album-review

Produce ONE extremely-high-quality long-form 乐评 (10,000–15,000 中文字符) from a
primary credit + album name. Deep multi-pass research grounds every
discographic fact; strong reasoning forms the critical thesis; a deterministic
validator gates length, section coverage, and claim→evidence traceability before
anything ships. Speed is not a concern — quality and honesty are the only bars.

Locked decisions (do not re-litigate):
- 中文字符 = CJK 汉字 ONLY (regex [一-鿿]). Latin/digits/punctuation do NOT
count toward the 10,000–15,000 window, so padding cannot game the floor.
- Emit a backing JSON (claims[] + evidence[]) alongside the prose, so the
traceability gate is machine-checkable. A fact-class claim whose source_id is
absent from evidence[] FAILs the gate.
- Research access: at runtime USE web/search tools (WebSearch/WebFetch) for the
fan-out when available; degrade honestly to caller-supplied material when offline
(set trace.research_mode). Never fabricate to fill a gap or hit the floor.

Steps

1. Preflight + route. Confirm exactly one album + a primary credit. If the
   input is gear, lyric-translation, or buying advice, do NOT produce a review —
   route per the description's Do-NOT line. The classifier in
   scripts/check_review.py:classify_route mirrors this.
2. Classify (runtime judgment, not a fixed enum). Set rich descriptors: idiom,
   era, role-of-credit, work-vs-performance (classical), and release form
   (single / EP / LP / box / live). Set the unit of analysis (逐曲 vs 逐乐章 vs 逐碟).
   Pick the critical lens from the descriptors — never force a pop template onto a
   symphony or vice versa. Load rules/genre-lenses.md.
3. Research. Build a source roster, breadth-fan-out across angles
   [artist/genesis, recording/production, the music itself, reception/criticism,
   comparisons, cultural-historical context], then depth-deepen thin angles. Clean,
   grade, triangulate. Map every discographic fact to a source_id. For thin
   (obscure) albums, degrade honestly with explicit 资料不足/公开资料有限 — never
   invent track/personnel/date specifics. Load rules/research-protocol.md and
   references/source-roster.md.
4. Reason. Multi-pass: form the critical thesis and per-section judgments; tag
   each statement grounded-fact vs interpretation.
5. Write. Render the genre-adapted long-form skeleton (assets/review-template.md),
   10,000–15,000 中文字符, classical separating WORK from PERFORMANCE and carrying a
   参考录音/版本比较 section. Emit the backing JSON (assets/backing.example.json,
   contract schemas/backing.schema.json).
6. Verify (gate — never ship a FAIL). Run the validator over the review +
   backing; fix and re-run until exit 0:
   bash python3 scripts/check_review.py <review.md> --class standard|classical \ --backing <backing.json>
7. Report. The 乐评 + an 证据附录 (evidence appendix) summarizing sources.

Controls (externalized, not prose-only)

• Length + section + traceability are enforced by scripts/check_review.py
  (CJK-字 window, genre-adapted section linter) + scripts/validate_backing.py
  (every fact-class claim's source_id must exist in evidence[]). Ship is
  blocked on any non-zero exit.
• No buying/price/transaction advice; read-only research.
• Honest degradation for thin-info albums (explicit 资料不足, zero invented
  specifics).

Metrics

See rules/metric-plan.md: length-window conformance rate (target ≥0.9),
ungrounded-claim rate (target 0), section-coverage pass rate, and activation
precision vs adjacent skills (album-review vs hifi-review vs lyric-translation).

Modules

Scripts

Assets

Lifecycle

Version 0.1.0; see CHANGELOG.md. Release gate: ship only when
python3 evals/run_all.py is GREEN (length + section + traceability + routing).
Roster/template changes require a re-run of the eval fixtures. Rollback = revert
to the prior SKILL.md + scripts/.