[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75S2N7ESKXHTWMAQA1NM4BC":3,"skill-same:01M75S2N7ESKXHTWMAQA1NM4BC":70},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":14,"categories":15,"keywords":16,"publishedAt":17,"linkOnly":18,"markdownContent":19,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":25,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":28,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M75S2N7ESKXHTWMAQA1NM4BC","day",null,"paranoica\u002Fbedrock","paranoica","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F57444931?v=4","01M75S0NENDBV4XTD2WQ53TJ9F","01M75S0NF7JWQ0SKVCWWPFJFS2",3,"MIT","https:\u002F\u002Fgithub.com\u002Fparanoica\u002Fbedrock\u002Fblob\u002Fmain\u002Fplugins\u002Fbedrock\u002Fskills\u002Fday\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: day\ndescription: The working loop for any task — intake, plan, critic, cut, implement, review, deliver. Use first for every new task, feature or change: \"надо добавить\", \"сделай\", \"build X\", \"начинаем день\".\n---\n\n# The working loop\n\nOne block = one task from \"taken\" to \"done and merged\" (D031). Each step ends on a check.\nThe only hook that refuses is the pull-request review gate; everything else here is the\nsession's own discipline.\n\n## Triggers\n- RU: «сделай X», «новая задача», «начинаем день», «закрываем день»\n- EN: \"build X\", \"fix X\", \"new task\", \"start the day\", \"close the day\"\n\n## 0. Start of day (once per work day)\nFollow `references\u002Fstart-of-day.md`. Done when the owner has the three-line summary\n\"вчера \u002F входящие \u002F сегодня\".\n\n## 1. Intake\n- Size the request: R1 (no logic), R2 (ordinary code), R3 (risky or new), and P0–P3 (D032).\n- P0 goes to the urgent path in `references\u002Furgent.md` and skips the plan.\n- Look facts up instead of asking. Questions depend on the risk (D033):\n  - R1: none.\n  - R2: only when the scope is genuinely unclear. One message, at most five questions, each\n    with a default and the cost of a wrong default.\n  - R3 or a new feature, when the owner says «грилл» or the task is murky: an interview, one\n    question at a time, each answer saved to the plan file at once. Otherwise as R2.\n- Log it: `bedrock log taken --block \u003Cid> --detail \"\u003CR\u002FP> \u003Ctitle>\"`.\n\nDone when: the `taken` line carries R and P, and the questions (or \"no questions\") are in\nthe plan file. R1 has no plan file: its `taken` line is the record.\n\n## 2. Plan\n- R1: no plan. R2: a short plan. R3: a full plan with a design section (D035).\n- Write it from `references\u002Fplan.md` to `~\u002Fprojects-days\u002F\u003Cproject>\u002F\u003Cdate>\u002F\u003Cblock>\u002Fplan.md`.\n- Every plan has: done-when (checkable), assumptions, files, tests named with what they\n  assert, tasks with who and model, the agents it uses, estimate, out of scope.\n- The agents list says which roles run and how often, so `bedrock agents` can be read\n  against it afterwards. Each agent is the bedrock role that fits (inventory, researcher,\n  implementer, reviewer, critic); general-purpose only where no role fits, since it runs on\n  the session's own model.\n- Research per `references\u002Fresearch.md` when the plan rests on library behaviour (D034).\n- The project's packs feed the plan: their test checklists go into Tests, their rules into\n  the implementer brief's \"Keep true\".\n\nDone when: the plan file exists and its done-when is a test, a command or a number.\n\n## 3. Critic\n- R1: none. R2: one critic agent, one round. R3: two critics on different models, at most\n  two rounds (D036). A second round with no fewer blockers goes to the owner.\n- Brief from the plugin's `templates\u002Fbriefs\u002Fbrief.md`; give it the plan, done-when,\n  decisions and code rules.\n- Take each finding with evidence or drop it; a blocker is re-read in the code first.\n- Tell the owner only the delta: \"критик: 5 найдено, 3 принято, +20 мин\".\n\nDone when: the plan file has a \"Critic\" section with taken and dropped findings.\n\n## 4. Owner's go\n- R1: the request itself is the go.\n- R2, R3: show the plan in five lines and wait for «го» (one go covers the whole plan, D016).\n- Then `bedrock log plan-approved --block \u003Cid>`, and:\n  ```\n  bedrock session set task=\"\u003Ctitle>\" plan='[0,\u003Cn>]' estimate_min=\u003Cm> state=work\n  ```\n\nDone when: the log line exists and the status line shows the task.\n\n## 5. Cut into tasks\n- One task = one commit with its own test, about 30–40 minutes of human work, its own files\n  (D037). Add each with `bedrock backlog add '\u003Cjson>'`.