[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FWV0540MT7E5XA4QJHNN4K":3,"skill-same:01M6FWV0540MT7E5XA4QJHNN4K":75},{"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":23,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6FWV0540MT7E5XA4QJHNN4K","quiz-me",null,"Adversarial one-question-at-a-time questioning to verify deep reading comprehension of alignment pages, specs, or any document","GeorgeQLe\u002Fagentic-skills","GeorgeQLe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F21134126?v=4","01M6D2JP418S0VGJGF8M93EC3H","George Le","01M6D2JPBAKYD82TA5FS6HKQ3D",1,"MIT","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fknowledge-check\u002Fclaude\u002Fquiz-me\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000039","教师与教育","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37],"me","quiz","quiz me","review","file","verify","question","v0","alignment","document","time","deep","pages","reading","2026-11-10 10:12:30",false,"---\nname: quiz-me\ndescription: Adversarial one-question-at-a-time questioning to verify deep reading comprehension of alignment pages, specs, or any document\ntype: review\nversion: v0.0\nargument-hint: \"[file-path-or-glob]\"\n---\n\n# Quiz Me\n\nAdversarial comprehension testing. Reads a document silently, then grills the user one question at a time to verify they actually read it — not skimmed it, not got the gist, actually read it. Delivers a pass\u002Ffail verdict when done.\n\nThis is not teaching. This is not alignment-building. This is a test. The user claims they read something; this skill finds out if that's true.\n\n## Process\n\n### Phase 1: Silent Document Ingestion\n\n1. **Resolve input files.**\n   - If `$ARGUMENTS` contains a file path or glob, read those files.\n   - If `$ARGUMENTS` is empty, find all alignment HTML files (`docs\u002F**\u002F*.html`) and spec documents (`specs\u002F**\u002F*.md`) in the current repo. If multiple files are found, ask the user which document(s) to quiz on.\n   - Supported formats: HTML, Markdown, plain text.\n   - If no readable document is found, stop and tell the user.\n\n2. **Analyze document structure internally.**\n   - Identify major sections, key decisions, trade-offs, cross-section relationships, specific constraints\u002Fnumbers\u002Fnames, and non-obvious details.\n   - Build an internal question plan that covers every major section, biased toward:\n     - Cross-section relationships (\"How does X in section 3 affect Y in section 7?\")\n     - Implications and trade-offs (\"What happens if the migration in step 2 fails?\")\n     - Specific details that skimmers miss (exact constraints, numbers, edge cases)\n     - Intent questions (\"Why was approach A chosen over approach B?\")\n     - Synthesis questions (\"Summarize the three most important trade-offs.\")\n   - Do NOT surface any of this analysis to the user.\n\n3. **Open the quiz.** Tell the user which document(s) they're being quizzed on and that you'll ask one question at a time. Nothing else — no summary, no encouragement, no preview of what's coming.\n\n### Phase 2: Adversarial Questioning\n\nAsk **one question per turn**. Non-negotiable.\n\nUse `AskUserQuestion` for every question. Provide 2-3 plausible multiple-choice options plus the implicit \"Other\" free-text option. At least one option should be a trap — superficially plausible but wrong if the user actually read the document. Vary whether the correct answer is a named option or requires free-text via \"Other\".\n\n**Question types** (mix throughout, do not cluster by type):\n\n- **Relationship:** \"Section X describes [thing]. How does that interact with [thing from section Y]?\"\n- **Implication:** \"If [condition from the doc] changes, what breaks?\"\n- **Detail trap:** \"What specific [constraint\u002Fnumber\u002Fname] does the doc specify for [thing]?\"\n- **Intent:** \"Why does the doc recommend [approach] instead of [alternative]?\"\n- **Synthesis:** \"What are the most important trade-offs the document makes?\"\n\n**After each answer, evaluate strictly:**\n\n- **Correct and specific:** Acknowledge in one sentence. Move to next question.\n- **Vague or incomplete:** Push back. \"That's too vague. What specifically does the doc say about [X]?\" Do not accept hand-wavy answers. Re-ask or ask a targeted follow-up.\n- **Wrong:** State what's wrong. Give the user one chance to correct. If they fail again, note the gap and move on.\n- **Suspiciously perfect verbatim recall:** Ask a follow-up that requires synthesis, not recitation. If they can synthesize, accept it. If they can only parrot, mark the section as weak.\n\nTrack per-section comprehension internally. Do not show the user a running score.\n\n### Phase 3: Termination\n\nContinue until one of:\n\n- The user has demonstrated understanding across **all major sections** — no section left untested.\n- The user explicitly gives up or asks to stop.\n\nDo NOT terminate early because the user got a few questions right. Cover the full document. Minimum 5 questions for short documents, more for longer ones.\n\n### Phase 4: Verdict\n\nWhen the quiz ends, deliver:\n\n1. **Pass or Fail.** Binary. Pass means the user demonstrated deep comprehension across all major sections. Fail means one or more sections had weak or missing comprehension.