[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71JJ7PPE2WPZXRTZ93FPQ8N":3,"skill-same:01M71JJ7PPE2WPZXRTZ93FPQ8N":89},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":5,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":48,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M71JJ7PPE2WPZXRTZ93FPQ8N","interrogate",null,"Run an adversarial review of code or a diff through independent reviewers, then lead-judge consensus, disagreements, and false positives. Use when the user asks to interrogate, challenge, stress-test, find blind spots, perform multi-model review, or when `henry-mode` needs adversarial judgment of a risky change.","caezium\u002Fskills","caezium","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113233555?v=4","01M71JB77ZPBAWEK009Y2W8BP7","Henry Zhang","01M71JB792NVXCWSYD27HQ0964",3,"MIT","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Finterrogate\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Finterrogate\u002FSKILL.md",[],[5,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"when","adversarial review","find","run","adversarial","change","test","multi","review","code","false","use","stress-test","spots","challenge","mode","model","diff","consensus","2026-11-10 10:12:30",false,"---\nname: interrogate\ndescription: Run an adversarial review of code or a diff through independent reviewers, then lead-judge consensus, disagreements, and false positives. Use when the user asks to interrogate, challenge, stress-test, find blind spots, perform multi-model review, or when `henry-mode` needs adversarial judgment of a risky change.\n---\n\n# Interrogate\n\nGive independent reviewers the same intent, code, and rubric. Diversity comes from independent reasoning and, where genuinely available, different model families—not invented personas or model aliases. The deliverable is a lead-reviewed verdict; never auto-apply findings.\n\n## Availability and fallback\n\n| Harness | Parallel mechanism | Model selection | Fallback |\n|---|---|---|---|\n| Cursor | Available Task\u002Fsubagent calls | Valid models exposed by the harness | Independent inherited-model reviewers or sequential passes |\n| Claude Code | Available Agent\u002FTask calls | Valid models exposed by the harness | Independent inherited-model reviewers or sequential passes |\n| Codex \u002F T3 | `spawn_agent`, drained with `wait_agent` | Valid overrides only when offered | Run waves within slot limits; inherit the parent model |\n| No delegation | None | None | Apply the rubric through separate sequential passes and label the result self-reviewed |\n\nOnly delegate when current user and system policy permit it. If true model diversity is unavailable, disclose that; never pretend reviewer labels are different models.\n\n## 1. Determine scope\n\nUse the exact files or diff the user names. Otherwise inspect the full feature-branch diff against its appropriate merge base. Include only surrounding files needed to trace the changed behavior; give every reviewer the same package.\n\n## 2. State intent\n\nWrite one paragraph describing what the change is meant to accomplish, derived from the user's request, commit\u002FPR context, and code. Ask only if ambiguity would materially change the review. Reviewers challenge execution, not the chosen product goal.\n\n## 3. Launch independent reviewers\n\nRead and fill these references:\n\n- [`references\u002Freviewer-prompt.md`](references\u002Freviewer-prompt.md)\n- [`references\u002Frubric.md`](references\u002Frubric.md)\n- [`references\u002Fcode-quality-review.md`](references\u002Fcode-quality-review.md)\n\nLaunch as many reviewers as the user requested or the harness can support usefully; default to three independent passes. Each reviewer is read-only and receives the identical filled prompt. Use model overrides only from valid harness-advertised choices. Require structured findings with severity, location, evidence, and an optional concrete suggestion.\n\n## 4. Aggregate\n\nDrain every reviewer. Merge duplicate findings, identify independent agreement, retain lone findings at lower confidence, and surface explicit disagreement. Inspect relevant code yourself before accepting a claim.\n\n## 5. Lead judgment\n\nRead [`references\u002Flead-judgment.md`](references\u002Flead-judgment.md), then categorize every finding:\n\n- **Act on:** concrete correctness, security, or maintainability issues that should block the change.\n- **Consider:** legitimate tradeoffs whose benefit may not exceed their cost now.