[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73F3HSPKQWVK6BAWK11RAEB":3,"skill-same:01M73F3HSPKQWVK6BAWK11RAEB":63},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"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":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M73F3HSPKQWVK6BAWK11RAEB","exam-bank-operations",null,"Question bank quality and exam operations workflow for assessment deliverables: authoring with answer-length bias checks, remediation ledger review, exam window preparation and statistics monitoring. Use when: adding\u002Freviewing bank items, running the bias remediation workflow, preparing an exam for a cohort, or analyzing exam statistics.","5throck\u002Fai-workspace-standards","5throck","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10958964?v=4","01M73BFEH0V0VS483TW4JD49JW","01M73BFEJ5VQZJHJSFTVPAZGDM",25,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-learning\u002F.agents\u002Fskills\u002Fexam-bank-operations\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: exam-bank-operations\nstatus: active\nscope: co-learning\ndescription: >\n  Question bank quality and exam operations workflow for assessment deliverables: authoring\n  with answer-length bias checks, remediation ledger review, exam window preparation and\n  statistics monitoring. Use when: adding\u002Freviewing bank items, running the bias\n  remediation workflow, preparing an exam for a cohort, or analyzing exam statistics.\nowner: exam-bank-steward\nversion: \"1.1.0\"\nlast_reviewed: \"2026-10-06\"\nprerequisites: Assessment deliverable in deliverables\u002F with its bias tooling (bias.js) and the admin question-edit surface; remediation drafts + ledger fixtures under tests\u002F\nrelates_to:\n  - skill: documentation-writing\n    type: composes_with\nmetadata:\n  type: process\n  triggers:\n    - question bank\n    - exam operations\n    - bias review\n    - item authoring\n---\n\n# Exam Bank Operations\n\nQuestion-bank quality workflow and exam operations for the assessment\ndeliverable, owned by the `exam-bank-steward` agent and dispatched via PM.\n\n## Context\n\nThe question bank is a quality-controlled content asset: answer-length bias in\ndistractors leaks the correct answer, so authoring and rewriting both run\nthrough a measurable bias gate, and every AI-drafted rewrite passes a named\nhuman reviewer before it is applied. Once a real exam attempt is recorded,\npublished items freeze without a formal comparability review.\n\n## When to Use\n\n- Adding or reviewing bank items (authoring quality, bias gate).\n- Running the distractor remediation workflow (drafts → review → ledger).\n- Preparing an exam for a cohort (windows, activation, review mode).\n- Interpreting exam statistics or producing the periodic bank health report.\n\n## Execution Steps\n\n### 1. Authoring a new item\n\n1. Draft: stem, 5 options, exactly one definitively correct answer, explanation,\n   dimension (`tech|control|evals|ops|collab`), difficulty (`1|2|3`).\n2. Bias check (mandatory):\n   ```\n   node -e \"import('.\u002Fdeliverables\u002Fharness-assessment\u002Fbias.js').then(m=>console.log(m.lengthBias({options:[...],correct:N})))\"\n   ```\n   - `hard: true` → rewrite before entry (correct is >1.2× the longest distractor).\n   - Aim for all five options within ~1.2× word count of each other.\n3. Verify the distractors are **definitively false** (no two-correct answers) and\n   register-matched with the stem.\n4. Balance the correct position across the bank (seed auto-balances; manual items\n   should avoid stacking one slot).\n5. Add via the admin question-edit form (status `active` or `draft`).\n\n### 2. Bias remediation workflow\n\nArtifacts:\n- `tests\u002Fbias-remediation-drafts.json` — AI drafts (distractors only)\n- `tests\u002Fbias-remediation-ledger.json` — review\u002Fapproval ledger\n- `tests\u002Fbias-golden.json` — golden baseline of the flagged set\n- `tests\u002Fbias-metric-test.mjs` — metric unit tests + snapshot check\n\nLoop per batch (target: worst-ratio items first):\n1. Generate\u002Frefresh drafts into the drafts file.\n2. For each item, the **named reviewer** checks every proposed distractor:\n   definitively FALSE (no ambiguity), register-matched, length within ~1.2× of correct.\n3. Apply via the admin question-edit form; then record in the ledger:\n   reviewer name, date, `verifiedFalse: true`, `registerMatch: true`, `appliedAt`.\n4. Re-run `node tests\u002Fbias-metric-test.mjs` and\n   `node deliverables\u002Fharness-assessment\u002Fscripts\u002Fvalidate.js` — the hard-flag share\n   must drop (target ≤30% longest-correct); regenerate `bias-golden.json`\n   deliberately after the batch.\n5. **Freeze rule**: once the first real (non-mock) exam attempt exists, no further\n   rewrites of published items without a formal comparability review.