[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E90QPSSX00AP3ENC461S3W":3,"skill-same:01M7E90QPSSX00AP3ENC461S3W":64},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7E90QPSSX00AP3ENC461S3W","interrogate",null,"Adversarially review a diff for correctness, security, regressions, and missing coverage. Use for `interrogate`, multi-agent review, challenge-this, or requests to find blind spots.","raka334\u002Fpstack-for-everyone","raka334","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F73239818?v=4","01M7E8ZM2DWAJ47JFYV6A7T6WQ","Aman Kumar Sah","01M7E8ZM3BB9K0N8HPPJVXWXGV",1,"MIT","https:\u002F\u002Fgithub.com\u002Fraka334\u002Fpstack-for-everyone\u002Fblob\u002Fmain\u002Fskills\u002Finterrogate\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: interrogate\ndescription: \"Adversarially review a diff for correctness, security, regressions, and missing coverage. Use for `interrogate`, multi-agent review, challenge-this, or requests to find blind spots.\"\n---\n\n# Interrogate\n\nThe deliverable is a synthesized review verdict. Do not auto-apply changes.\n\n## Step 1. Determine scope\n\nUse the caller's files or diff. Otherwise inspect the current working diff against its base branch and gather only the context needed to review it.\n\n## Step 2. State intent\n\nDerive the intended behavior from the user's request, any PR description, and the code. State the intended behavior in one paragraph. If it is genuinely ambiguous, identify the ambiguity and its impact.\n\n## Step 3. Review independently\n\nRead `references\u002Freviewer-prompt.md`, `references\u002Frubric.md`, and `references\u002Fcode-quality-review.md`. Give the same intent, patch, context, and rubric to independent read-only agents when the host supports delegation. Ask reviewers to report only actionable findings with file and line references, trigger conditions, impact, and evidence. Use a configured comment-focused reviewer only when one is available.\n\nWhen several configured agent profiles use distinct models, use them for model diversity. Otherwise treat the results as independent passes from the same model. If delegation is unavailable, do separate review passes yourself and disclose the limitation.\n\nDo not ask reviewers to change files. Do not widen the review beyond the supplied change and its necessary context.\n\n## Step 4. Synthesize\n\nDeduplicate findings, distinguish consensus from single-reviewer findings, and inspect every cited path yourself. Categorize each finding as Act on, Consider, Noted, or Dismissed. Give a one-line evidence-based reason for the disposition.\n\n## Output\n\nReturn Intent, Reviewers, Act On, Consider, Noted, Dismissed, and Agreement Map. Each finding includes exact location, impact, trigger, and disposition. If there are no findings, say what scope you reviewed and what the review could not establish.\n","# Interrogate\n\nThe deliverable is a synthesized review verdict. Do not auto-apply changes.\n\n## Step 1. Determine scope\n\nUse the caller's files or diff. Otherwise inspect the current working diff against its base branch and gather only the context needed to review it.\n\n## Step 2. State intent\n\nDerive the intended behavior from the user's request, any PR description, and the code. State the intended behavior in one paragraph. If it is genuinely ambiguous, identify the ambiguity and its impact.\n\n## Step 3. Review independently\n\nRead `references\u002Freviewer-prompt.md`, `references\u002Frubric.md`, and `references\u002Fcode-quality-review.md`. Give the same intent, patch, context, and rubric to independent read-only agents when the host supports delegation. Ask reviewers to report only actionable findings with file and line references, trigger conditions, impact, and evidence. Use a configured comment-focused reviewer only when one is available.\n\nWhen several configured agent profiles use distinct models, use them for model diversity. Otherwise treat the results as independent passes from the same model. If delegation is unavailable, do separate review passes yourself and disclose the limitation.\n\nDo not ask reviewers to change files. Do not widen the review beyond the supplied change and its necessary context.\n\n## Step 4. Synthesize\n\nDeduplicate findings, distinguish consensus from single-reviewer findings, and inspect every cited path yourself. Categorize each finding as Act on, Consider, Noted, or Dismissed. Give a one-line evidence-based reason for the disposition.\n\n## Output\n\nReturn Intent, Reviewers, Act On, Consider, Noted, Dismissed, and Agreement Map. Each finding includes exact location, impact, trigger, and disposition. If there are no findings, say what scope you reviewed and what the review could not establish.\n",{"name":5,"description":7},"main","af6ee0013b6ed238e588ef50b26477371d5ed45d","skills\u002Finterrogate",0,"https:\u002F\u002Fgithub.com\u002Fraka334\u002Fpstack-for-everyone","https:\u002F\u002Fgithub.com\u002Fraka334","Love problems ","2026-10-06 19:34:24",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add raka334\u002Fpstack-for-everyone --skill interrogate",{"tool":38,"command":39},"bunx","bunx skills add raka334\u002Fpstack-for-everyone --skill interrogate",{"tool":41,"command":42},"pnpm","pnpm dlx skills add raka334\u002Fpstack-for-everyone --skill interrogate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fraka334\u002Fpstack-for-everyone\u002Fblob\u002Fmain\u002Fskills\u002Finterrogate\u002FSKILL.md",true,[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fcode-quality-review.md","REFERENCE","参考文档",5217,"https:\u002F\u002Fgithub.com\u002Fraka334\u002Fpstack-for-everyone\u002Fblob\u002Fmain\u002Fskills\u002Finterrogate\u002Freferences\u002Fcode-quality-review.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Flead-judgment.md",3465,"https:\u002F\u002Fgithub.com\u002Fraka334\u002Fpstack-for-everyone\u002Fblob\u002Fmain\u002Fskills\u002Finterrogate\u002Freferences\u002Flead-judgment.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Freviewer-prompt.md",2491,"https:\u002F\u002Fgithub.com\u002Fraka334\u002Fpstack-for-everyone\u002Fblob\u002Fmain\u002Fskills\u002Finterrogate\u002Freferences\u002Freviewer-prompt.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Frubric.md",5025,"https:\u002F\u002Fgithub.com\u002Fraka334\u002Fpstack-for-everyone\u002Fblob\u002Fmain\u002Fskills\u002Finterrogate\u002Freferences\u002Frubric.md",[65,72,79,86,93,100],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7E94MNW2YN56TEZ484NNS1V","why","Trace the evidence behind an architectural choice, regression, postmortem, or measured threshold. Use for why-do-we-do-this and why-did-we-pick-that questions. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Fraka334\u002Fpstack-for-everyone\u002Fblob\u002Fmain\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"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},"01M7E94JPVHR0HY1N4JVC7CREG","unslop","Cut AI tells from any writing. Must always apply.","https:\u002F\u002Fgithub.com\u002Fraka334\u002Fpstack-for-everyone\u002Fblob\u002Fmain\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7E94GX3MEN3K1P4QYJJ09VA","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002Fraka334\u002Fpstack-for-everyone\u002Fblob\u002Fmain\u002Fskills\u002Ftypescript-best-practices\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7E94CNQ8T3XXN0GWW2N1DRE","technical-writing","Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for `technical-writing` or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.","https:\u002F\u002Fgithub.com\u002Fraka334\u002Fpstack-for-everyone\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-writing\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7E948XR026AVVDB4WSE6SP1","teach","Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.","https:\u002F\u002Fgithub.com\u002Fraka334\u002Fpstack-for-everyone\u002Fblob\u002Fmain\u002Fskills\u002Fteach\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7E9458RXF4QAWW1RCH67KS3","tdd","Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.","https:\u002F\u002Fgithub.com\u002Fraka334\u002Fpstack-for-everyone\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002FSKILL.md",[],[]]