[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72T8BRP4DMG7RF0YZPWXDQ3":3,"skill-same:01M72T8BRP4DMG7RF0YZPWXDQ3":45},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":27,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M72T8BRP4DMG7RF0YZPWXDQ3","worldexams-question-reviewer",null,"Review and validate WorldExams question bundles. Detects errors, scores quality, and applies regeneration policy. Report-only; never edits or commits bundles or generator prompts.","iberi22\u002Fskills","iberi22","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10615454?v=4","01M72SQ2NXAA3GW0FSH053A5ES","Brahyan Belalcazar","01M72SQ2PYCH0SSA1K61NGEHDV",0,"MIT","https:\u002F\u002Fgithub.com\u002Fiberi22\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fgeneral\u002Fworldexams-question-reviewer\u002FSKILL.md",[],[],"2026-11-10 22:39:42",false,"---\nname: worldexams-question-reviewer\ndescription: Review and validate WorldExams question bundles. Detects errors, scores quality, and applies regeneration policy. Report-only; never edits or commits bundles or generator prompts.\n---\n\n# WorldExams Question Reviewer\n\nAutomatic bundle review. Each batch runs as a sub-agent that applies the full validation protocol.\n\nThe reviewer only reports. It never edits generator prompts or bundles, and it never commits. The author of a bundle and its reviewer must be different parties.\n\n## Trigger\n\nThis skill runs when:\n- The cron job `worldexams-bundle-review` starts a review sub-agent.\n- Someone asks manually: `Review bundle [ID]`.\n- A bulk audit is requested: `Review all bundles for [country]`.\n\n## Review workflow\n\n### PHASE 1: Bundle discovery\n\n1. Identify the bundle path.\n2. Read the frontmatter for metadata:\n   - `id`, `country`, `grade`, `subject`, `topic`, `period`\n   - `bundle_size`, `protocol_version`\n\n### PHASE 2: Structural validation\n\nRun the checks in order:\n\n1. **Valid frontmatter**\n   - All required fields present.\n   - ID format: `CO-[AREA]-[GRADE]-P[N]-[TOPIC]-[###]-MASTERY`.\n   - `bundle_size` matches the number of questions in the file.\n\n2. **Question structure**\n   - Each question has: ID, Bloom level, ICFES tag, Expected_Success, stem, 4 options, 1 correct answer, feedback, explanation.\n   - Consistent format across questions.\n\n3. **Unique IDs**\n   - No duplicate IDs.\n   - No repeated question IDs within the same bundle.\n\n### PHASE 3: Content validation (per question)\n\nApply this checklist to each question:\n\n```\nPER-QUESTION CHECKLIST:\n□ Is the stem clear and unambiguous?\n□ Is the context useful (not decorative)?\n□ Are the 4 options homogeneous in category and register?\n□ Is there exactly one correct answer?\n□ Are the distractors plausible (they represent real errors)?\n□ No \"all of the above\" \u002F \"none of the above\"?\n□ No grammatical clues (the correct option stands out by form)?\n□ Is the explanation pedagogically correct?\n□ Is there useful feedback per option?\n□ Is the language appropriate for the grade?\n□ Free of word salad?\n□ Free of pseudo-technical jargon?\n□ Free of grandiose jargon with no function?\n□ Free of words repeated artificially?\n□ Free of unnecessary morbid or sensationalist context?\n```\n\n### PHASE 4: Psychometric validation\n\n1. **Progressive difficulty**: early questions are easier (recognition), later ones harder (evaluation\u002Ftransfer).\n2. **Discrimination**: distractors represent different, plausible errors.\n3. **Expected success rate**: compare `expected_success_rate` in the frontmatter with each question's `Expected_Success` field.\n\n### PHASE 5: Decision\n\n| Condition | Decision |\n|-----------|----------|\n| 0 errors | ✅ `ACEPTAR`: bundle ready for production |\n| 1 error | ⚠️ `CORREGIR_PUNTUAL`: regenerate that specific question |\n| 2+ errors | 🔴 `REGENERAR_BUNDLE`: regenerate the whole bundle |\n| Systematic errors (critical pattern) | 🔴 `REGENERAR_BUNDLE` + flag `CONTAMINATION` |\n\n## Regeneration rules\n\n**Regenerate the whole bundle if:**\n- 2+ questions carry `[CRITICAL FAILURE]`.