[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M76PKJ8FHTJZKCKN2QYNW1NY":3,"skill-same:01M76PKJ8FHTJZKCKN2QYNW1NY":73},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":14,"repositoryHtmlUrl":43,"repositoryHomepageUrl":44,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M76PKJ8FHTJZKCKN2QYNW1NY","grill-with-docs",null,"Use when the user asks to be grilled AND wants the design written down as you go — a relentless interview that sharpens terminology and records the domain model (glossary + ADRs) inline.","jratlee\u002FFDI","jratlee","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F203306824?v=4","01M753581GDCXCM370SDH6W7G7","JRL","01M753582SPQY4E0FZXCF8P3RX",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjratlee\u002FFDI\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgrill-with-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjratlee\u002FFDI\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgrill-with-docs\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: grill-with-docs\ndescription: Use when the user asks to be grilled AND wants the design written down as you go — a relentless interview that sharpens terminology and records the domain model (glossary + ADRs) inline.\nversion: 1.0.0\nauthor: Matt Pocock (mattpocock\u002Fskills, MIT); adapted for Hermes\nlicense: MIT\nmetadata:\n  hermes:\n    tags: [design-review, questioning, domain-modeling, glossary, adr, planning]\n    related_skills: [productivity\u002Fgrilling, engineering\u002Fdomain-modeling, productivity\u002Fgrill-me]\n---\n\n# Grill With Docs\n\nAdapted from `mattpocock\u002Fskills` -> `skills\u002Fengineering\u002Fgrill-with-docs` (MIT, upstream body is a\nsingle line: _Call the Skill tool twice, for \"grilling\" and \"domain-modeling\"_). Hermes has no Skill\ntool, so the pointer is rewritten below. Behaviour is unchanged.\n\n## When to Use\n\n- The user says \"grill me with docs\", \"grill me on this codebase\", \"stress-test this and write down\n  the decisions\", or asks for an interview where the output should be design documentation.\n- Use plain `productivity\u002Fgrill-me` when they only want the interrogation and no docs.\n\n## Do this now\n\nLoad BOTH skills and work them together -- do not paraphrase from memory.\n\n```\n# Hermes\nskill_view(name=\"productivity\u002Fgrilling\")\nskill_view(name=\"engineering\u002Fdomain-modeling\")\n\n# any other agent (Replit \u002F Claude Code \u002F Codex): read the files directly, wherever\n# the skills root puts them (category folders vary by install)\n\u003Cskills-root>\u002F**\u002Fgrilling\u002FSKILL.md\n\u003Cskills-root>\u002F**\u002Fdomain-modeling\u002FSKILL.md\n```\n\n`grilling` supplies the interview discipline (rounds, the frontier, a recommended answer per\nquestion). `domain-modeling` supplies the writing discipline (challenge terms, sharpen fuzzy\nlanguage, test scenarios, update the glossary and ADRs the moment a decision crystallises).\n\n## How the two combine\n\n- Each round is still a `grilling` round: numbered questions, one recommended answer each, wait for\n  the answers before the next round.\n- While asking, apply `domain-modeling` **inline**: when an answer resolves a term, write it to\n  `GLOSSARY.md` immediately; when a decision passes all three ADR tests (hard to reverse, surprising\n  without context, a real trade-off), offer the ADR and write it then.\n- Before asking a question, check the code and the existing `GLOSSARY.md` \u002F `docs\u002Fadr\u002F` first. A\n  contradiction between what the user says and what the code does is a question, not a footnote.\n- Docs are the *side effect* of settled decisions, never a way to pre-empt them: never write a term\n  or an ADR the user has not agreed to.\n\n## Hermes notes\n\n- Use `clarify` for pickable rounds (up to 5 per call); drop to numbered prose when a question needs\n  a long answer.\n- Fact-finding is yours: read the repo, run commands, or `delegate_task` for wide searches. Never ask\n  the user for something you could look up. Don't block the whole round on a running search -- only\n  the questions downstream of it wait.\n- In a repo, the docs live at the repo root (`GLOSSARY.md`, `docs\u002Fadr\u002F`, or `GLOSSARY-MAP.md` +\n  per-context glossaries). Outside a repo (Obsidian, business planning), put the same two files\n  beside the work you are planning and say where you wrote them.\n- Report at the end: which terms were added, which ADRs were written, and which questions are still\n  open.\n","# Grill With Docs\n\nAdapted from `mattpocock\u002Fskills` -> `skills\u002Fengineering\u002Fgrill-with-docs` (MIT, upstream body is a\nsingle line: _Call the Skill tool twice, for \"grilling\" and \"domain-modeling\"_). Hermes has no Skill\ntool, so the pointer is rewritten below. Behaviour is unchanged.\n\n## When to Use\n\n- The user says \"grill me with docs\", \"grill me on this codebase\", \"stress-test this and write down\n  the decisions\", or asks for an interview where the output should be design documentation.\n- Use plain `productivity\u002Fgrill-me` when they only want the interrogation and no docs.\n\n## Do this now\n\nLoad BOTH skills and work them together -- do not paraphrase from memory.