\n- Set auto-continue for the first task:\n  `bedrock session set autocontinue.next='{\"id\": \"T1\", \"title\": \"...\", \"safe\": true}'`.\n  A task with an outward or destructive step is never `safe`: set `null` instead, so the\n  session stops there and asks.\n\nDone when: every task is in the backlog with files, test, who and estimate.\n\n## 6. Implement each task\n1. `bedrock backlog claim \u003Cid> --session \"$CLAUDE_CODE_SESSION_ID\"` (it sets `doing`).\n2. Follow `references\u002Fimplement.md` (D039): a failing test first, minimal code, verify after\n   every few edits, refactor only while green, read the diff yourself, commit.\n3. After the commit: `bedrock backlog status \u003Cid> done`,\n   `bedrock log task-done --block \u003Cblock> --ref \u003Ccommit>`,\n   `bedrock session set plan='[\u003Ck>,\u003Cn>]'`, and point `autocontinue.next` at the next task\n   in order. It is `null` when none is left or the next one is not safe. Never skip over an\n   unsafe task to a later one.\n\nDone when: the task's test failed before and passes now, the commit exists, and the\nbacklog shows the task done.\n\n## 7. Review\n- Use the `review` skill for every block. It scales itself: R1 gets the checks and a\n  quick read, R2 and R3 get both reviews (D050).\n- The full suite runs once at the end of the block and before a PR: `bedrock cmd test`\n  (D040).\n- `bedrock log review --block \u003Cid> --detail \"\u003Cthe summary line>\"`.\n\nDone when: the review summary line is logged and `bedrock review pass \u003Cbranch> --agent \u003Cid>`\nis recorded with the reviewer agent that ran.\n\n## 8. Deliver\nFollow `references\u002Fdeliver.md`: branch and PR per the project, live verification, and every\noutward step only on the owner's word in the conversation (D052, D053). After a merge:\n`bedrock log merged --block \u003Cid> --ref \u003CPR>`.\n\nDone when: the change is checked live, or the report says plainly that it was not, or it\nnames the outward step that waits for the owner's word.\n\n## 9. Close the block\n- `bedrock log closed --block \u003Cid>` and `bedrock minutes \u003Cid>` into the report.\n- Update the knowledge base for every module touched; `bedrock kb drift` shows what is left.\n- Report to the owner in plain Russian (D021): what changed for the product, checked live\n  or not, what is needed from the owner, what is next.\n- `bedrock session set state=null task=null plan=null autocontinue=null`.\n\nDone when: the log line, the base update and the report are all done.\n\n## End of day\n`references\u002Fstart-of-day.md` § End of day. Done when the owner has the day summary.\n","# The working loop\n\nOne block = one task from \"taken\" to \"done and merged\" (D031). Each step ends on a check.\nThe only hook that refuses is the pull-request review gate; everything else here is the\nsession's own discipline.\n\n## Triggers\n- RU: «сделай X», «новая задача», «начинаем день», «закрываем день»\n- EN: \"build X\", \"fix X\", \"new task\", \"start the day\", \"close the day\"\n\n## 0. Start of day (once per work day)\nFollow `references\u002Fstart-of-day.md`. Done when the owner has the three-line summary\n\"вчера \u002F входящие \u002F сегодня\".\n\n## 1. Intake\n- Size the request: R1 (no logic), R2 (ordinary code), R3 (risky or new), and P0–P3 (D032).\n- P0 goes to the urgent path in `references\u002Furgent.md` and skips the plan.\n- Look facts up instead of asking. Questions depend on the risk (D033):\n  - R1: none.\n  - R2: only when the scope is genuinely unclear. One message, at most five questions, each\n    with a default and the cost of a wrong default.\n  - R3 or a new feature, when the owner says «грилл» or the task is murky: an interview, one\n    question at a time, each answer saved to the plan file at once. Otherwise as R2.\n- Log it: `bedrock log taken --block \u003Cid> --detail \"\u003CR\u002FP> \u003Ctitle>\"`.\n\nDone when: the `taken` line carries R and P, and the questions (or \"no questions\") are in\nthe plan file. R1 has no plan file: its `taken` line is the record.\n\n## 2. Plan\n- R1: no plan. R2: a short plan. R3: a full plan with a design section (D035).\n- Write it from `references\u002Fplan.md` to `~\u002Fprojects-days\u002F\u003Cproject>\u002F\u003Cdate>\u002F\u003Cblock>\u002Fplan.md`.\n- Every plan has: done-when (checkable), assumptions, files, tests named with what they\n  assert, tasks with who and model, the agents it uses, estimate, out of scope.