[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F2P459S5T73RNMGXNPSTAT":3,"skill-same:01M7F2P459S5T73RNMGXNPSTAT":67},{"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":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7F2P459S5T73RNMGXNPSTAT","using-grillspec",null,"Use when starting any conversation, and before acting on any request that involves choosing between options - routes work through grilling, specs, plans and execution so the agent never guesses what the user would decide.","forbxpg\u002Fgrillspec","forbxpg","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F144426975?v=4","01M7F2KNWHMXF9R8YPQNDQPECB","Kirgizov Temurmalik","01M7F2KNX4T75NN17D5C25KKKZ",0,"MIT","https:\u002F\u002Fgithub.com\u002Fforbxpg\u002Fgrillspec\u002Fblob\u002Fmain\u002Fskills\u002Fusing-grillspec\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: using-grillspec\ndescription: Use when starting any conversation, and before acting on any request that involves choosing between options - routes work through grilling, specs, plans and execution so the agent never guesses what the user would decide.\n---\n\n# Using grillspec\n\ngrillspec spends questions up front so you never have to guess later. A choice\nbetween options is a decision, and decisions belong to the user.\n\n## The rule\n\nBefore you act on a request — before clarifying questions, before exploring code —\ndecide which row applies:\n\n| The request | Do |\n|---|---|\n| has no choice between options: a typo, a rename, formatting, a fix whose cause and remedy are both certain | Just do it. |\n| has a decision but is small: one function or file, reversible, no new interface | Ask in chat: name the decision, give your recommendation, ask. One question, no skill, no files. |\n| adds or changes a feature, module, interface, schema, infrastructure, or anything hard to reverse | Run the full pipeline below. |\n\nUnsure between two rows? Take the lower one. One extra question costs less than\none rework.\n\nDebugging, test-driven development and verification skills (`grillspec-debugging`,\n`grillspec-tdd`, `grillspec-verification`) keep their own triggers\nwhatever the row.\n\n## The pipeline\n\n`grill → spec (+ memory) → plan → execute → archive`\n\n| Phase | Skill | Leaves behind |\n|---|---|---|\n| grill | `grillspec-grill`, with `grillspec-council` when the council is on | a decision log (Open \u002F Settled), confirmed by the user |\n| spec | `grillspec-specs`, then `grillspec-memory` | an approved spec; approved memory entries |\n| plan | `grillspec-plans` | an approved plan |\n| execute | `grillspec-subagent-execution` or `grillspec-inline-execution` (the plan's executor), with `grillspec-tdd`, `grillspec-debugging`, `grillspec-verification`, then `grillspec-finishing` | code and green tests; every task ticked |\n| archive | `grillspec-archive` | the change merged into the living specs, or marked implemented |\n\nIf a skill named here is not installed yet, tell the user which phase you are in\nand follow the phase by hand.\n\nNo `.grillspec\u002Fconfig.toml` in the project and the request is in row 2 or 3? Then\noffer the `grillspec-init` skill once; if the user declines, ask in chat without files.\nRow-1 work never needs it.\n\n## Where you are\n\nEach session starts with a line like\n`grillspec: phase=grill change=2026-10-17-login next=continue grilling: 3 open questions`.\nWhen unsure, run `grillspec status`, using the command on the `grillspec CLI:` line\nof the session-start context (or `uvx grillspec` where no plugin is installed). Phases: `idle`, `grill`, `spec`, `plan`,\n`execute`, `done`.\n\nConfirming a grill and approving a spec or a plan come only from an explicit reply\nfrom the user —\nnever inferred from silence, from a \"looks fine so far\", or from your own review.\nAn explicit \"no questions\" or \"just do it\" is consent to proceed on your own\njudgment. Before you change any file, write the decisions you are taking for the\nuser as a visible list headed \"Assumptions\" — in your reply, not only in your\nreasoning; one line each, with what to change if it is wrong. Then do the work,\nand repeat the list in your final message. \"I'm in a hurry\" alone is not that consent: still ask the one decision\nthat matters most, with your recommendation.