exam-audit

name	exam-audit
description	只读检查一个已生成的备考工作区是否健康并报告问题，默认不做任何修改。核对 .ingest 原材料版本、 内容单元、接管队列与派生产物完整性，以及 wiki、题库、视觉证据、计划和进度的一致性。当用户怀疑 工作区有问题、建库 readiness 被阻断、或想在开始复习前体检时使用。
license	MIT

exam-audit — workspace health check (read-only)

Purpose

Inspect a prep workspace built by exam-ingest and report health issues. This is a read-only inspector. Do NOT fix anything by default; only fix after the user explicitly grants permission. Emit a concrete issue report; never silently modify or delete files.

Activation

Activate when the user suspects the workspace is broken (missing chapters, ungradable quiz items, inconsistent progress), or when the user wants a pre-review health check before studying. Do not activate to build, teach, or grade.

Inputs

• references/wiki/ — chapter knowledge files (chN_*.md).
• references/quiz_bank.json — quiz items.
• references/teaching_examples.json — optional parallel teaching inventory; examples may remain here even when they are deliberately excluded from the gradable bank.
• references/teaching_baseline.json — append-only retention baseline for new workspaces; it must never shrink on re-ingest and must not be hand-edited.
• references/figure_page_index.json / references/image_question_index.json — regenerable three-sided visual coverage evidence (wiki / prompt / answer).
• .ingest/source_manifest.json — source-root-relative paths, source hashes, media types, and parse status.
• .ingest/base_content_units.jsonl / content_units.jsonl — deterministic extraction baseline and the compiled view after replaying validated patches.
• .ingest/base_chapter_phase_mappings.jsonl / chapter_phase_mappings.jsonl — explicit chapter-to-study-phase identity.
• .ingest/review_queue.jsonl / review_patches.jsonl — typed issue lifecycle and append-only evidence-bound patch ledger.
• .ingest/build_manifest.json / unbound_review.json — source root, page-quality accounting, input/derived hashes, and issues not yet bound to one source record.
• ingest_report.json — import counts, current-snapshot statistics, missing-answer alerts, and the legacy retention fallback.
• study_plan.md — phase plan with chapter anchors.
• study_state.json — the structured progress state (the SINGLE SOURCE OF TRUTH when present: phase_checklist, mistake_archive, confusion_log).
• study_progress.md — a GENERATED VIEW of the state (rendered phase checkpoints and recorded wrong-question IDs); stale/hand-edited when it drifts from study_state.json.

Workflow

Inspect read-only. Open and parse files; never write, rename, or delete. Check each item below and record every failure as a concrete issue (file path + what is wrong).

1. Structure. For each phase listed in study_plan.md, confirm a matching references/wiki/chN_*.md file exists. Flag orphan chapters (wiki files no phase references) and broken links (phases pointing to absent chapters).
2. Quiz bank. For each item in references/quiz_bank.json: confirm type is one of the six allowed types (choice / subjective / diagram / fill_blank / true_false / code); confirm choice items carry options; treat missing keywords on subjective items as a grading-quality warning. An item without an answer must declare answer_status: unknown; in a structured workspace it also remains a blocking review issue until an evidence-backed official answer, an explicitly labeled AI answer, or an unrecoverable terminal decision is recorded.
3. Provenance honesty. Flag any AI-generated answer presented as the teacher's standard answer (missing the ⚠️ marker). Flag any AI-supplement wiki passage that should carry 🟡 but does not.
4. Plan/progress consistency. When study_state.json exists, treat it as the source of truth: confirm study_progress.md is a faithful render of it (flag drift / stale hand-edits where the md disagrees with the state), and check the state's phase_checklist phases map to study_plan.md. When no study_state.json exists, audit study_progress.md directly. Either way, confirm each rendered phase-checkpoint line maps to a phase in study_plan.md and every wrong-question ID exists in references/quiz_bank.json. Note: the template anchor <!-- PHASE_CHECKLIST --> is replaced by scripts/ingest.py at generation time and is absent from a correct finished workspace — do NOT report its absence as a problem.
5. Teaching-example retention. Prefer references/teaching_baseline.json; validate its schema, exact per-chapter mapping, append-only policy, and require every baseline ID to have a same-chapter current snapshot in references/teaching_examples.json. Presence of the same ID in references/quiz_bank.json is diagnostic overlap only and never substitutes for that teaching snapshot. Only old workspaces without the baseline file may fall back to ingest_report.json.teaching_example_ids. It is valid for an ungradable worked example to be absent from the bank if the teaching layer retains it; disappearance from the current teaching layer is a blocking retention gap even when a quiz item survives. Validate the current teaching manifest's IDs, chapter/phase tags, source pages, answer source, and asset paths. Read it per chapter in tutoring; do not treat the whole manifest as a new answer source.

Run python <package-root>/scripts/validate_workspace.py <workspace> --json as the canonical static check and include its readiness in the report. ok=true means structurally runnable (no validation errors); it does not erase warnings or mean content-complete.

Output Contract

Emit a single issue list. Each entry contains: 【级别(阻断/警告/提示)】 (severity: blocker / warning / notice) + 【位置文件】 (file path) + 【现象】 (concrete symptom) + 【建议修法】 (suggested fix). End with exactly one readiness verdict: ready (no errors or warnings), usable_with_gaps (no errors, but warnings/incomplete evidence remain), or blocked (one or more errors). Never translate ok=true into ready without checking warnings.

Do NOT auto-fix. After reporting, fix item-by-item only if the user grants permission, or hand the workspace back to exam-ingest for rebuild.

Preserve these provenance labels VERBATIM when quoting them in findings: 🟢 来自资料 / 🟡 AI补充，可能与你老师讲的不完全一致 / ⚠️ AI生成答案，非老师/教材提供.

Student-facing output defaults to English (Simplified Chinese if the student opened in Chinese); the persisted study_state.json.language code (zh/en/bilingual) switches it per exam-cram's dispatch rule with single-language purity.

Language packs

This skill produces no student-facing template; its report is agent-composed in the student's language. There are no locales/zh/skills/exam-audit.md or locales/en/skills/exam-audit.md pack files — compose the issue report directly in the language given by study_state.json.language:

• 中文 → Simplified Chinese, using the zh canonical wording in ../../docs/language-policy.md
• English → English, using the EN canonical vocabulary in ../../docs/language-policy.md
• 双语 → compose zh-first with a > EN: mirror line per block (rules in ../../docs/language-policy.md) Display aliases such as 中文, English, and 双语 are normalized by update_progress.py; route persisted state on zh, en, or bilingual. Unset language → the merged first-ask decides it; default English unless the student opened in Chinese.

Boundaries

• Zero modifications and zero deletions by default — this is an inspection, not construction.
• Do not infer the teacher's intent; report only objective inconsistencies and leave the judgment to the student.