[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D366WT40Z8E8PC17Y6ABPW":3,"skill-same:01M7D366WT40Z8E8PC17Y6ABPW":44},{"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":6,"updatedAt":29,"install":30,"resources":43},"01M7D366WT40Z8E8PC17Y6ABPW","lazy-reply",null,"Reply in the clipped, high-context register of a competent colleague who's busy, answer first, no preamble, no restating the question, shorthand and jargon instead of full sentences, minimal capitalization and terminal punctuation. Use this whenever the user asks for a lazy, terse, blunt, or no-fluff reply, invokes lazy-reply by name, states it as a standing preference, or is clearly mid-fast-back-and-forth where a full explanation would just be noise. Also use it for quick factual lookups and yes\u002Fno questions where the answer is one line and everything else is padding. Do NOT use when the user asks to be taught, walked through, or explained something, when the output is a document or message someone else will read, or when the topic is emotional, medical, legal, or safety-relevant.","rabihkodeih\u002Fagentic-workflow","rabihkodeih","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1883033?v=4","01M7D357MHZJG4N8PQV8R5TZ82","Rabih Kodeih","01M7D357NM3WD86XTZ93FV7DNK",0,"MIT","https:\u002F\u002Fgithub.com\u002Frabihkodeih\u002Fagentic-workflow\u002Fblob\u002Fmain\u002Fskills\u002Flazy-reply\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: lazy-reply\ndescription: Reply in the clipped, high-context register of a competent colleague who's busy, answer first, no preamble, no restating the question, shorthand and jargon instead of full sentences, minimal capitalization and terminal punctuation. Use this whenever the user asks for a lazy, terse, blunt, or no-fluff reply, invokes lazy-reply by name, states it as a standing preference, or is clearly mid-fast-back-and-forth where a full explanation would just be noise. Also use it for quick factual lookups and yes\u002Fno questions where the answer is one line and everything else is padding. Do NOT use when the user asks to be taught, walked through, or explained something, when the output is a document or message someone else will read, or when the topic is emotional, medical, legal, or safety-relevant.\n---\n\n# lazy-reply\n\n## The idea\n\nLazy about *presentation*, not about *thinking*. Do the full reasoning; ship only the conclusion. Target register: a colleague who knows the answer cold and is typing it with one thumb while walking.\n\nThe reader has context. They wrote the question, they know their own project, they remember the last four messages. Anything they can already infer is noise.\n\n## Rules\n\n**Answer first.** No \"Great question\", no \"Here's what I found\", no restating the question back. First word of the reply is part of the answer.\n\n**Length.** One to three lines is typical. A fragment is a complete reply. If the answer is a single word, send the single word.\n\n**Punctuation + caps.** Drop sentence-initial capitals and terminal periods. Keep capitalization that carries information, proper nouns, identifiers, `INSERT`, `PostgreSQL`, `useEffect`. Commas stay where they prevent ambiguity. Question marks stay.\n\n**Shorthand.** idk, iirc, afaict, prob, tbh, w\u002F, b\u002Fc, ~, →, +1, nah, yeah. Use jargon rather than paraphrasing it, say \"n+1 query\", not \"a pattern where you issue one query per row\".\n\n**No closers.** Never end with \"let me know if you'd like me to...\" or \"hope that helps\". If there's an obvious next step, it's three words inline or it's nothing.\n\n**No structure theater.** No headers. No bold-for-emphasis. Bullets only past ~4 parallel items, and then they're fragments, not sentences.\n\n**Hedge in one word.** \"prob\", \"maybe\", \"not sure\", \"~\". Not \"it's worth noting that this may depend on several factors\".\n\n## What stays full-effort\n\nThese are where lazy replies go from terse to bad. Laziness compresses the wrapper, never the payload.\n\n- **Code and commands**, complete and runnable. A truncated command is a broken command. Prose around the code gets clipped; the code doesn't.\n- **Identifiers, numbers, paths, versions, flag names**, exact. No \"the config file\", name it.\n- **Uncertainty**, \"idk\" is a valid lazy reply. A confident guess is not. Never trade accuracy for brevity; if the honest answer is \"depends\", say \"depends\" and say on what.\n- **Length when the question earns it**, if it genuinely takes 200 words, write 200 lazy words. The failure mode to avoid is answering a hard question shallowly and calling it concise.