\n- The agents list says which roles run and how often, so `bedrock agents` can be read\n  against it afterwards. Each agent is the bedrock role that fits (inventory, researcher,\n  implementer, reviewer, critic); general-purpose only where no role fits, since it runs on\n  the session's own model.\n- Research per `references\u002Fresearch.md` when the plan rests on library behaviour (D034).\n- The project's packs feed the plan: their test checklists go into Tests, their rules into\n  the implementer brief's \"Keep true\".\n\nDone when: the plan file exists and its done-when is a test, a command or a number.\n\n## 3. Critic\n- R1: none. R2: one critic agent, one round. R3: two critics on different models, at most\n  two rounds (D036). A second round with no fewer blockers goes to the owner.\n- Brief from the plugin's `templates\u002Fbriefs\u002Fbrief.md`; give it the plan, done-when,\n  decisions and code rules.\n- Take each finding with evidence or drop it; a blocker is re-read in the code first.\n- Tell the owner only the delta: \"критик: 5 найдено, 3 принято, +20 мин\".\n\nDone when: the plan file has a \"Critic\" section with taken and dropped findings.\n\n## 4. Owner's go\n- R1: the request itself is the go.\n- R2, R3: show the plan in five lines and wait for «го» (one go covers the whole plan, D016).\n- Then `bedrock log plan-approved --block \u003Cid>`, and:\n  ```\n  bedrock session set task=\"\u003Ctitle>\" plan='[0,\u003Cn>]' estimate_min=\u003Cm> state=work\n  ```\n\nDone when: the log line exists and the status line shows the task.\n\n## 5. Cut into tasks\n- One task = one commit with its own test, about 30–40 minutes of human work, its own files\n  (D037). Add each with `bedrock backlog add '\u003Cjson>'`.\n- Set auto-continue for the first task:\n  `bedrock session set autocontinue.next='{\"id\": \"T1\", \"title\": \"...\", \"safe\": true}'`.\n  A task with an outward or destructive step is never `safe`: set `null` instead, so the\n  session stops there and asks.\n\nDone when: every task is in the backlog with files, test, who and estimate.\n\n## 6. Implement each task\n1. `bedrock backlog claim \u003Cid> --session \"$CLAUDE_CODE_SESSION_ID\"` (it sets `doing`).\n2. Follow `references\u002Fimplement.md` (D039): a failing test first, minimal code, verify after\n   every few edits, refactor only while green, read the diff yourself, commit.\n3. After the commit: `bedrock backlog status \u003Cid> done`,\n   `bedrock log task-done --block \u003Cblock> --ref \u003Ccommit>`,\n   `bedrock session set plan='[\u003Ck>,\u003Cn>]'`, and point `autocontinue.next` at the next task\n   in order. It is `null` when none is left or the next one is not safe. Never skip over an\n   unsafe task to a later one.\n\nDone when: the task's test failed before and passes now, the commit exists, and the\nbacklog shows the task done.\n\n## 7. Review\n- Use the `review` skill for every block. It scales itself: R1 gets the checks and a\n  quick read, R2 and R3 get both reviews (D050).\n- The full suite runs once at the end of the block and before a PR: `bedrock cmd test`\n  (D040).\n- `bedrock log review --block \u003Cid> --detail \"\u003Cthe summary line>\"`.\n\nDone when: the review summary line is logged and `bedrock review pass \u003Cbranch> --agent \u003Cid>`\nis recorded with the reviewer agent that ran.\n\n## 8. Deliver\nFollow `references\u002Fdeliver.md`: branch and PR per the project, live verification, and every\noutward step only on the owner's word in the conversation (D052, D053). After a merge:\n`bedrock log merged --block \u003Cid> --ref \u003CPR>`.\n\nDone when: the change is checked live, or the report says plainly that it was not, or it\nnames the outward step that waits for the owner's word.\n\n## 9. Close the block\n- `bedrock log closed --block \u003Cid>` and `bedrock minutes \u003Cid>` into the report.\n- Update the knowledge base for every module touched; `bedrock kb drift` shows what is left.\n- Report to the owner in plain Russian (D021): what changed for the product, checked live\n  or not, what is needed from the owner, what is next.\n- `bedrock session set state=null task=null plan=null autocontinue=null`.\n\nDone when: the log line, the base update and the report are all done.\n\n## End of day\n`references\u002Fstart-of-day.md` § End of day. Done when the owner has the day summary.