\n- 2+ questions have an ambiguous or non-unique key.\n- A systematic pattern of absurd distractors appears.\n- Broad curricular misalignment.\n- Inconsistent bundle structure.\n\n**Fix a single question if:**\n- 1 question has a local error (stem, option, or feedback).\n- Frontmatter format error.\n- Duplicate ID.\n\nThe reviewer recommends these actions. The generator performs them.\n\n## Review record\n\nEach review produces one record, returned in the report. Nothing is stored by this skill.\n\n```json\n{\n  \"bundle_id\": \"CO-MAT-11-ALGEBRA-001-MASTERY\",\n  \"revision_id\": \"rev_20260402_001\",\n  \"timestamp\": \"2026-04-02T18:00:00Z\",\n  \"reviewer\": \"agent\",\n  \"total_questions\": 20,\n  \"errors_found\": 0,\n  \"warnings\": 0,\n  \"decision\": \"ACEPTAR\",\n  \"questions_reviewed\": [\n    {\n      \"question_id\": \"CO-MAT-11-ALGEBRA-001-v1\",\n      \"status\": \"ok\",\n      \"errors\": []\n    }\n  ],\n  \"flags\": [],\n  \"next_review\": \"2026-04-09\"\n}\n```\n\n## Validation commands\n\n```bash\n# Structure validation\nnode saberparatodos\u002Fscripts\u002Fvalidate_content.js --scope=colombia --grade=11\n\n# Quality audit\nnode saberparatodos\u002Fscripts\u002Faudit_question_quality.js --scope=colombia --grade-min=3 --grade-max=11\n\n# Review a specific bundle\nnode scripts\u002Freview-bundle.js --bundle=CO-MAT-11-ALGEBRA-001-MASTERY\n```\n\n## Sub-agent output format\n\n```\n📋 BUNDLE REVIEW: [ID]\nCountry: [CO\u002FMX\u002FAR\u002FCL\u002FPE\u002FBR]\nGrade: [N]\nSubject: [name]\nTopic: [topic]\nBundle size: [N] questions\n\n═══════════════════════════════════════\nRESULT: [✅ ACEPTAR \u002F ⚠️ CORREGIR_PUNTUAL \u002F 🔴 REGENERATE]\n═══════════════════════════════════════\n\nSUMMARY:\n- Questions reviewed: [N]\n- Errors found: [N]\n- Warnings: [N]\n- Review time: [X] min\n\nQUESTIONS WITH ERRORS:\n1. [ID] - [error_type] - [description]\n2. [ID] - [error_type] - [description]\n\nREQUIRED ACTIONS (for the generator or owner):\n- [list of actions]\n```\n\n## Flag system\n\n| Flag | Meaning | Recommended action |\n|------|---------|--------------------|\n| `CONTAMINATION` | Bundle contains copied or invalid content | Regenerate and purge cache |\n| `LOW_QUALITY` | Bundle with qualityScore \u003C 40 | Regenerate and mark |\n| `OUTDATED` | Not reviewed in > 30 days | Include in the next batch |\n| `PREMIUM_READY` | Passed validation and ready for sale | Eligible for premium publication (owner decision) |\n\n## Batch configuration\n\n- **Batch size**: 10 bundles per run.\n- **Frequency**: every 6 hours (cron job).\n- **Priority**: bundles without a recent review (> 7 days).\n- **Country per batch**: rotating (CO → MX → AR → CL → PE → BR).\n\n## Behavior rules\n\n- Do not modify the bundle during review.\n- Do not edit generator prompts, bundles, or repository files. Do not commit.\n- Only report errors and decisions.\n- If something is ambiguous, mark `CORREGIR_PUNTUAL` and explain why.\n- For regeneration, the report carries the full brief; the generator sub-agent acts on it.\n","# WorldExams Question Reviewer\n\nAutomatic bundle review. Each batch runs as a sub-agent that applies the full validation protocol.\n\nThe reviewer only reports. It never edits generator prompts or bundles, and it never commits. The author of a bundle and its reviewer must be different parties.\n\n## Trigger\n\nThis skill runs when:\n- The cron job `worldexams-bundle-review` starts a review sub-agent.\n- Someone asks manually: `Review bundle [ID]`.\n- A bulk audit is requested: `Review all bundles for [country]`.\n\n## Review workflow\n\n### PHASE 1: Bundle discovery\n\n1. Identify the bundle path.