\n\n### 3. Exam operations checklist (per cohort)\n\n1. Confirm the cohort exists (admin → Training tab) and participants are assigned.\n2. Create the exam (admin → Exams tab): question count, time limit, attempt limit\n   (multi-attempt ⇒ review mode auto `never`), open\u002Fclose windows with explicit\n   timezone, review mode.\n3. Activate (`draft → active`) only after the window is confirmed.\n4. After submission: read exam stats (submitted, distribution, p-value,\n   discrimination); flag items with p > 0.95 or discrimination \u003C 0 for steward review.\n5. Close the exam when the window ends.\n\n### 4. Bank health report (periodic)\n\n```\nnode tests\u002Fbias-metric-test.mjs            # metric + golden snapshot\nnode deliverables\u002Fharness-assessment\u002Fscripts\u002Fvalidate.js   # warn-only bias shares\n```\n\nReport: hard\u002Fsoft shares, longest-correct rank distribution, per-dimension counts,\nthin strata (need more items), ledger progress (reviewed\u002Fapplied counts).\n\n## Output Format\n\n- Bank items land in the deliverable's question store via the admin form; bias\n  evidence and remediation history land in the fixtures under `tests\u002F`\n  (drafts, ledger, golden baseline).\n- Exam operations leave an admin-side exam record plus a steward note in the\n  session memory log (`memory\u002FYYYY-MM-DD.md`) with the statistics interpretation.\n\n## Related Skills\n\n- `documentation-writing` — composes with this skill when bank\u002Freport content is\n  written for a client-facing audience.\n","# Exam Bank Operations\n\nQuestion-bank quality workflow and exam operations for the assessment\ndeliverable, owned by the `exam-bank-steward` agent and dispatched via PM.\n\n## Context\n\nThe question bank is a quality-controlled content asset: answer-length bias in\ndistractors leaks the correct answer, so authoring and rewriting both run\nthrough a measurable bias gate, and every AI-drafted rewrite passes a named\nhuman reviewer before it is applied. Once a real exam attempt is recorded,\npublished items freeze without a formal comparability review.\n\n## When to Use\n\n- Adding or reviewing bank items (authoring quality, bias gate).\n- Running the distractor remediation workflow (drafts → review → ledger).\n- Preparing an exam for a cohort (windows, activation, review mode).\n- Interpreting exam statistics or producing the periodic bank health report.\n\n## Execution Steps\n\n### 1. Authoring a new item\n\n1. Draft: stem, 5 options, exactly one definitively correct answer, explanation,\n   dimension (`tech|control|evals|ops|collab`), difficulty (`1|2|3`).\n2. Bias check (mandatory):\n   ```\n   node -e \"import('.\u002Fdeliverables\u002Fharness-assessment\u002Fbias.js').then(m=>console.log(m.lengthBias({options:[...],correct:N})))\"\n   ```\n   - `hard: true` → rewrite before entry (correct is >1.2× the longest distractor).\n   - Aim for all five options within ~1.2× word count of each other.\n3. Verify the distractors are **definitively false** (no two-correct answers) and\n   register-matched with the stem.\n4. Balance the correct position across the bank (seed auto-balances; manual items\n   should avoid stacking one slot).\n5. Add via the admin question-edit form (status `active` or `draft`).\n\n### 2. Bias remediation workflow\n\nArtifacts:\n- `tests\u002Fbias-remediation-drafts.json` — AI drafts (distractors only)\n- `tests\u002Fbias-remediation-ledger.json` — review\u002Fapproval ledger\n- `tests\u002Fbias-golden.json` — golden baseline of the flagged set\n- `tests\u002Fbias-metric-test.mjs` — metric unit tests + snapshot check\n\nLoop per batch (target: worst-ratio items first):\n1. Generate\u002Frefresh drafts into the drafts file.\n2. For each item, the **named reviewer** checks every proposed distractor:\n   definitively FALSE (no ambiguity), register-matched, length within ~1.2× of correct.\n3. Apply via the admin question-edit form; then record in the ledger:\n   reviewer name, date, `verifiedFalse: true`, `registerMatch: true`, `appliedAt`.\n4. Re-run `node tests\u002Fbias-metric-test.mjs` and\n   `node deliverables\u002Fharness-assessment\u002Fscripts\u002Fvalidate.js` — the hard-flag share\n   must drop (target ≤30% longest-correct); regenerate `bias-golden.json`\n   deliberately after the batch.\n5. **Freeze rule**: once the first real (non-mock) exam attempt exists, no further\n   rewrites of published items without a formal comparability review.\n\n### 3. Exam operations checklist (per cohort)\n\n1. Confirm the cohort exists (admin → Training tab) and participants are assigned.\n2. Create the exam (admin → Exams tab): question count, time limit, attempt limit\n   (multi-attempt ⇒ review mode auto `never`), open\u002Fclose windows with explicit\n   timezone, review mode.