[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6F827G4S8CCFD06M12C5FNB":3,"skill-same:01M6F827G4S8CCFD06M12C5FNB":77},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":33,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":62,"install":63,"resources":76},"01M6F827G4S8CCFD06M12C5FNB","kernel-prompt",null,"Use when composing or improving an LLM prompt or agent instruction. Asks one round of questions, then returns only the prompt; never performs the task.","boisenoise\u002Fskills-collections","boisenoise","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F193180?v=4","01M6CDBDQK6BDN55ZMA6B6PKBM","01M6CDBDVSJ3JPTBYN26FZ7TZK",12,"MIT","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-kernel-prompt\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"kernel","kernel prompt","prompt","when","github","blob","prompt-optimization","meta-prompting","agent-handoff","questions","main","task","community","prompt-engineering","only","never","use","Meta","Optimization","productivity","https","license","2026-11-10 10:12:30",false,"---\nname: kernel-prompt\ndescription: \"Use when composing or improving an LLM prompt or agent instruction. Asks one round of questions, then returns only the prompt; never performs the task.\"\ncategory: productivity\nrisk: safe\nsource: community\nsource_repo: codegiveness\u002Fkernel-prompt\nsource_type: community\nlicense: MIT\nlicense_source: https:\u002F\u002Fgithub.com\u002Fcodegiveness\u002Fkernel-prompt\u002Fblob\u002Fmain\u002FLICENSE\ndate_added: \"2026-10-10\"\nauthor: codegiveness\ntags: [prompt-engineering, meta-prompting, prompt-optimization, agent-handoff]\ntools: []\n---\n\n# Kernel Prompt\n\nTurn the user's message into a better prompt they can give to an AI agent. You write the instruction; you never do the work it describes.\n\n## When to Use\n- The user invokes kernel-prompt by name, or asks to compose or improve an LLM prompt or an instruction for another AI.\n- The user asks to turn guidance (for example collaboration or project guidance) into a system prompt.\n- Not when the user only asks to review documents or guidance, even with wording suggestions, merely because they concern AI instructions.\n\n## Source\n- The text the user writes with the invocation is the prompt to improve, even when it reads as a task (\"improve skill X\", \"fix bug Y\", \"write a report on Z\").\n- Files, skills, URLs, and repos it mentions are context: read them so the prompt is accurate and specific (exact paths, names, current state, constraints), and reference them in the prompt. Never rewrite, improve, or summarize them as the deliverable.\n- Transform a file or quoted text instead only when the user explicitly says that text *is* the prompt to improve.\n\n## Never do the task\n- The deliverable is an instruction to an agent, not the agent's output. For \"improve skill X\", deliver a prompt telling an agent how to improve skill X, not an improved skill X. The same applies to code, documents, plans, and reviews.\n- Before replying, check: does the reply contain the result the prompt asks for (a revised file, code, a finished document)? If so, you executed the task. Discard it and write the prompt.\n- Create or edit no files unless the user explicitly asks to save the prompt.\n\n## Grill first\n- Before drafting, always ask one round of questions, unless the user says \"no questions\" or \"just write it\".\n- First look up what files and tools can answer, then ask 2–5 questions only the user can decide that would change the prompt: what \"better\" means, scope and non-goals, constraints, what the agent may change or must not touch, what done looks like, what the agent reports back.\n- Lead each question with your recommended answer (first option in the harness question tool, or worded so \"yes\" accepts it). Anchor questions in specifics from the context you read.\n- Ask another round only for decisions the previous answers opened. Stop when none remain or the user says to write.\n\n## Write the prompt (KERNEL)\n- **K — Keep intent.** Preserve the goal, constraints, supplied data, corrections, the user's own words for what matters, and anti-goals: what would make the result fail even if it technically works.\n- **E — Establish what is known.** Carry facts from the context and the user's answers into the prompt. Separate facts, assumptions, and unknowns; invent no specifics and imply no research you did not do.