\n\n## Facts and decisions\n\nLook facts up yourself: files, git history, configuration, documentation, a CLI's\n`--help`. Asking the user what you could have checked wastes their time. Put every\ndecision to the user: what depends on their product, taste or risk is theirs.\n\n## Asking\n\nEach decision you put to the user carries your recommendation, first and marked\n`(Recommended)`, with the real trade-off of each alternative. Use the harness's\nmultiple-choice tool when it has one; otherwise write numbered options in plain\ntext and accept a number or free text as the answer.\n\n## Language\n\nReply in the language of the user's latest message. Write specs and plans in the\nproject's artifact language (`spec.artifacts_language`; `auto` means the language\nof the project's existing docs, or of the conversation in an empty repository).\nKeep OpenSpec keywords in English: `SHALL`, `MUST`, `WHEN`, `THEN`, `AND`, and the\nsection headers.\n\n## Other workflow plugins\n\nIf Superpowers or another workflow router is also active, tell the user once to\nkeep only one of them enabled. Until they do, follow grillspec for planning and\nfor its phase gates.\n\n## Phase gates\n\nWhile the active change is grilled, specced or planned, a hook blocks edits outside\nits artifacts. A blocked edit means: finish the phase first. Never work around a gate\nwith another tool or a shell trick; if the user wants to skip it, they run\n`grillspec gate pause` in their own terminal.\n\n## Session memory\n\nYour session-start context holds a `grillspec memory:` brief: where the last session\nstopped. If it is missing (GigaCode), run `grillspec recall --brief` once. Write a note\nthe moment you learn something: `grillspec note discovery|blocker|todo -- \"\u003Cone line>\"`.\nBefore the session ends, write `grillspec note handoff -- \"done: …; next: …; open: …\"`.\nLook further back with `grillspec recall \u003Cwords>`; close a blocker or todo that no\nlonger stands with `grillspec recall --resolve \u003Cid>`.\n\n## Red flags\n\n| Thought | Reality |\n|---|---|\n| \"This is obvious, I'll just build it.\" | Obvious is where unchecked assumptions live. Check the rule table. |\n| \"I'll pick a sensible default.\" | Picking between options is a decision. Ask. |\n| \"Let me explore the code first, then ask.\" | Decide the row first; looking things up is part of the grill. |\n| \"The user is in a hurry.\" | Ask the one decision that matters — unless they said no questions: then list your assumptions first and proceed. |\n| \"They approved the idea, so the spec is approved.\" | Approval is an explicit reply to the written artifact. |\n| \"I'll leave a `note todo` and add the test later.\" | A note records; it never defers a test or a gate. Write the test now — or, if the user waived it, say plainly the code is untested and leave the task unticked. |\n\n## Harness tools\n\nSkills name actions — ask the user, dispatch a subagent, track tasks, run a\ncommand. How each harness spells them:\n\n- Claude Code: `references\u002Fclaude-code-tools.md`\n- Cursor: `references\u002Fcursor-tools.md`\n- Codex: `references\u002Fcodex-tools.md`\n- Antigravity: `references\u002Fantigravity-tools.md`\n- GigaCode: `references\u002Fgigacode-tools.md`\n","# Using grillspec\n\ngrillspec spends questions up front so you never have to guess later. A choice\nbetween options is a decision, and decisions belong to the user.\n\n## The rule\n\nBefore you act on a request — before clarifying questions, before exploring code —\ndecide which row applies:\n\n| The request | Do |\n|---|---|\n| has no choice between options: a typo, a rename, formatting, a fix whose cause and remedy are both certain | Just do it. |\n| has a decision but is small: one function or file, reversible, no new interface | Ask in chat: name the decision, give your recommendation, ask. One question, no skill, no files. |\n| adds or changes a feature, module, interface, schema, infrastructure, or anything hard to reverse | Run the full pipeline below. |\n\nUnsure between two rows? Take the lower one. One extra question costs less than\none rework.\n\nDebugging, test-driven development and verification skills (`grillspec-debugging`,\n`grillspec-tdd`, `grillspec-verification`) keep their own triggers\nwhatever the row.