\n",{},"main","ff167da1e0a6cfc5bdb942eb3e109845f4f88d23","plugins\u002Fbedrock\u002Fskills\u002Fday",1,"https:\u002F\u002Fgithub.com\u002Fparanoica\u002Fbedrock","https:\u002F\u002Fgithub.com\u002Fparanoica","https:\u002F\u002Fgamesense.pub\u002F","2026-11-08 01:01:15",{"source":7,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add paranoica\u002Fbedrock --skill day",{"tool":36,"command":37},"bunx","bunx skills add paranoica\u002Fbedrock --skill day",{"tool":39,"command":40},"pnpm","pnpm dlx skills add paranoica\u002Fbedrock --skill day","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fparanoica\u002Fbedrock\u002Fblob\u002Fmain\u002Fplugins\u002Fbedrock\u002Fskills\u002Fday\u002FSKILL.md",true,[44,50,54,58,62,66],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"references\u002Fdeliver.md","REFERENCE","参考文档",1366,"https:\u002F\u002Fgithub.com\u002Fparanoica\u002Fbedrock\u002Fblob\u002Fmain\u002Fplugins\u002Fbedrock\u002Fskills\u002Fday\u002Freferences\u002Fdeliver.md",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fimplement.md",1585,"https:\u002F\u002Fgithub.com\u002Fparanoica\u002Fbedrock\u002Fblob\u002Fmain\u002Fplugins\u002Fbedrock\u002Fskills\u002Fday\u002Freferences\u002Fimplement.md",{"path":55,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fplan.md",1135,"https:\u002F\u002Fgithub.com\u002Fparanoica\u002Fbedrock\u002Fblob\u002Fmain\u002Fplugins\u002Fbedrock\u002Fskills\u002Fday\u002Freferences\u002Fplan.md",{"path":59,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fresearch.md",728,"https:\u002F\u002Fgithub.com\u002Fparanoica\u002Fbedrock\u002Fblob\u002Fmain\u002Fplugins\u002Fbedrock\u002Fskills\u002Fday\u002Freferences\u002Fresearch.md",{"path":63,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fstart-of-day.md",1935,"https:\u002F\u002Fgithub.com\u002Fparanoica\u002Fbedrock\u002Fblob\u002Fmain\u002Fplugins\u002Fbedrock\u002Fskills\u002Fday\u002Freferences\u002Fstart-of-day.md",{"path":67,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Furgent.md",892,"https:\u002F\u002Fgithub.com\u002Fparanoica\u002Fbedrock\u002Fblob\u002Fmain\u002Fplugins\u002Fbedrock\u002Fskills\u002Fday\u002Freferences\u002Furgent.md",[71,78,85,92,99,106],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":17},"01M75S4P9CEEETSAKSEJKA76KG","writing","Write or rewrite skills, agent definitions, briefs and rule files by the D013 rules, then check them. Use for \"напиши скилл\", \"поправь агента\", \"write a skill\", \"edit this brief\".","https:\u002F\u002Fgithub.com\u002Fparanoica\u002Fbedrock\u002Fblob\u002Fmain\u002Fplugins\u002Fbedrock\u002Fskills\u002Fwriting\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":17},"01M75S4KZRNVBQP46Q33X62R35","triage","Bug triage — reproduce each report on the current version, group duplicates, set priority, decide fix, defer or decline. Use for \"разбери баги\", \"что с репортами QA\", \"triage\", \"new bug reports\".","https:\u002F\u002Fgithub.com\u002Fparanoica\u002Fbedrock\u002Fblob\u002Fmain\u002Fplugins\u002Fbedrock\u002Fskills\u002Ftriage\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":17},"01M75S4H283C8XRHFM6E7TQHV4","start","Start a project with bedrock — a new one by interview, or an existing one by onboarding; writes the base, AGENTS.md, workspace settings and verified commands. Use for \"новый проект\", \"подключи проект\", \"start a project\".","https:\u002F\u002Fgithub.com\u002Fparanoica\u002Fbedrock\u002Fblob\u002Fmain\u002Fplugins\u002Fbedrock\u002Fskills\u002Fstart\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":17},"01M75S4EVW60KBZJGZWEZJYXY7","review","Review gate for a finished block — deterministic checks, code review, plan-compliance review, silent fixes, rounds until clean. Use for \"проверь\", \"ревью\", \"review this\", before any PR.","https:\u002F\u002Fgithub.com\u002Fparanoica\u002Fbedrock\u002Fblob\u002Fmain\u002Fplugins\u002Fbedrock\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":17},"01M75S4BY5EMAFTJECKJ6ZC5EP","retro","Weekly retro — read the week's logs, agents, reviews and failures, find what repeats, tune the system, plan a realistic next week. Use for \"ретро\", \"итоги недели\", \"retro\", \"how did the week go\".","https:\u002F\u002Fgithub.com\u002Fparanoica\u002Fbedrock\u002Fblob\u002Fmain\u002Fplugins\u002Fbedrock\u002Fskills\u002Fretro\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":17},"01M75S47TW93TAZ04HD75JJ98K","night","Autonomous work until morning — a pre-sleep check, the allowed list, auto-continue with fuses, a watchdog, a morning report. Use for \"автономно до утра\", \"поработай ночью\", \"work overnight\".","https:\u002F\u002Fgithub.com\u002Fparanoica\u002Fbedrock\u002Fblob\u002Fmain\u002Fplugins\u002Fbedrock\u002Fskills\u002Fnight\u002FSKILL.md",[],[]]