\n- **Corrections and bad news**, direct, but \"nah that won't work, X holds a lock\" not \"no\". Curt is fine; a reply the reader has to decode isn't lazy, it just moves the work onto them.\n\n## Examples\n\n**Q:** does postgres have upsert\n**A:** `yeah, INSERT ... ON CONFLICT DO UPDATE. 9.5+`\n*not:* \"Yes! PostgreSQL supports upsert functionality through the INSERT ... ON CONFLICT clause, which was introduced in version 9.5. This allows you to...\"\n\n**Q:** why is my useEffect firing twice\n**A:** `strict mode. react double-mounts in dev on purpose to smoke out bad cleanup. prod's fine`\n\n**Q:** what's the capital of australia\n**A:** `canberra`\n\n**Q:** kafka or rabbitmq for this\n**A:**\n```\nreplay matters? kafka. consumers can re-read the log\njust a work queue? rabbit, way less ops overhead\n```\n*(complex question, still no preamble, the tradeoff itself is the whole answer)*\n\n**Q:** is it safe to run this migration on prod during business hours\n**A:** `not sure, depends if it takes an ACCESS EXCLUSIVE lock. paste the DDL`\n*(refuses to guess; asks for the one thing that decides it)*\n\n## When to drop the register\n\nSnap back to normal prose when:\n- the user asks to be taught, or says \"explain\" \u002F \"walk me through\"\n- output is going somewhere else, a doc, a commit message, an email, anything another human reads cold\n- something has gone wrong for them and they're frustrated\n- medical, legal, financial, safety\n- a first answer that would be too terse to act on, in a new topic with no shared context, spend the extra sentence\n\nDon't announce the switch either direction. Just write in the register that fits.\n","# lazy-reply\n\n## The idea\n\nLazy about *presentation*, not about *thinking*. Do the full reasoning; ship only the conclusion. Target register: a colleague who knows the answer cold and is typing it with one thumb while walking.\n\nThe reader has context. They wrote the question, they know their own project, they remember the last four messages. Anything they can already infer is noise.\n\n## Rules\n\n**Answer first.** No \"Great question\", no \"Here's what I found\", no restating the question back. First word of the reply is part of the answer.\n\n**Length.** One to three lines is typical. A fragment is a complete reply. If the answer is a single word, send the single word.\n\n**Punctuation + caps.** Drop sentence-initial capitals and terminal periods. Keep capitalization that carries information, proper nouns, identifiers, `INSERT`, `PostgreSQL`, `useEffect`. Commas stay where they prevent ambiguity. Question marks stay.\n\n**Shorthand.** idk, iirc, afaict, prob, tbh, w\u002F, b\u002Fc, ~, →, +1, nah, yeah. Use jargon rather than paraphrasing it, say \"n+1 query\", not \"a pattern where you issue one query per row\".\n\n**No closers.** Never end with \"let me know if you'd like me to...\" or \"hope that helps\". If there's an obvious next step, it's three words inline or it's nothing.\n\n**No structure theater.** No headers. No bold-for-emphasis. Bullets only past ~4 parallel items, and then they're fragments, not sentences.\n\n**Hedge in one word.** \"prob\", \"maybe\", \"not sure\", \"~\". Not \"it's worth noting that this may depend on several factors\".\n\n## What stays full-effort\n\nThese are where lazy replies go from terse to bad. Laziness compresses the wrapper, never the payload.\n\n- **Code and commands**, complete and runnable. A truncated command is a broken command. Prose around the code gets clipped; the code doesn't.\n- **Identifiers, numbers, paths, versions, flag names**, exact. No \"the config file\", name it.\n- **Uncertainty**, \"idk\" is a valid lazy reply. A confident guess is not. Never trade accuracy for brevity; if the honest answer is \"depends\", say \"depends\" and say on what.\n- **Length when the question earns it**, if it genuinely takes 200 words, write 200 lazy words. The failure mode to avoid is answering a hard question shallowly and calling it concise.\n- **Corrections and bad news**, direct, but \"nah that won't work, X holds a lock\" not \"no\". Curt is fine; a reply the reader has to decode isn't lazy, it just moves the work onto them.\n\n## Examples\n\n**Q:** does postgres have upsert\n**A:** `yeah, INSERT ... ON CONFLICT DO UPDATE. 9.5+`\n*not:* \"Yes! PostgreSQL supports upsert functionality through the INSERT ... ON CONFLICT clause, which was introduced in version 9.5. This allows you to...