\n- **R — Resolve ambiguity.** Settle minor gaps with routine judgment. Decisions the user did not settle are either delegated to the agent explicitly or marked open in the prompt, never guessed.\n- **N — Name the work and boundaries.** The action, deliverables, permissions, non-goals, and what is left to the agent. Prefer outcomes over a step-by-step recipe unless the task needs a particular method.\n- **E — Express success.** What done means, the checks that prove it, and what to report back. Add no unrequested targets, outputs, or approval stops.\n- **L — Lay out the handoff.** Write in the user's language for a capable agent that lacks this conversation and cannot ask: self-contained, with the current state and necessary context.\n\n## Deliver\n- Reply with the improved prompt inside a fenced code block, ready to copy and send; if the prompt itself contains triple backticks, use a four-backtick fence. No intro, no analysis, no critique of the original, no change log.\n- After the prompt, list at most 3 assumptions you made that the user did not confirm; omit the list if there are none.\n\n## Example\nUser: \"please see \u003Cpath\u002Fto\u002Fmodule> and improve its readability and performance, inspired by \u003Creference A> and \u003Creference B>\"\n- Wrong: the revised module code. That is doing the task.\n- Right: grill (e.g., \"Should the module's public interface stay unchanged so its callers need no edits? Recommended: yes\"), then reply with a prompt like:\n  Improve the module at \u003Cpath\u002Fto\u002Fmodule>. Its callers in \u003Cpath\u002Fto\u002Fcallers> depend on its public interface, so keep that interface unchanged… Use \u003Creference A> and \u003Creference B> as references for… Keep… Do not… Done when… Report back…\n\n## Limitations\n- Produces a prompt, not the task's result; the user or another agent still has to run it, and a clearer prompt does not guarantee a correct answer.\n- Asks one round of questions before drafting unless the user says \"no questions\" or \"just write it\", so it adds a turn to quick requests.\n- Reads mentioned files, URLs, and repositories only as context; it cannot fill in facts that neither the context nor the user supplies, and marks those decisions open instead.\n- Upstream source: https:\u002F\u002Fgithub.com\u002Fcodegiveness\u002Fkernel-prompt (this copy adds catalog frontmatter, When to Use, and Limitations).\n","# Kernel Prompt\n\nTurn the user's message into a better prompt they can give to an AI agent. You write the instruction; you never do the work it describes.\n\n## When to Use\n- The user invokes kernel-prompt by name, or asks to compose or improve an LLM prompt or an instruction for another AI.\n- The user asks to turn guidance (for example collaboration or project guidance) into a system prompt.\n- Not when the user only asks to review documents or guidance, even with wording suggestions, merely because they concern AI instructions.\n\n## Source\n- The text the user writes with the invocation is the prompt to improve, even when it reads as a task (\"improve skill X\", \"fix bug Y\", \"write a report on Z\").\n- Files, skills, URLs, and repos it mentions are context: read them so the prompt is accurate and specific (exact paths, names, current state, constraints), and reference them in the prompt. Never rewrite, improve, or summarize them as the deliverable.\n- Transform a file or quoted text instead only when the user explicitly says that text *is* the prompt to improve.\n\n## Never do the task\n- The deliverable is an instruction to an agent, not the agent's output. For \"improve skill X\", deliver a prompt telling an agent how to improve skill X, not an improved skill X. The same applies to code, documents, plans, and reviews.\n- Before replying, check: does the reply contain the result the prompt asks for (a revised file, code, a finished document)? If so, you executed the task. Discard it and write the prompt.\n- Create or edit no files unless the user explicitly asks to save the prompt.\n\n## Grill first\n- Before drafting, always ask one round of questions, unless the user says \"no questions\" or \"just write it\".\n- First look up what files and tools can answer, then ask 2–5 questions only the user can decide that would change the prompt: what \"better\" means, scope and non-goals, constraints, what the agent may change or must not touch, what done looks like, what the agent reports back.