\n3. Activate (`draft → active`) only after the window is confirmed.\n4. After submission: read exam stats (submitted, distribution, p-value,\n   discrimination); flag items with p > 0.95 or discrimination \u003C 0 for steward review.\n5. Close the exam when the window ends.\n\n### 4. Bank health report (periodic)\n\n```\nnode tests\u002Fbias-metric-test.mjs            # metric + golden snapshot\nnode deliverables\u002Fharness-assessment\u002Fscripts\u002Fvalidate.js   # warn-only bias shares\n```\n\nReport: hard\u002Fsoft shares, longest-correct rank distribution, per-dimension counts,\nthin strata (need more items), ledger progress (reviewed\u002Fapplied counts).\n\n## Output Format\n\n- Bank items land in the deliverable's question store via the admin form; bias\n  evidence and remediation history land in the fixtures under `tests\u002F`\n  (drafts, ledger, golden baseline).\n- Exam operations leave an admin-side exam record plus a steward note in the\n  session memory log (`memory\u002FYYYY-MM-DD.md`) with the statistics interpretation.\n\n## Related Skills\n\n- `documentation-writing` — composes with this skill when bank\u002Freport content is\n  written for a client-facing audience.\n",{"name":5,"owner":23,"scope":24,"status":25,"version":26,"metadata":27,"relates_to":34,"description":38,"last_reviewed":39,"prerequisites":40},"exam-bank-steward","co-learning","active","1.1.0",{"type":28,"triggers":29},"process",[30,31,32,33],"question bank","exam operations","bias review","item authoring",[35],{"type":36,"skill":37},"composes_with","documentation-writing","Question bank quality and exam operations workflow for assessment deliverables: authoring with answer-length bias checks, remediation ledger review, exam window preparation and statistics monitoring. Use when: adding\u002Freviewing bank items, running the bias remediation workflow, preparing an exam for a cohort, or analyzing exam statistics.\n","2026-10-06","Assessment deliverable in deliverables\u002F with its bias tooling (bias.js) and the admin question-edit surface; remediation drafts + ledger fixtures under tests\u002F","main","1162ccc568cf90c01b3886d6143cbfd851a37883","templates\u002Fco-learning\u002F.agents\u002Fskills\u002Fexam-bank-operations",9,"https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards","https:\u002F\u002Fgithub.com\u002F5throck","Experienced in digital transformation, enterprise IT, startup acceleration, and business strategy. Focused on building practical systems that connect technolo","2026-11-14 21:22:34",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add 5throck\u002Fai-workspace-standards --skill exam-bank-operations",{"tool":55,"command":56},"bunx","bunx skills add 5throck\u002Fai-workspace-standards --skill exam-bank-operations",{"tool":58,"command":59},"pnpm","pnpm dlx skills add 5throck\u002Fai-workspace-standards --skill exam-bank-operations","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-learning\u002F.agents\u002Fskills\u002Fexam-bank-operations\u002FSKILL.md",true,[],[64,72,77,82,87,92],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":71},"01M7BBJDYHJMGTJYSC37JVWY8S","i18n-layout","Text layout and encoding guidance: character encoding (UTF-8, legacy Korean code pages, BOM hazards), line endings, RTL\u002Fbidi handling, and script-specific font selection (Hangul focus). Use when: encoding is corrupted or mojibake appears, an RTL locale must render correctly, fonts must be chosen for a script, or CRLF\u002FBOM issues surface.","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":73,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":71},"01M7BBJ9XHAAS1AVGKZZ841VBZ","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.hermes\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":78,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":71},"01M7BBJ5C3X8TKFKG5R9P9P49W","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.gemini\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":83,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":71},"01M7BBJ1B52X0QMJ2QVBMPJB37","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.codex\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":88,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":71},"01M7BBHX91BW2Q2R276MRX5AW3","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.claude\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[],{"skillNo":93,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":71},"01M7BBHQWGXPSFRWN1PRC2NMMV","https:\u002F\u002Fgithub.com\u002F5throck\u002Fai-workspace-standards\u002Fblob\u002Fmain\u002Ftemplates\u002Fco-work\u002F.agents\u002Fskills\u002Fi18n-layout\u002FSKILL.md",[],[]]