\n2. Resolve the next incomplete task.\n3. Verify the task contract before acting.\n4. Recover memory\u002Fcontext.\n5. Execute a bounded slice.\n6. Record evidence and status.\n7. Continue, schedule, or stop based on the plan.\n\n## Common Rationalizations\n\n| Rationalization | Reality |\n| --- | --- |\n| \"The plan is in the conversation.\" | Chat context is volatile; file-backed plans are inspectable and resumable. |\n| \"Review can happen at the end.\" | Late review makes scope drift expensive. |\n| \"Unknown probably means absent.\" | Unknown means not observed; do not promote it to a claim. |\n| \"One big pass is faster.\" | Bounded slices reduce rollback cost and make verification meaningful. |\n\n## Red Flags\n\n- Work starts before the task boundary is clear.\n- Plans list tasks without acceptance criteria.\n- Verification evidence is reconstructed from memory.\n- Review approves changes without command output or file references.\n- The agent pushes changes without explicit publish intent.\n\n## Verification\n\n- [ ] Current scope is recorded.\n- [ ] Each completed task has evidence.\n- [ ] Review is separate from implementation.\n- [ ] Remaining risks are explicit.\n- [ ] Memory logging was run for major outcomes.\n",{"name":5,"description":7},"main","4fd50b1281e8cd978866b6b4556242605cabf708","2_KNOWLEDGE\u002Fframeworks\u002Fagentic_workflows\u002Fharness_delivery_loop",1,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS","https:\u002F\u002Fseosona-os.vercel.app","https:\u002F\u002Fgithub.com\u002FLongLeo287","https:\u002F\u002Fwww.facebook.com\u002FResourceRookie2023","2026-10-09 15:14:13",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add LongLeo287\u002FSEOSONA-OS --skill harness_delivery_loop",{"tool":39,"command":40},"bunx","bunx skills add LongLeo287\u002FSEOSONA-OS --skill harness_delivery_loop",{"tool":42,"command":43},"pnpm","pnpm dlx skills add LongLeo287\u002FSEOSONA-OS --skill harness_delivery_loop","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fframeworks\u002Fagentic_workflows\u002Fharness_delivery_loop\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M75F0T3V3W7JQQ05X26NNN2T","web_crawler_katana","High-speed web crawling using Katana patterns for deep site mapping, URL discovery, and content extraction.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fweb_crawler_katana\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M75F0Q2QJXDGAFKC7D84GT88","server_log_analyzer","Analyzes Nginx\u002FApache server logs to identify Googlebot crawl patterns, errors, and performance bottlenecks.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fserver_log_analyzer\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M75F0KZP6D8R8XPN2YT35BAJ","schema_markup_generator","Auto-generates JSON-LD structured data for any page type (Article, Product, FAQ, LocalBusiness, etc.).","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fschema_markup_generator\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M75F0G3KX4Y86AXJXTKXVEVA","internal_linking_optimizer","Analyzes and optimizes the internal link graph of a website for SEO authority distribution.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Finternal_linking_optimizer\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M75F0CS1RYX4YPJC7N6RAAQJ","google_trends_analyzer","Detects trending topics and seasonal patterns using Google Trends data for content planning and keyword strategy.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fgoogle_trends_analyzer\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M75F0ASMQ1GKPFX82D19SRTN","brand_context_analyzer","Tracks brand mentions, sentiment, and online reputation across web sources.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fbrand_context_analyzer\u002FSKILL.md",[],[]]