\n- Lead each question with your recommended answer (first option in the harness question tool, or worded so \"yes\" accepts it). Anchor questions in specifics from the context you read.\n- Ask another round only for decisions the previous answers opened. Stop when none remain or the user says to write.\n\n## Write the prompt (KERNEL)\n- **K — Keep intent.** Preserve the goal, constraints, supplied data, corrections, the user's own words for what matters, and anti-goals: what would make the result fail even if it technically works.\n- **E — Establish what is known.** Carry facts from the context and the user's answers into the prompt. Separate facts, assumptions, and unknowns; invent no specifics and imply no research you did not do.\n- **R — Resolve ambiguity.** Settle minor gaps with routine judgment. Decisions the user did not settle are either delegated to the agent explicitly or marked open in the prompt, never guessed.\n- **N — Name the work and boundaries.** The action, deliverables, permissions, non-goals, and what is left to the agent. Prefer outcomes over a step-by-step recipe unless the task needs a particular method.\n- **E — Express success.** What done means, the checks that prove it, and what to report back. Add no unrequested targets, outputs, or approval stops.\n- **L — Lay out the handoff.** Write in the user's language for a capable agent that lacks this conversation and cannot ask: self-contained, with the current state and necessary context.\n\n## Deliver\n- Reply with the improved prompt inside a fenced code block, ready to copy and send; if the prompt itself contains triple backticks, use a four-backtick fence. No intro, no analysis, no critique of the original, no change log.\n- After the prompt, list at most 3 assumptions you made that the user did not confirm; omit the list if there are none.\n\n## Example\nUser: \"please see \u003Cpath\u002Fto\u002Fmodule> and improve its readability and performance, inspired by \u003Creference A> and \u003Creference B>\"\n- Wrong: the revised module code. That is doing the task.\n- Right: grill (e.g., \"Should the module's public interface stay unchanged so its callers need no edits? Recommended: yes\"), then reply with a prompt like:\n  Improve the module at \u003Cpath\u002Fto\u002Fmodule>. Its callers in \u003Cpath\u002Fto\u002Fcallers> depend on its public interface, so keep that interface unchanged… Use \u003Creference A> and \u003Creference B> as references for… Keep… Do not… Done when… Report back…\n\n## Limitations\n- Produces a prompt, not the task's result; the user or another agent still has to run it, and a clearer prompt does not guarantee a correct answer.\n- Asks one round of questions before drafting unless the user says \"no questions\" or \"just write it\", so it adds a turn to quick requests.\n- Reads mentioned files, URLs, and repositories only as context; it cannot fill in facts that neither the context nor the user supplies, and marks those decisions open instead.\n- Upstream source: https:\u002F\u002Fgithub.com\u002Fcodegiveness\u002Fkernel-prompt (this copy adds catalog frontmatter, When to Use, and Limitations).\n",{"name":5,"risk":50,"tags":51,"tools":52,"author":53,"source":35,"license":14,"category":42,"date_added":54,"description":7,"source_repo":55,"source_type":35,"license_source":56},"safe",[36,30,29,31],[],"codegiveness","2026-10-10","codegiveness\u002Fkernel-prompt","https:\u002F\u002Fgithub.com\u002Fcodegiveness\u002Fkernel-prompt\u002Fblob\u002Fmain\u002FLICENSE","7bf2279c8a65758319526a721d5c4b75683aec9c","skills\u002Fantigravity-kernel-prompt",3,"https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections","https:\u002F\u002Fgithub.com\u002Fboisenoise","2026-11-11 14:20:43",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add boisenoise\u002Fskills-collections --skill kernel-prompt",{"tool":69,"command":70},"bunx","bunx skills add boisenoise\u002Fskills-collections --skill kernel-prompt",{"tool":72,"command":73},"pnpm","pnpm dlx skills add boisenoise\u002Fskills-collections --skill kernel-prompt","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-kernel-prompt\u002FSKILL.md",true,[],[78,106,126,151,170,193],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":82,"licenseFileUrl":83,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":45},"01M6WNH92BHVFXHGPDZCPJ0AG0","web-access","Use Treg for public web or platform data only when existing search, browser and connected tools cannot cover the task, with explicit cost and data boundaries.