\n\n## The pipeline\n\n`grill → spec (+ memory) → plan → execute → archive`\n\n| Phase | Skill | Leaves behind |\n|---|---|---|\n| grill | `grillspec-grill`, with `grillspec-council` when the council is on | a decision log (Open \u002F Settled), confirmed by the user |\n| spec | `grillspec-specs`, then `grillspec-memory` | an approved spec; approved memory entries |\n| plan | `grillspec-plans` | an approved plan |\n| execute | `grillspec-subagent-execution` or `grillspec-inline-execution` (the plan's executor), with `grillspec-tdd`, `grillspec-debugging`, `grillspec-verification`, then `grillspec-finishing` | code and green tests; every task ticked |\n| archive | `grillspec-archive` | the change merged into the living specs, or marked implemented |\n\nIf a skill named here is not installed yet, tell the user which phase you are in\nand follow the phase by hand.\n\nNo `.grillspec\u002Fconfig.toml` in the project and the request is in row 2 or 3? Then\noffer the `grillspec-init` skill once; if the user declines, ask in chat without files.\nRow-1 work never needs it.\n\n## Where you are\n\nEach session starts with a line like\n`grillspec: phase=grill change=2026-10-17-login next=continue grilling: 3 open questions`.\nWhen unsure, run `grillspec status`, using the command on the `grillspec CLI:` line\nof the session-start context (or `uvx grillspec` where no plugin is installed). Phases: `idle`, `grill`, `spec`, `plan`,\n`execute`, `done`.\n\nConfirming a grill and approving a spec or a plan come only from an explicit reply\nfrom the user —\nnever inferred from silence, from a \"looks fine so far\", or from your own review.\nAn explicit \"no questions\" or \"just do it\" is consent to proceed on your own\njudgment. Before you change any file, write the decisions you are taking for the\nuser as a visible list headed \"Assumptions\" — in your reply, not only in your\nreasoning; one line each, with what to change if it is wrong. Then do the work,\nand repeat the list in your final message. \"I'm in a hurry\" alone is not that consent: still ask the one decision\nthat matters most, with your recommendation.\n\n## Facts and decisions\n\nLook facts up yourself: files, git history, configuration, documentation, a CLI's\n`--help`. Asking the user what you could have checked wastes their time. Put every\ndecision to the user: what depends on their product, taste or risk is theirs.\n\n## Asking\n\nEach decision you put to the user carries your recommendation, first and marked\n`(Recommended)`, with the real trade-off of each alternative. Use the harness's\nmultiple-choice tool when it has one; otherwise write numbered options in plain\ntext and accept a number or free text as the answer.\n\n## Language\n\nReply in the language of the user's latest message. Write specs and plans in the\nproject's artifact language (`spec.artifacts_language`; `auto` means the language\nof the project's existing docs, or of the conversation in an empty repository).\nKeep OpenSpec keywords in English: `SHALL`, `MUST`, `WHEN`, `THEN`, `AND`, and the\nsection headers.\n\n## Other workflow plugins\n\nIf Superpowers or another workflow router is also active, tell the user once to\nkeep only one of them enabled. Until they do, follow grillspec for planning and\nfor its phase gates.\n\n## Phase gates\n\nWhile the active change is grilled, specced or planned, a hook blocks edits outside\nits artifacts. A blocked edit means: finish the phase first. Never work around a gate\nwith another tool or a shell trick; if the user wants to skip it, they run\n`grillspec gate pause` in their own terminal.\n\n## Session memory\n\nYour session-start context holds a `grillspec memory:` brief: where the last session\nstopped. If it is missing (GigaCode), run `grillspec recall --brief` once. Write a note\nthe moment you learn something: `grillspec note discovery|blocker|todo -- \"\u003Cone line>\"`.\nBefore the session ends, write `grillspec note handoff -- \"done: …; next: …; open: …\"`.\nLook further back with `grillspec recall \u003Cwords>`; close a blocker or todo that no\nlonger stands with `grillspec recall --resolve \u003Cid>`.\n\n## Red flags\n\n| Thought | Reality |\n|---|---|\n| \"This is obvious, I'll just build it.\" | Obvious is where unchecked assumptions live. Check the rule table. |\n| \"I'll pick a sensible default.\" | Picking between options is a decision. Ask. |\n| \"Let me explore the code first, then ask.\" | Decide the row first; looking things up is part of the grill. |\n| \"The user is in a hurry.