[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75S38B8WJQND298ASQPX9FS":3,"skill-same:01M75S38B8WJQND298ASQPX9FS":45},{"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":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M75S38B8WJQND298ASQPX9FS","hunt",null,"Bug hunter — try to break code that is already green, with properties, boundaries, hostile input and concurrency. Use for \"сломай это\", \"поищи баги\", \"break it\", after green on R2\u002FR3.","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\u002Fhunt\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: hunt\ndescription: Bug hunter — try to break code that is already green, with properties, boundaries, hostile input and concurrency. Use for \"сломай это\", \"поищи баги\", \"break it\", after green on R2\u002FR3.\n---\n\n# Bug hunt\n\nGreen tests prove the cases someone thought of. A hunt looks for the ones nobody did (D049).\n\n## Triggers\n- RU: «сломай это», «поищи баги», «что тут может упасть»\n- EN: \"break it\", \"hunt for bugs\", \"what could go wrong here\"\n\n## When it runs\n- Always on R3 blocks and on files inside the project's `critical_zones`.\n- Briefly on R2, after the block's tests are green.\n- On the hottest modules (`bedrock arch hotspots`) when the architecture review runs.\nDone when: the block's plan says which of these applies.\n\n## 1. Brief the hunter\nStart the `bug-hunter` agent with a brief from `templates\u002Fbriefs\u002Fbrief.md`:\n- Task: the module and the spec it must meet (plan done-when, decisions, module note).\n- Read: the code and its tests, in order.\n- Known: the cases the tests already cover.\n- Commands: the project's test command through `bedrock cmd`.\nDone when: the agent's report file exists.\n\n## 2. What the hunter tries\n1. **Properties from the spec**, not from the code: Hypothesis in Python, fast-check in TS.\n   Examples: a round trip returns the input, a sort keeps every element, a total never goes\n   negative. The libraries are dev dependencies, added only on the owner's word.\n2. **Boundaries:** empty, null, zero, max, one past max, the first and the last element.\n3. **Hostile input:** injection strings, huge input, odd unicode, wrong types.\n4. **Concurrency:** the same request twice at once, a replay, a kill mid-run.\n5. **Scale:** the data volume the plan's Scale section names.\n6. **Metamorphic checks** for text and extraction systems (the domain pack names them):\n   a paraphrase keeps the result, an added negation never yields a positive fact, a\n   relative's condition is not the subject's, document order does not change the facts, and a\n   fact split across a chunk boundary is still found.\nDone when: each tried technique is listed in the report with its result.\n\n## 3. Every finding is checked\n1. Minimise it to the smallest failing input.\n2. A `verifier` agent re-runs it from scratch. Agent-written property reports are often\n   invalid: only a reproduced failure counts.\n3. Confirmed → the `debug` skill, cause first. Spec ambiguity → one question to the owner.\nDone when: each finding is reproduced and routed, or cut with the verifier's reason.\n\n## 4. Keep what it found\nA confirmed finding leaves a regression test at the right seam (the `debug` skill does this)\nand, when it is a pattern, a line in the domain pack or a failure note in the knowledge base.\nDone when: each confirmed finding has its test or its note.\n","# Bug hunt\n\nGreen tests prove the cases someone thought of. A hunt looks for the ones nobody did (D049).\n\n## Triggers\n- RU: «сломай это», «поищи баги», «что тут может упасть»\n- EN: \"break it\", \"hunt for bugs\", \"what could go wrong here\"\n\n## When it runs\n- Always on R3 blocks and on files inside the project's `critical_zones`.\n- Briefly on R2, after the block's tests are green.\n- On the hottest modules (`bedrock arch hotspots`) when the architecture review runs.\nDone when: the block's plan says which of these applies.\n\n## 1. Brief the hunter\nStart the `bug-hunter` agent with a brief from `templates\u002Fbriefs\u002Fbrief.md`:\n- Task: the module and the spec it must meet (plan done-when, decisions, module note).\n- Read: the code and its tests, in order.\n- Known: the cases the tests already cover.\n- Commands: the project's test command through `bedrock cmd`.\nDone when: the agent's report file exists.\n\n## 2. What the hunter tries\n1. **Properties from the spec**, not from the code: Hypothesis in Python, fast-check in TS.\n   Examples: a round trip returns the input, a sort keeps every element, a total never goes\n   negative. The libraries are dev dependencies, added only on the owner's word.\n2. **Boundaries:** empty, null, zero, max, one past max, the first and the last element.\n3. **Hostile input:** injection strings, huge input, odd unicode, wrong types.\n4. **Concurrency:** the same request twice at once, a replay, a kill mid-run.\n5. **Scale:** the data volume the plan's Scale section names.\n6. **Metamorphic checks** for text and extraction systems (the domain pack names them):\n   a paraphrase keeps the result, an added negation never yields a positive fact, a\n   relative's condition is not the subject's, document order does not change the facts, and a\n   fact split across a chunk boundary is still found.\nDone when: each tried technique is listed in the report with its result.\n\n## 3. Every finding is checked\n1. Minimise it to the smallest failing input.\n2. A `verifier` agent re-runs it from scratch. Agent-written property reports are often\n   invalid: only a reproduced failure counts.\n3. Confirmed → the `debug` skill, cause first. Spec ambiguity → one question to the owner.\nDone when: each finding is reproduced and routed, or cut with the verifier's reason.\n\n## 4. Keep what it found\nA confirmed finding leaves a regression test at the right seam (the `debug` skill does this)\nand, when it is a pattern, a line in the domain pack or a failure note in the knowledge base.\nDone when: each confirmed finding has its test or its note.\n",{"name":5,"description":7},"main","ff167da1e0a6cfc5bdb942eb3e109845f4f88d23","plugins\u002Fbedrock\u002Fskills\u002Fhunt",1,"https:\u002F\u002Fgithub.com\u002Fparanoica\u002Fbedrock","https:\u002F\u002Fgithub.com\u002Fparanoica","https:\u002F\u002Fgamesense.pub\u002F","2026-11-08 01:01:15",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add paranoica\u002Fbedrock --skill hunt",{"tool":37,"command":38},"bunx","bunx skills add paranoica\u002Fbedrock --skill hunt",{"tool":40,"command":41},"pnpm","pnpm dlx skills add paranoica\u002Fbedrock --skill hunt","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fparanoica\u002Fbedrock\u002Fblob\u002Fmain\u002Fplugins\u002Fbedrock\u002Fskills\u002Fhunt\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"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":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"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":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"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":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"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",[],[]]