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-web-access\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-web-access\u002FSKILL.md",[],[87,88,89,90,91,92,93,94,95,96,97,37,98,99,100,101,102,103,104,26,105],"web","access","web access","official","development","browser","search","data","Tools","read","fetch","youtube","free tools","platform","critical","free","cover","normal","2026",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":82,"licenseFileUrl":110,"sourceHtmlUrl":111,"categories":112,"keywords":114,"publishedAt":45},"01M6WNF9XAYAB2CZDDJBAKNM93","treg","Use the Treg CLI or MCP catalog to discover, price and call authorized external tools with team-scoped credentials and a user-approved budget.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-treg\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-treg\u002FSKILL.md",[113],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[108,115,116,27,90,91,44,95,117,118,119,120,39,121,122,101,123,124,125,28,105],"MCP","cli","Budget","credentials","team","catalog","call","discover","external tools","with","scoped",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":82,"licenseFileUrl":130,"sourceHtmlUrl":131,"categories":132,"keywords":138,"publishedAt":45},"01M6WN93MEAZ4E41DYAHJRPHQT","recruit","Turn a job description into an evidence-linked candidate shortlist through Treg, with job-related ranking and optional authorized business contact enrichment.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-recruit\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-recruit\u002FSKILL.md",[133],{"categoryNo":134,"categoryName":135,"taxonomyType":136,"taxonomyTypeDesc":137},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[128,27,90,44,43,139,140,141,142,143,101,144,145,146,124,147,148,149,150,28,108,105],"email","enrichment","business","evidence","phone","ranking","post","job description","for","person","candidate","reason",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":82,"licenseFileUrl":155,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":45},"01M6WN8R5RXSMHM9B4D9FAFX42","rea-growth","Analyze a company’s public growth and content through Treg, distinguish observations from hypotheses, and produce an evidence-linked playbook within an approved budget.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-rea-growth\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-rea-growth\u002FSKILL.md",[],[159,160,161,27,90,44,162,163,43,164,117,165,166,167,142,101,168,169,28,108,105],"growth","rea","rea growth","produce","content","playbook","marketing","analyze","public","observations","company",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":82,"licenseFileUrl":174,"sourceHtmlUrl":175,"categories":176,"keywords":177,"publishedAt":45},"01M6WN2EVE3RQRGWAKBT4S7YT2","make-ugc","Create original AI UGC-style product videos through Treg: research hooks, approve a licensed presenter and voice, generate clips, add captions and report costs.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-make-ugc\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-make-ugc\u002FSKILL.md",[],[178,179,27,180,90,181,44,182,183,184,185,186,101,187,188,189,190,191,192,28],"make","make ugc","research","create","Video","Captions","ads","short","hooks","head","style","niche","trending","talking-head","approve",{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":82,"licenseFileUrl":197,"sourceHtmlUrl":198,"categories":199,"keywords":200,"publishedAt":45},"01M6WN10ARAA63Y8K1YNGXJ2RM","lead-signals","Find and qualify public buying signals through Treg, rank fitting business accounts and optionally enrich authorized business contact information.","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-lead-signals\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboisenoise\u002Fskills-collections\u002Fblob\u002Fmain\u002Fskills\u002Fantigravity-lead-signals\u002FSKILL.md",[],[201,202,203,27,90,44,204,205,141,206,207,101,208,209,210,211,212,213,214,28],"signals","lead","lead signals","how","find","ready","as","how to","qualify","people","information","enrich","changes","funding"]