\n- **Noted:** valid but low-priority or context-dependent observations.\n- **Dismissed:** wrong, nitpicky, hypothetical, or missing known context.\n\nName the reviewers that raised each finding and give a one-line rationale. Consensus is strong evidence, not a substitute for tracing the code.\n\n## Output contract\n\n1. `Intent`\n2. `Reviewers`—configuration, model-diversity status, and finding count\n3. `Act On`\n4. `Consider`\n5. `Noted`\n6. `Dismissed`\n7. `Agreement Map`\n8. `Coverage Gaps`\n\nDo not edit code or create review comments unless the user separately authorizes those actions.\n\n\u003C!-- Adapted from poteto\u002Fpstack interrogate, MIT License, Lauren Tan, cursor\u002Fplugins@51a96e0. -->\n","# Interrogate\n\nGive independent reviewers the same intent, code, and rubric. Diversity comes from independent reasoning and, where genuinely available, different model families—not invented personas or model aliases. The deliverable is a lead-reviewed verdict; never auto-apply findings.\n\n## Availability and fallback\n\n| Harness | Parallel mechanism | Model selection | Fallback |\n|---|---|---|---|\n| Cursor | Available Task\u002Fsubagent calls | Valid models exposed by the harness | Independent inherited-model reviewers or sequential passes |\n| Claude Code | Available Agent\u002FTask calls | Valid models exposed by the harness | Independent inherited-model reviewers or sequential passes |\n| Codex \u002F T3 | `spawn_agent`, drained with `wait_agent` | Valid overrides only when offered | Run waves within slot limits; inherit the parent model |\n| No delegation | None | None | Apply the rubric through separate sequential passes and label the result self-reviewed |\n\nOnly delegate when current user and system policy permit it. If true model diversity is unavailable, disclose that; never pretend reviewer labels are different models.\n\n## 1. Determine scope\n\nUse the exact files or diff the user names. Otherwise inspect the full feature-branch diff against its appropriate merge base. Include only surrounding files needed to trace the changed behavior; give every reviewer the same package.\n\n## 2. State intent\n\nWrite one paragraph describing what the change is meant to accomplish, derived from the user's request, commit\u002FPR context, and code. Ask only if ambiguity would materially change the review. Reviewers challenge execution, not the chosen product goal.\n\n## 3. Launch independent reviewers\n\nRead and fill these references:\n\n- [`references\u002Freviewer-prompt.md`](references\u002Freviewer-prompt.md)\n- [`references\u002Frubric.md`](references\u002Frubric.md)\n- [`references\u002Fcode-quality-review.md`](references\u002Fcode-quality-review.md)\n\nLaunch as many reviewers as the user requested or the harness can support usefully; default to three independent passes. Each reviewer is read-only and receives the identical filled prompt. Use model overrides only from valid harness-advertised choices. Require structured findings with severity, location, evidence, and an optional concrete suggestion.\n\n## 4. Aggregate\n\nDrain every reviewer. Merge duplicate findings, identify independent agreement, retain lone findings at lower confidence, and surface explicit disagreement. Inspect relevant code yourself before accepting a claim.\n\n## 5. Lead judgment\n\nRead [`references\u002Flead-judgment.md`](references\u002Flead-judgment.md), then categorize every finding:\n\n- **Act on:** concrete correctness, security, or maintainability issues that should block the change.\n- **Consider:** legitimate tradeoffs whose benefit may not exceed their cost now.\n- **Noted:** valid but low-priority or context-dependent observations.\n- **Dismissed:** wrong, nitpicky, hypothetical, or missing known context.\n\nName the reviewers that raised each finding and give a one-line rationale. Consensus is strong evidence, not a substitute for tracing the code.\n\n## Output contract\n\n1. `Intent`\n2. `Reviewers`—configuration, model-diversity status, and finding count\n3. `Act On`\n4. `Consider`\n5. `Noted`\n6. `Dismissed`\n7. `Agreement Map`\n8. `Coverage Gaps`\n\nDo not edit code or create review comments unless the user separately authorizes those actions.\n\n\u003C!-- Adapted from poteto\u002Fpstack interrogate, MIT License, Lauren Tan, cursor\u002Fplugins@51a96e0. -->\n",{"name":5,"description":7},"main","6ef866230c1ba3459fd08fc65141dfd37fffd41a",0,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills","https:\u002F\u002Fskills.henryzh.dev","https:\u002F\u002Fgithub.com\u002Fcaezium","henryzh.dev","quant, data science, full-stack, robotics.