\" | Ask the one decision that matters — unless they said no questions: then list your assumptions first and proceed. |\n| \"They approved the idea, so the spec is approved.\" | Approval is an explicit reply to the written artifact. |\n| \"I'll leave a `note todo` and add the test later.\" | A note records; it never defers a test or a gate. Write the test now — or, if the user waived it, say plainly the code is untested and leave the task unticked. |\n\n## Harness tools\n\nSkills name actions — ask the user, dispatch a subagent, track tasks, run a\ncommand. How each harness spells them:\n\n- Claude Code: `references\u002Fclaude-code-tools.md`\n- Cursor: `references\u002Fcursor-tools.md`\n- Codex: `references\u002Fcodex-tools.md`\n- Antigravity: `references\u002Fantigravity-tools.md`\n- GigaCode: `references\u002Fgigacode-tools.md`\n",{"name":5,"description":7},"main","348b0fb01ff821b20f8a5c13878439f18ca9ee5e","skills\u002Fusing-grillspec","https:\u002F\u002Fgithub.com\u002Fforbxpg\u002Fgrillspec","https:\u002F\u002Fgithub.com\u002Fforbxpg","Pretty chill irl but incredibly turbulent in the coding steam","2026-10-21 18:43:44",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add forbxpg\u002Fgrillspec --skill using-grillspec",{"tool":37,"command":38},"bunx","bunx skills add forbxpg\u002Fgrillspec --skill using-grillspec",{"tool":40,"command":41},"pnpm","pnpm dlx skills add forbxpg\u002Fgrillspec --skill using-grillspec","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fforbxpg\u002Fgrillspec\u002Fblob\u002Fmain\u002Fskills\u002Fusing-grillspec\u002FSKILL.md",true,[45,51,55,59,63],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Fantigravity-tools.md","REFERENCE","参考文档",717,"https:\u002F\u002Fgithub.com\u002Fforbxpg\u002Fgrillspec\u002Fblob\u002Fmain\u002Fskills\u002Fusing-grillspec\u002Freferences\u002Fantigravity-tools.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fclaude-code-tools.md",678,"https:\u002F\u002Fgithub.com\u002Fforbxpg\u002Fgrillspec\u002Fblob\u002Fmain\u002Fskills\u002Fusing-grillspec\u002Freferences\u002Fclaude-code-tools.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fcodex-tools.md",766,"https:\u002F\u002Fgithub.com\u002Fforbxpg\u002Fgrillspec\u002Fblob\u002Fmain\u002Fskills\u002Fusing-grillspec\u002Freferences\u002Fcodex-tools.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fcursor-tools.md",581,"https:\u002F\u002Fgithub.com\u002Fforbxpg\u002Fgrillspec\u002Fblob\u002Fmain\u002Fskills\u002Fusing-grillspec\u002Freferences\u002Fcursor-tools.md",{"path":64,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fgigacode-tools.md",956,"https:\u002F\u002Fgithub.com\u002Fforbxpg\u002Fgrillspec\u002Fblob\u002Fmain\u002Fskills\u002Fusing-grillspec\u002Freferences\u002Fgigacode-tools.md",[68,74,79,86,93,100],{"skillNo":69,"name":70,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7F2PAK6YPZZ3J2DHYTMSAE9","graders","https:\u002F\u002Fgithub.com\u002Fforbxpg\u002Fgrillspec\u002Fblob\u002Fmain\u002Ftests\u002Fevals\u002Fgrill-triggers\u002Fgraders\u002Fskill.md",[],[],{"skillNo":75,"name":70,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7F2P8RZ76WHAB41AN13JPZT","https:\u002F\u002Fgithub.com\u002Fforbxpg\u002Fgrillspec\u002Fblob\u002Fmain\u002Ftests\u002Fevals\u002Farchive-asks\u002Fgraders\u002Fskill.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7F2NZJEKXP7B1YZKVWDFJSA","grillspec-worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback","https:\u002F\u002Fgithub.com\u002Fforbxpg\u002Fgrillspec\u002Fblob\u002Fmain\u002Fskills\u002Fgrillspec-worktrees\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7F2NTZFV9EVXEH7VEFWM58W","grillspec-verification","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fforbxpg\u002Fgrillspec\u002Fblob\u002Fmain\u002Fskills\u002Fgrillspec-verification\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7F2NQ2YHVGVTJZJSRFH8GQQ","grillspec-tdd","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002Fforbxpg\u002Fgrillspec\u002Fblob\u002Fmain\u002Fskills\u002Fgrillspec-tdd\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7F2NKY0GEQNPA5S3KCMYJS1","grillspec-subagent-execution","Use when executing implementation plans with independent tasks in the current session","https:\u002F\u002Fgithub.com\u002Fforbxpg\u002Fgrillspec\u002Fblob\u002Fmain\u002Fskills\u002Fgrillspec-subagent-execution\u002FSKILL.md",[],[]]