\n\n```\n# Hermes\nskill_view(name=\"productivity\u002Fgrilling\")\nskill_view(name=\"engineering\u002Fdomain-modeling\")\n\n# any other agent (Replit \u002F Claude Code \u002F Codex): read the files directly, wherever\n# the skills root puts them (category folders vary by install)\n\u003Cskills-root>\u002F**\u002Fgrilling\u002FSKILL.md\n\u003Cskills-root>\u002F**\u002Fdomain-modeling\u002FSKILL.md\n```\n\n`grilling` supplies the interview discipline (rounds, the frontier, a recommended answer per\nquestion). `domain-modeling` supplies the writing discipline (challenge terms, sharpen fuzzy\nlanguage, test scenarios, update the glossary and ADRs the moment a decision crystallises).\n\n## How the two combine\n\n- Each round is still a `grilling` round: numbered questions, one recommended answer each, wait for\n  the answers before the next round.\n- While asking, apply `domain-modeling` **inline**: when an answer resolves a term, write it to\n  `GLOSSARY.md` immediately; when a decision passes all three ADR tests (hard to reverse, surprising\n  without context, a real trade-off), offer the ADR and write it then.\n- Before asking a question, check the code and the existing `GLOSSARY.md` \u002F `docs\u002Fadr\u002F` first. A\n  contradiction between what the user says and what the code does is a question, not a footnote.\n- Docs are the *side effect* of settled decisions, never a way to pre-empt them: never write a term\n  or an ADR the user has not agreed to.\n\n## Hermes notes\n\n- Use `clarify` for pickable rounds (up to 5 per call); drop to numbered prose when a question needs\n  a long answer.\n- Fact-finding is yours: read the repo, run commands, or `delegate_task` for wide searches. Never ask\n  the user for something you could look up. Don't block the whole round on a running search -- only\n  the questions downstream of it wait.\n- In a repo, the docs live at the repo root (`GLOSSARY.md`, `docs\u002Fadr\u002F`, or `GLOSSARY-MAP.md` +\n  per-context glossaries). Outside a repo (Obsidian, business planning), put the same two files\n  beside the work you are planning and say where you wrote them.\n- Report at the end: which terms were added, which ADRs were written, and which questions are still\n  open.\n",{"name":5,"author":25,"license":15,"version":26,"metadata":27,"description":7},"Matt Pocock (mattpocock\u002Fskills, MIT); adapted for Hermes","1.0.0",{"hermes":28},{"tags":29,"related_skills":36},[30,31,32,33,34,35],"design-review","questioning","domain-modeling","glossary","adr","planning",[37,38,39],"productivity\u002Fgrilling","engineering\u002Fdomain-modeling","productivity\u002Fgrill-me","main","2e74ca81f4863be77f9e0e61d0ed862b459a80ef",".agents\u002Fskills\u002Fgrill-with-docs","https:\u002F\u002Fgithub.com\u002Fjratlee\u002FFDI","https:\u002F\u002Ffalsedawn.industries","https:\u002F\u002Fgithub.com\u002Fjratlee","http:\u002F\u002Fjratlee.com","Forward research.","2026-10-19 22:38:27",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add jratlee\u002FFDI --skill grill-with-docs",{"tool":55,"command":56},"bunx","bunx skills add jratlee\u002FFDI --skill grill-with-docs",{"tool":58,"command":59},"pnpm","pnpm dlx skills add jratlee\u002FFDI --skill grill-with-docs","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjratlee\u002FFDI\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgrill-with-docs\u002FSKILL.md",true,[63,67],{"path":64,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":16},"LICENSE","许可证",1068,{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"PROVENANCE.md","REFERENCE","参考文档",987,"https:\u002F\u002Fgithub.com\u002Fjratlee\u002FFDI\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgrill-with-docs\u002FPROVENANCE.md",[74,81,88,95,102,111],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":20},"01M76PTJ6CSGJ8P20GYRBTG763","vercel-react-native-skills","React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.","https:\u002F\u002Fgithub.com\u002Fjratlee\u002FFDI\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fvercel-react-native-skills\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":20},"01M76PTDRG4DWY93TVRQQWNJVY","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002Fjratlee\u002FFDI\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fvercel-react-best-practices\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":20},"01M76PTADCDZZQJG4D28Y56M84","vercel-composition-patterns","React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.","https:\u002F\u002Fgithub.com\u002Fjratlee\u002FFDI\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fvercel-composition-patterns\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":20},"01M76PSWWJJEC0762TR9YJ7CN6","supabase-postgres-best-practices","Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.","https:\u002F\u002Fgithub.com\u002Fjratlee\u002FFDI\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsupabase-postgres-best-practices\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":106,"licenseFileUrl":107,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":20},"01M76PS6PNXZECWHRPZF3K9513","skill-creator","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fjratlee\u002FFDI\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fjratlee\u002FFDI\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-creator\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":20},"01M76PKNZ07CRNGVFKY92QMT7E","grilling","Use when the user wants a plan stress-tested.","https:\u002F\u002Fgithub.com\u002Fjratlee\u002FFDI\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgrilling\u002FSKILL.md",[],[]]