\n\n2. **Per-section summary:**\n   - Sections with strong comprehension\n   - Sections with weak or missing comprehension\n   - Specific gaps identified\n\n3. **If fail:** List which sections to re-read and why.\n\n## Constraints\n\n- **Read-only.** Do not write, create, modify, or delete any files.\n- **No commits, no pushes, no file mutations.**\n- **No external requests.** All content is local.\n- **One question per turn.** Always.\n- **Use AskUserQuestion for every question.** Do not ask questions via plain text output.\n- **Adversarial but not hostile.** Push back firmly on bad answers. Do not insult the user. Do not congratulate excessively on correct answers.\n- **No teaching.** Do not explain document content during the quiz. If the user gets something wrong, state what's wrong — do not deliver a lesson.\n- **No hints.** Do not help the user arrive at the right answer. This is a test, not a tutorial.\n\n## Differences from taste-calibration\n\n| | quiz-me | taste-calibration |\n|---|---|---|\n| Purpose | Test comprehension of existing docs | Build alignment for new work |\n| Tone | Adversarial examiner | Socratic collaborator |\n| Input | Existing document to test against | Rough idea or problem |\n| Output | Pass\u002Ffail verdict | Shared understanding summary |\n| Recommended answers | Never | Always |\n| File output | None | None |\n\n## Default Shipping Contract\n\nRead-only — do not create or modify tracked repository files. Follow the shared shipping contract convention in CLAUDE.md for next-step routing only.\n\n","# Quiz Me\n\nAdversarial comprehension testing. Reads a document silently, then grills the user one question at a time to verify they actually read it — not skimmed it, not got the gist, actually read it. Delivers a pass\u002Ffail verdict when done.\n\nThis is not teaching. This is not alignment-building. This is a test. The user claims they read something; this skill finds out if that's true.\n\n## Process\n\n### Phase 1: Silent Document Ingestion\n\n1. **Resolve input files.**\n   - If `$ARGUMENTS` contains a file path or glob, read those files.\n   - If `$ARGUMENTS` is empty, find all alignment HTML files (`docs\u002F**\u002F*.html`) and spec documents (`specs\u002F**\u002F*.md`) in the current repo. If multiple files are found, ask the user which document(s) to quiz on.\n   - Supported formats: HTML, Markdown, plain text.\n   - If no readable document is found, stop and tell the user.\n\n2. **Analyze document structure internally.**\n   - Identify major sections, key decisions, trade-offs, cross-section relationships, specific constraints\u002Fnumbers\u002Fnames, and non-obvious details.\n   - Build an internal question plan that covers every major section, biased toward:\n     - Cross-section relationships (\"How does X in section 3 affect Y in section 7?\")\n     - Implications and trade-offs (\"What happens if the migration in step 2 fails?\")\n     - Specific details that skimmers miss (exact constraints, numbers, edge cases)\n     - Intent questions (\"Why was approach A chosen over approach B?\")\n     - Synthesis questions (\"Summarize the three most important trade-offs.\")\n   - Do NOT surface any of this analysis to the user.\n\n3. **Open the quiz.** Tell the user which document(s) they're being quizzed on and that you'll ask one question at a time. Nothing else — no summary, no encouragement, no preview of what's coming.\n\n### Phase 2: Adversarial Questioning\n\nAsk **one question per turn**. Non-negotiable.\n\nUse `AskUserQuestion` for every question. Provide 2-3 plausible multiple-choice options plus the implicit \"Other\" free-text option. At least one option should be a trap — superficially plausible but wrong if the user actually read the document. Vary whether the correct answer is a named option or requires free-text via \"Other\".\n\n**Question types** (mix throughout, do not cluster by type):\n\n- **Relationship:** \"Section X describes [thing]. How does that interact with [thing from section Y]?\"\n- **Implication:** \"If [condition from the doc] changes, what breaks?\"\n- **Detail trap:** \"What specific [constraint\u002Fnumber\u002Fname] does the doc specify for [thing]?\"\n- **Intent:** \"Why does the doc recommend [approach] instead of [alternative]?\"\n- **Synthesis:** \"What are the most important trade-offs the document makes?\"\n\n**After each answer, evaluate strictly:**\n\n- **Correct and specific:** Acknowledge in one sentence. Move to next question.\n- **Vague or incomplete:** Push back. \"That's too vague. What specifically does the doc say about [X]?\" Do not accept hand-wavy answers. Re-ask or ask a targeted follow-up.\n- **Wrong:** State what's wrong. Give the user one chance to correct. If they fail again, note the gap and move on.\n- **Suspiciously perfect verbatim recall:** Ask a follow-up that requires synthesis, not recitation. If they can synthesize, accept it. If they can only parrot, mark the section as weak.\n\nTrack per-section comprehension internally. Do not show the user a running score.\n\n### Phase 3: Termination\n\nContinue until one of:\n\n- The user has demonstrated understanding across **all major sections** — no section left untested.\n- The user explicitly gives up or asks to stop.