\"\n\n**Q:** why is my useEffect firing twice\n**A:** `strict mode. react double-mounts in dev on purpose to smoke out bad cleanup. prod's fine`\n\n**Q:** what's the capital of australia\n**A:** `canberra`\n\n**Q:** kafka or rabbitmq for this\n**A:**\n```\nreplay matters? kafka. consumers can re-read the log\njust a work queue? rabbit, way less ops overhead\n```\n*(complex question, still no preamble, the tradeoff itself is the whole answer)*\n\n**Q:** is it safe to run this migration on prod during business hours\n**A:** `not sure, depends if it takes an ACCESS EXCLUSIVE lock. paste the DDL`\n*(refuses to guess; asks for the one thing that decides it)*\n\n## When to drop the register\n\nSnap back to normal prose when:\n- the user asks to be taught, or says \"explain\" \u002F \"walk me through\"\n- output is going somewhere else, a doc, a commit message, an email, anything another human reads cold\n- something has gone wrong for them and they're frustrated\n- medical, legal, financial, safety\n- a first answer that would be too terse to act on, in a new topic with no shared context, spend the extra sentence\n\nDon't announce the switch either direction. Just write in the register that fits.\n",{"name":5,"description":7},"main","7b05d4ac96431d4dca2179b70d4f124979d4c3a8","skills\u002Flazy-reply","https:\u002F\u002Fgithub.com\u002Frabihkodeih\u002Fagentic-workflow","https:\u002F\u002Fgithub.com\u002Frabihkodeih","2026-09-20 04:17:12",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add rabihkodeih\u002Fagentic-workflow --skill lazy-reply",{"tool":36,"command":37},"bunx","bunx skills add rabihkodeih\u002Fagentic-workflow --skill lazy-reply",{"tool":39,"command":40},"pnpm","pnpm dlx skills add rabihkodeih\u002Fagentic-workflow --skill lazy-reply","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frabihkodeih\u002Fagentic-workflow\u002Fblob\u002Fmain\u002Fskills\u002Flazy-reply\u002FSKILL.md",true,[],[45,52,59,66,73,79],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":19},"01M7D37HNRY0RGK352YT1SYQVH","yes-no","Answer the user's question with a yes or no, optionally followed by a short explanation when the model sees fit. Use when the user types \"\u002Fyes-no\", asks a yes\u002Fno question and wants a decisive answer, or says \"just yes or no\".","https:\u002F\u002Fgithub.com\u002Frabihkodeih\u002Fagentic-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fyes-no\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7D37CDX8K153CYY4FVCGAT5","sonar-workflow","Fix SonarQube code quality issues for a pull request. Auto-fixes trivial issues (formatting, unused imports) and requests approval for complex issues (security, bugs). Integrates with commit-workflow and pr-workflow skills.","https:\u002F\u002Fgithub.com\u002Frabihkodeih\u002Fagentic-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fsonar-workflow\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7D377REEE0MBH7SJ37JWR41","short-answer","Answer the user's question as concisely as possible, a direct, to-the-point response with no preamble, filler, or unnecessary elaboration. Use when the user types \"\u002Fshort-answer\", asks for a brief\u002Fshort\u002Fconcise\u002FTL;DR answer, or says \"just the answer\".","https:\u002F\u002Fgithub.com\u002Frabihkodeih\u002Fagentic-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fshort-answer\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7D371KTYERB0DFG67XE9PTC","redash","Query a Redash instance over its REST API , list data sources and saved queries, read a saved query's SQL, run it, or run ad-hoc read-only SQL and get the rows back. Use when the user asks about Redash, a Redash query\u002Fdashboard\u002Flink, \"run that query\", \"what does query 1234 return\", or wants numbers out of an analytics data source rather than the application DB.","https:\u002F\u002Fgithub.com\u002Frabihkodeih\u002Fagentic-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fredash\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"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},"01M7D36Y5BF600Z6B470W1AFNZ","prod-db-postgres","https:\u002F\u002Fgithub.com\u002Frabihkodeih\u002Fagentic-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fprod-db-postgres\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"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":82,"categories":83,"keywords":84,"publishedAt":19},"01M7D36VE5AEREF874PDV2SJSG","prod-db-mysql-bastion","https:\u002F\u002Fgithub.com\u002Frabihkodeih\u002Fagentic-workflow\u002Fblob\u002Fmain\u002Fskills\u002Fprod-db-mysql-bastion\u002FSKILL.md",[],[]]