[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79H7JKJHAKMAASNW4EG07DX":3,"skill-same:01M79H7JKJHAKMAASNW4EG07DX":46},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M79H7JKJHAKMAASNW4EG07DX","grilling",null,"Grill the user relentlessly about a plan, decision, or idea, one question at a time, keeping a running notepad of every decision. A reusable primitive; end with \u002Fmake-it-so to promote or \u002Fcheckpoint to pause. Use when the user wants to stress-test thinking or uses any 'grill' trigger phrase.","KaydenClark\u002FFoundry","KaydenClark","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F26465021?v=4","01M79H31FNE2HKKE40PPQA5VCC","Kayden Clark","01M79H31GPGM16FRE9M4QXJT4T",0,"MIT","https:\u002F\u002Fgithub.com\u002FKaydenClark\u002FFoundry\u002Fblob\u002Fmain\u002Frecovery\u002Flegacy-skill-snapshot\u002Fgrilling\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: grilling\ndescription: Grill the user relentlessly about a plan, decision, or idea, one question at a time, keeping a running notepad of every decision. A reusable primitive; end with \u002Fmake-it-so to promote or \u002Fcheckpoint to pause. Use when the user wants to stress-test thinking or uses any 'grill' trigger phrase.\n---\n\nThis is the core interview primitive. It runs the questioning and keeps a running\nnotepad of the result. It never writes canonical files itself — the `\u002Fmake-it-so`\nskill promotes the notepad, so `grilling` can also run on its own.\n\nGrill the user relentlessly about every aspect of this until we reach a shared\nunderstanding. Walk down each branch of the decision tree, resolving dependencies\nbetween decisions one-by-one. For each question, provide your recommended answer.\n\nAsk the questions one at a time, waiting for feedback on each question before\ncontinuing. Asking multiple questions at once is bewildering.\n\nIf a fact can be found by exploring the environment (filesystem, tools, etc.),\nlook it up rather than asking me. The decisions, though, are mine — put each one\nto me and wait for my answer.\n\n## The notepad (start here, before asking anything)\n\nKeep a running notepad of the whole session so nothing is lost to a context\ncompaction or a hand-off to another assistant. The notepad is the working record;\nit is not canonical until it is promoted.\n\n1. Explore enough to build the real decision tree.\n2. Create the notepad at `.agents\u002Fgrilling diary\u002F\u003Ctopic-slug>-\u003CYYYY-MM-DD>.md`\n   (use the current date; create the folder if missing). Header it exactly:\n   `STATUS: PROVISIONAL — not canonical until \u002Fmake-it-so`\n3. Write the FULL planned question list up front, so I see the terrain before\n   answering. It is a best-effort map; it will flex.\n\nFormat — stable IDs that are never renumbered, one status tag per line:\n\n```markdown\n# Grilling — \u003Ctopic>\nSTATUS: PROVISIONAL — not canonical until \u002Fmake-it-so   |   Started \u003Cdate>\n\n## Planned questions\n1. [open]      \u003Cquestion>\n2. [open]      \u003Cquestion>\n   2A. [open]  \u003Csub-question \u002F dependency of 2>\n3. [open]      \u003Cquestion>\n\n## Spawned branches\n```\n\n- A sub-question or dependency nests as `2A`, `2B` under its parent.\n- A NEW line of questioning I open appends to the bottom under\n  `## Spawned branches` as the next top-level number; never renumber the items\n  above it.\n- Tags: `[open]` (unasked\u002Fundecided), `[tentative]` (leaning, revisit),\n  `[locked]` (decided).\n\n## During the interview\n\n- Ask the next `[open]` question with your recommendation.\n- After I confirm an answer, immediately flip that line to `[locked]` (or\n  `[tentative]`) and append the one-line result in the notepad, before asking the\n  next question. This tiny per-answer write is the entire cost.\n- Do not act on it until I confirm we have reached a shared understanding, and do\n  not touch canonical files during the interview.\n\n## Resuming after a compaction or model switch\n\nThe notepad is the durable record, not the chat. If the conversation is\ncompressed, truncated, or handed to another assistant, re-read the notepad and\ncontinue at the first `[open]` line. Never re-ask a `[locked]` question.\n\n## Exits\n\nKeep grilling until I explicitly run one of these skills — do not stop on a\nlookalike phrase said in passing:\n\n- `\u002Fmake-it-so` — I am done; confirm the approvals, promote the notepad's\n  locked decisions to canon, implement them, and push the results to the\n  remote.\n- `\u002Fcheckpoint` — save and stop for now; commit the notepad to resume later.\n\nOnly those invoked skills end the interview. Continue only within the standing\nproject authority and safety boundaries.\n","This is the core interview primitive. It runs the questioning and keeps a running\nnotepad of the result. It never writes canonical files itself — the `\u002Fmake-it-so`\nskill promotes the notepad, so `grilling` can also run on its own.\n\nGrill the user relentlessly about every aspect of this until we reach a shared\nunderstanding. Walk down each branch of the decision tree, resolving dependencies\nbetween decisions one-by-one. For each question, provide your recommended answer.\n\nAsk the questions one at a time, waiting for feedback on each question before\ncontinuing. Asking multiple questions at once is bewildering.\n\nIf a fact can be found by exploring the environment (filesystem, tools, etc.),\nlook it up rather than asking me. The decisions, though, are mine — put each one\nto me and wait for my answer.