\n\nDo NOT terminate early because the user got a few questions right. Cover the full document. Minimum 5 questions for short documents, more for longer ones.\n\n### Phase 4: Verdict\n\nWhen the quiz ends, deliver:\n\n1. **Pass or Fail.** Binary. Pass means the user demonstrated deep comprehension across all major sections. Fail means one or more sections had weak or missing comprehension.\n\n2. **Per-section summary:**\n   - Sections with strong comprehension\n   - Sections with weak or missing comprehension\n   - Specific gaps identified\n\n3. **If fail:** List which sections to re-read and why.\n\n## Constraints\n\n- **Read-only.** Do not write, create, modify, or delete any files.\n- **No commits, no pushes, no file mutations.**\n- **No external requests.** All content is local.\n- **One question per turn.** Always.\n- **Use AskUserQuestion for every question.** Do not ask questions via plain text output.\n- **Adversarial but not hostile.** Push back firmly on bad answers. Do not insult the user. Do not congratulate excessively on correct answers.\n- **No teaching.** Do not explain document content during the quiz. If the user gets something wrong, state what's wrong — do not deliver a lesson.\n- **No hints.** Do not help the user arrive at the right answer. This is a test, not a tutorial.\n\n## Differences from taste-calibration\n\n| | quiz-me | taste-calibration |\n|---|---|---|\n| Purpose | Test comprehension of existing docs | Build alignment for new work |\n| Tone | Adversarial examiner | Socratic collaborator |\n| Input | Existing document to test against | Rough idea or problem |\n| Output | Pass\u002Ffail verdict | Shared understanding summary |\n| Recommended answers | Never | Always |\n| File output | None | None |\n\n## Default Shipping Contract\n\nRead-only — do not create or modify tracked repository files. Follow the shared shipping contract convention in CLAUDE.md for next-step routing only.\n\n",{"name":5,"type":27,"version":43,"description":7,"argument-hint":44},"v0.0","[file-path-or-glob]","master","96e2912af886dd1606b1b97df707715aef062b02","packs\u002Fknowledge-check\u002Fclaude\u002Fquiz-me",0,"https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills","https:\u002F\u002Fagentic-skills-blush.vercel.app","https:\u002F\u002Fgithub.com\u002FGeorgeQLe","georgeqle.com","George Le is a futurist and serial tech entrepreneur who wants to work toward a world where humanity is free from robotic tasks.","2026-11-10 04:07:24",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add GeorgeQLe\u002Fagentic-skills --skill quiz-me",{"tool":61,"command":62},"bunx","bunx skills add GeorgeQLe\u002Fagentic-skills --skill quiz-me",{"tool":64,"command":65},"pnpm","pnpm dlx skills add GeorgeQLe\u002Fagentic-skills --skill quiz-me","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fknowledge-check\u002Fclaude\u002Fquiz-me\u002FSKILL.md",true,[69],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"CHANGELOG.md","REFERENCE","参考文档",93,"https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fknowledge-check\u002Fclaude\u002Fquiz-me\u002FCHANGELOG.md",[76,88,98,110,125,136],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":38},"01M6G0NJES15RJKZE6YZ0TSYGF","source-checkout-allowed","Valid source-checkout-only fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fsource-checkout-allowed\u002FSKILL.md",[],[83,84,85,86,31,87],"source checkout allowed","checkout","fixture","only","valid",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":38},"01M6G0NFZ3R1MNB1E3DVTM0WB7","deck-install-valid","Valid deck install fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fdeck-install\u002FSKILL.md",[],[95,96,97,87,85,31],"deck install valid","deck","install",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":38},"01M6G0ND3QZQC4MDZ9NVB97PT2","codex-pack-guard-valid","Valid Codex Pack Availability Guard fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-pack-guard\u002FSKILL.md",[],[105,106,107,87,108,109,85,31],"codex pack guard valid","pack","guard","codex","availability",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":121,"publishedAt":38},"01M6G0NA9YB3NKGZKD3S96JMNB","codex-missing-skill-valid","Valid Codex missing skill fallback fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-missing-skill-fallback\u002FSKILL.md",[116],{"categoryNo":117,"categoryName":118,"taxonomyType":119,"taxonomyTypeDesc":120},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[122,123,87,108,31,124,85],"codex missing skill valid","missing","fallback",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":132,"publishedAt":38},"01M6G0N7PC0EKFD40ZWQAXSAQ9","codex-base-skill-fallback-valid","Valid Codex base skill fallback fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-base-skill-fallback\u002FSKILL.md",[131],{"categoryNo":117,"categoryName":118,"taxonomyType":119,"taxonomyTypeDesc":120},[87,108,124,133,134,135,31,85],"base skill","codex base skill fallback valid","base",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":38},"01M6G0N4VRR2YKZQ6N3Y6S2BQA","claude-pack-guard-valid","Valid Claude Pack Availability Guard fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fclaude-pack-guard\u002FSKILL.md",[],[87,107,106,143,109,31,85],"claude pack guard valid"]