\r\nbuilding cool stuff","2026-08-24 19:21:44",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add caezium\u002Fskills --skill interrogate",{"tool":59,"command":60},"bunx","bunx skills add caezium\u002Fskills --skill interrogate",{"tool":62,"command":63},"pnpm","pnpm dlx skills add caezium\u002Fskills --skill interrogate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Finterrogate\u002FSKILL.md",true,[67,71,77,81,85],{"path":68,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":16},"LICENSE","许可证",1067,{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fcode-quality-review.md","REFERENCE","参考文档",5372,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Finterrogate\u002Freferences\u002Fcode-quality-review.md",{"path":78,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Flead-judgment.md",3465,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Finterrogate\u002Freferences\u002Flead-judgment.md",{"path":82,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Freviewer-prompt.md",2756,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Finterrogate\u002Freferences\u002Freviewer-prompt.md",{"path":86,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Frubric.md",5096,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Finterrogate\u002Freferences\u002Frubric.md",[90,112,140,157,178,200],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":106,"publishedAt":39},"01M71JT4RYCAS18RF6003YYR1D","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FSKILL.md",[96,101],{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":102,"categoryName":103,"taxonomyType":104,"taxonomyTypeDesc":105},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[107,108,109,110,31,111,20],"writing for agents","for","writing","editing","documents",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":121,"publishedAt":39},"01M71JT0GES4AZ5ADH8EADNN1Z","wrangler","Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwrangler\u002FSKILL.md",[118],{"categoryNo":119,"categoryName":120,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000010","后端与接口",[114,122,123,124,125,126,127,128,129,130,131,132,133,108,134,135,136,137,138,139],"cloudflare","d1","knowledge","workflows","cli","secrets","commands","syntax","cloudflare workers","r2","queues","running","containers","correct","load","workers","best practices","store",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":39},"01M71JSWX4R203M32K9A18AAW8","workers-best-practices","Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fworkers-best-practices\u002FSKILL.md",[],[147,137,138,148,149,150,108,122,151,124,152,114,109,136,20,29,153,154,155,156],"workers best practices","observability","reviews","promises","worker","new","common","streaming","state","anti-patterns",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":39},"01M71JST6P88MXGT2MWDTPJGEG","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwizard\u002FSKILL.md",[],[159,133,164,108,165,166,167,168,31,169,20,170,171,172,173,174,175,176,177,127],"setting","up","ci","provisioning infrastructure","only","invoke","Bash","one","interactive","can","credentials","dashboard","generate","human",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":182,"sourceHtmlUrl":183,"categories":184,"keywords":185,"publishedAt":39},"01M71JSQ95S7BQ61DAPN95X2W4","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available evidence sources, searches each relevant category, and returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwhy\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwhy\u002FSKILL.md",[],[180,186,187,188,189,108,190,191,31,192,193,194,195,196,197,198,199],"sources","thresholds","evidence","relevant","runtime","design","decisions","work","how","behavior","read","data","rationale","returns",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":209,"publishedAt":39},"01M71JSMHFVSH8HK8GXN6YAX6J","week-prep","Generate a briefing with calendar, tasks, and attention flags. Use for \"week prep\", \"briefing\", or \"what's on this week\".","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fweek-prep\u002FSKILL.md",[206],{"categoryNo":207,"categoryName":208,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000023","Skill与智能体开发",[210,211,212,213,214,108,215,216,217,218,31,170,219,220,221,176,222,196,223,224],"week prep","prep","deep","attention","get","search","messages","briefing","MCP","tasks","with","slack","calendar","flags","grep"]