\n\n## The notepad (start here, before asking anything)\n\nKeep a running notepad of the whole session so nothing is lost to a context\ncompaction or a hand-off to another assistant. The notepad is the working record;\nit is not canonical until it is promoted.\n\n1. Explore enough to build the real decision tree.\n2. Create the notepad at `.agents\u002Fgrilling diary\u002F\u003Ctopic-slug>-\u003CYYYY-MM-DD>.md`\n   (use the current date; create the folder if missing). Header it exactly:\n   `STATUS: PROVISIONAL — not canonical until \u002Fmake-it-so`\n3. Write the FULL planned question list up front, so I see the terrain before\n   answering. It is a best-effort map; it will flex.\n\nFormat — stable IDs that are never renumbered, one status tag per line:\n\n```markdown\n# Grilling — \u003Ctopic>\nSTATUS: PROVISIONAL — not canonical until \u002Fmake-it-so   |   Started \u003Cdate>\n\n## Planned questions\n1. [open]      \u003Cquestion>\n2. [open]      \u003Cquestion>\n   2A. [open]  \u003Csub-question \u002F dependency of 2>\n3. [open]      \u003Cquestion>\n\n## Spawned branches\n```\n\n- A sub-question or dependency nests as `2A`, `2B` under its parent.\n- A NEW line of questioning I open appends to the bottom under\n  `## Spawned branches` as the next top-level number; never renumber the items\n  above it.\n- Tags: `[open]` (unasked\u002Fundecided), `[tentative]` (leaning, revisit),\n  `[locked]` (decided).\n\n## During the interview\n\n- Ask the next `[open]` question with your recommendation.\n- After I confirm an answer, immediately flip that line to `[locked]` (or\n  `[tentative]`) and append the one-line result in the notepad, before asking the\n  next question. This tiny per-answer write is the entire cost.\n- Do not act on it until I confirm we have reached a shared understanding, and do\n  not touch canonical files during the interview.\n\n## Resuming after a compaction or model switch\n\nThe notepad is the durable record, not the chat. If the conversation is\ncompressed, truncated, or handed to another assistant, re-read the notepad and\ncontinue at the first `[open]` line. Never re-ask a `[locked]` question.\n\n## Exits\n\nKeep grilling until I explicitly run one of these skills — do not stop on a\nlookalike phrase said in passing:\n\n- `\u002Fmake-it-so` — I am done; confirm the approvals, promote the notepad's\n  locked decisions to canon, implement them, and push the results to the\n  remote.\n- `\u002Fcheckpoint` — save and stop for now; commit the notepad to resume later.\n\nOnly those invoked skills end the interview. Continue only within the standing\nproject authority and safety boundaries.\n",{"name":5,"description":7},"main","9381af33e9db4f69f7c4f83ded287e23e109c7c1","recovery\u002Flegacy-skill-snapshot\u002Fgrilling","https:\u002F\u002Fgithub.com\u002FKaydenClark\u002FFoundry","https:\u002F\u002Fgithub.com\u002FKaydenClark","https:\u002F\u002Fkayden-clark.vercel.app\u002F","Building simple systems to solve complex problems","2026-09-05 15:28:09",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add KaydenClark\u002FFoundry --skill grilling",{"tool":38,"command":39},"bunx","bunx skills add KaydenClark\u002FFoundry --skill grilling",{"tool":41,"command":42},"pnpm","pnpm dlx skills add KaydenClark\u002FFoundry --skill grilling","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKaydenClark\u002FFoundry\u002Fblob\u002Fmain\u002Frecovery\u002Flegacy-skill-snapshot\u002Fgrilling\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M79H8BQMY5ZFKYHRQ12YT67B","writing-great-skills","Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.","https:\u002F\u002Fgithub.com\u002FKaydenClark\u002FFoundry\u002Fblob\u002Fmain\u002Frecovery\u002Flegacy-skill-snapshot\u002Fwriting-great-skills\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M79H88YTKNDMAPEHS9HDM51E","update-harness","Update a project to the current canonical LLM Workbench harness without losing project-specific controls, work state, or proof.","https:\u002F\u002Fgithub.com\u002FKaydenClark\u002FFoundry\u002Fblob\u002Fmain\u002Frecovery\u002Flegacy-skill-snapshot\u002Fupdate-harness\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M79H867VMC0SQ5A1687SCGCF","tracer-bullet","Cut a capability into vertical tracer-bullet slices that each pierce every layer of a project's stack, then order, scope, and assign them.","https:\u002F\u002Fgithub.com\u002FKaydenClark\u002FFoundry\u002Fblob\u002Fmain\u002Frecovery\u002Flegacy-skill-snapshot\u002Ftracer-bullet\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M79H84D6KN135D17505TFEXH","to-tickets","Break an assigned Workbench spec into dependency-aware tracer-bullet tickets.","https:\u002F\u002Fgithub.com\u002FKaydenClark\u002FFoundry\u002Fblob\u002Fmain\u002Frecovery\u002Flegacy-skill-snapshot\u002Fto-tickets\u002FSKILL.md",[],[],{"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":19},"01M79H82Q2GFBBCQZ4ZHHHYDW1","to-spec","Turn an already-settled conversation into one stable Workbench capability spec without restarting the interview.","https:\u002F\u002Fgithub.com\u002FKaydenClark\u002FFoundry\u002Fblob\u002Fmain\u002Frecovery\u002Flegacy-skill-snapshot\u002Fto-spec\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M79H80SAT2SWTSF8HA4J8X34","to-docs","Route settled conversation truth into existing Workbench documentation owners without restarting discovery or creating another store.","https:\u002F\u002Fgithub.com\u002FKaydenClark\u002FFoundry\u002Fblob\u002Fmain\u002Frecovery\u002Flegacy-skill-snapshot\u002Fto-docs\u002FSKILL.md",[],[]]