\n2. Read the frontmatter for metadata:\n   - `id`, `country`, `grade`, `subject`, `topic`, `period`\n   - `bundle_size`, `protocol_version`\n\n### PHASE 2: Structural validation\n\nRun the checks in order:\n\n1. **Valid frontmatter**\n   - All required fields present.\n   - ID format: `CO-[AREA]-[GRADE]-P[N]-[TOPIC]-[###]-MASTERY`.\n   - `bundle_size` matches the number of questions in the file.\n\n2. **Question structure**\n   - Each question has: ID, Bloom level, ICFES tag, Expected_Success, stem, 4 options, 1 correct answer, feedback, explanation.\n   - Consistent format across questions.\n\n3. **Unique IDs**\n   - No duplicate IDs.\n   - No repeated question IDs within the same bundle.\n\n### PHASE 3: Content validation (per question)\n\nApply this checklist to each question:\n\n```\nPER-QUESTION CHECKLIST:\n□ Is the stem clear and unambiguous?\n□ Is the context useful (not decorative)?\n□ Are the 4 options homogeneous in category and register?\n□ Is there exactly one correct answer?\n□ Are the distractors plausible (they represent real errors)?\n□ No \"all of the above\" \u002F \"none of the above\"?\n□ No grammatical clues (the correct option stands out by form)?\n□ Is the explanation pedagogically correct?\n□ Is there useful feedback per option?\n□ Is the language appropriate for the grade?\n□ Free of word salad?\n□ Free of pseudo-technical jargon?\n□ Free of grandiose jargon with no function?\n□ Free of words repeated artificially?\n□ Free of unnecessary morbid or sensationalist context?\n```\n\n### PHASE 4: Psychometric validation\n\n1. **Progressive difficulty**: early questions are easier (recognition), later ones harder (evaluation\u002Ftransfer).\n2. **Discrimination**: distractors represent different, plausible errors.\n3. **Expected success rate**: compare `expected_success_rate` in the frontmatter with each question's `Expected_Success` field.\n\n### PHASE 5: Decision\n\n| Condition | Decision |\n|-----------|----------|\n| 0 errors | ✅ `ACEPTAR`: bundle ready for production |\n| 1 error | ⚠️ `CORREGIR_PUNTUAL`: regenerate that specific question |\n| 2+ errors | 🔴 `REGENERAR_BUNDLE`: regenerate the whole bundle |\n| Systematic errors (critical pattern) | 🔴 `REGENERAR_BUNDLE` + flag `CONTAMINATION` |\n\n## Regeneration rules\n\n**Regenerate the whole bundle if:**\n- 2+ questions carry `[CRITICAL FAILURE]`.\n- 2+ questions have an ambiguous or non-unique key.\n- A systematic pattern of absurd distractors appears.\n- Broad curricular misalignment.\n- Inconsistent bundle structure.\n\n**Fix a single question if:**\n- 1 question has a local error (stem, option, or feedback).\n- Frontmatter format error.\n- Duplicate ID.\n\nThe reviewer recommends these actions. The generator performs them.\n\n## Review record\n\nEach review produces one record, returned in the report. Nothing is stored by this skill.\n\n```json\n{\n  \"bundle_id\": \"CO-MAT-11-ALGEBRA-001-MASTERY\",\n  \"revision_id\": \"rev_20260402_001\",\n  \"timestamp\": \"2026-04-02T18:00:00Z\",\n  \"reviewer\": \"agent\",\n  \"total_questions\": 20,\n  \"errors_found\": 0,\n  \"warnings\": 0,\n  \"decision\": \"ACEPTAR\",\n  \"questions_reviewed\": [\n    {\n      \"question_id\": \"CO-MAT-11-ALGEBRA-001-v1\",\n      \"status\": \"ok\",\n      \"errors\": []\n    }\n  ],\n  \"flags\": [],\n  \"next_review\": \"2026-04-09\"\n}\n```\n\n## Validation commands\n\n```bash\n# Structure validation\nnode saberparatodos\u002Fscripts\u002Fvalidate_content.js --scope=colombia --grade=11\n\n# Quality audit\nnode saberparatodos\u002Fscripts\u002Faudit_question_quality.js --scope=colombia --grade-min=3 --grade-max=11\n\n# Review a specific bundle\nnode scripts\u002Freview-bundle.js --bundle=CO-MAT-11-ALGEBRA-001-MASTERY\n```\n\n## Sub-agent output format\n\n```\n📋 BUNDLE REVIEW: [ID]\nCountry: [CO\u002FMX\u002FAR\u002FCL\u002FPE\u002FBR]\nGrade: [N]\nSubject: [name]\nTopic: [topic]\nBundle size: [N] questions\n\n═══════════════════════════════════════\nRESULT: [✅ ACEPTAR \u002F ⚠️ CORREGIR_PUNTUAL \u002F 🔴 REGENERATE]\n═══════════════════════════════════════\n\nSUMMARY:\n- Questions reviewed: [N]\n- Errors found: [N]\n- Warnings: [N]\n- Review time: [X] min\n\nQUESTIONS WITH ERRORS:\n1. [ID] - [error_type] - [description]\n2. [ID] - [error_type] - [description]\n\nREQUIRED ACTIONS (for the generator or owner):\n- [list of actions]\n```\n\n## Flag system\n\n| Flag | Meaning | Recommended action |\n|------|---------|--------------------|\n| `CONTAMINATION` | Bundle contains copied or invalid content | Regenerate and purge cache |\n| `LOW_QUALITY` | Bundle with qualityScore \u003C 40 | Regenerate and mark |\n| `OUTDATED` | Not reviewed in > 30 days | Include in the next batch |\n| `PREMIUM_READY` | Passed validation and ready for sale | Eligible for premium publication (owner decision) |\n\n## Batch configuration\n\n- **Batch size**: 10 bundles per run.\n- **Frequency**: every 6 hours (cron job).\n- **Priority**: bundles without a recent review (> 7 days).\n- **Country per batch**: rotating (CO → MX → AR → CL → PE → BR).\n\n## Behavior rules\n\n- Do not modify the bundle during review.\n- Do not edit generator prompts, bundles, or repository files. Do not commit.\n- Only report errors and decisions.\n- If something is ambiguous, mark `CORREGIR_PUNTUAL` and explain why.\n- For regeneration, the report carries the full brief; the generator sub-agent acts on it.\n",{"name":5,"description":7},"main","688810f2886d212632acf81e532b24e483dd8b98","skills\u002Fgeneral\u002Fworldexams-question-reviewer","https:\u002F\u002Fgithub.com\u002Fiberi22\u002Fskills","https:\u002F\u002Fgithub.com\u002Fiberi22","Senior WEB Full-Stack","2026-10-12 02:46:21",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add iberi22\u002Fskills --skill worldexams-question-reviewer",{"tool":37,"command":38},"bunx","bunx skills add iberi22\u002Fskills --skill worldexams-question-reviewer",{"tool":40,"command":41},"pnpm","pnpm dlx skills add iberi22\u002Fskills --skill worldexams-question-reviewer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fiberi22\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fgeneral\u002Fworldexams-question-reviewer\u002FSKILL.md",true,[],[46,52,59,65,71,77],{"skillNo":47,"name":48,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":19},"01M72TWQEQD46ZC9TRBAABF78P","web-design-guidelines","https:\u002F\u002Fgithub.com\u002Fiberi22\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fweb\u002Fweb-design-guidelines\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M72TWMQFTYD08DGXVAXRPPEB","blocked-page-recovery","Use when a fetch fails: 403\u002F429, paywall, WAF, bot wall. Recovers the page via archives and provenance-checked fallbacks.","https:\u002F\u002Fgithub.com\u002Fiberi22\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fweb\u002Fblocked-page-recovery\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M72TVQMS3HCTX18C8T97WTQQ","studio-coach","https:\u002F\u002Fgithub.com\u002Fiberi22\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftools\u002Fstudio-coach\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M72TVNA2PR9RZW0ZAXYP1G6J","src-generator","https:\u002F\u002Fgithub.com\u002Fiberi22\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftools\u002Fsrc-generator\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M72TVEJHHB6SAT3R3TY9MJKS","sqlite-pro","https:\u002F\u002Fgithub.com\u002Fiberi22\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftools\u002Fsqlite-pro\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M72TVC2EVBHQHCX96VTTYKB8","rigor-evaluator","Use when you need a quick heuristic rigor score (10 criteria, 0-2 each) for the features in a .gitcore\u002Ffeatures.json file, to decide which features are ready to ship.","https:\u002F\u002Fgithub.com\u002Fiberi22\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftools\u002Frigor-evaluator\u002FSKILL.md",[],[]]