← 返回
未分类

hifi-review

Objective, source-traceable evaluation of HiFi gear. Transducers (IEM / headphone / TWS): 量感 (per-band quantity) + 风格 (signature) from frequency-response-vs-target; technicalities from review consensus. Source gear (DAC / amp / DAP): measured competence (SINAD/THD/output-Z/power) + system matching + chip/topology — a competent source is audibly transparent. Searches all sources (measurements, media reviews, specs) via a style-profiled media roster (orientation judged dynamically), cleans them, r
Objective, source-traceable evaluation of HiFi gear. Transducers (IEM / headphone / TWS): 量感 (per-band quantity) + 风格 (signature) from frequency-response-vs-target; technicalities from review consensus. Source gear (DAC / amp / DAP): measured competence (SINAD/THD/output-Z/power) + system matching + chip/topology — a competent source is audibly transparent. Searches all sources (measurements, media reviews, specs) via a style-profiled media roster (orientation judged dynamically), cleans them, renders a bilingual verdict where every claim traces to evidence. Triggers: "客观评价这条耳机", "对比 A 和 B 的声音", "这个 DAC 素质如何 / 推得动吗", "$hifi-review". Not for: buying/价格 recommendations; EQ tuning; speakers; non-audio.
yjkj999999
未分类 community v1.0.0 1 版本 100000 Key: 无需
★ 0
Stars
📥 17
下载
💾 0
安装
1
版本
#latest

概述

hifi-review

Objective, evidence-traceable evaluation of a HiFi device. Evidence hierarchy:

**① measurement/curve data (anchor) → ② reviews (what measurement can't show) →

③ specs/family (priors). Literary phrasing may color but never exceed the

evidence. Output bilingual (中文 + English). Read-only. Accuracy ≫ speed.**

Two classes: transducer (IEM/HP/TWS) → 量感 + 风格 from FR-vs-target, technicalities

from review consensus only (never measured). source (DAC/amp/DAP) → measured

competence + system matching, chip/topology as priors — resist 玄学: if it measures

transparent, say so.

Protocol — 8 steps (branch on device class)

  1. Scope & classify — confirm objective eval/compare; set device_class ∈ {transducer, source}. Reject buying-rec / EQ / speakers / non-audio.
  2. Identify — exact model + variant (cable/filter/pad/firmware) + driver/chip; sub-category → rig+target or measurement set. Disambiguate only if genuinely ambiguous.
  3. Gather (live) — fetch per class; source-registry.json targets known reviewers + search hints; record tier + style-lean + freshness + lang. → rules/retrieval-playbook.md.
  4. Clean & normalize (mandatory) — dedup, strip marketing/non-evidence, normalize to glossary, reconcile scales, flag outliers, keep provenance. → rules/data-cleaning.md.
  5. Measure & quantize — transducer: python3 scripts/fr_analyze.py --target ; source: python3 scripts/source_analyze.py --sinad … --zout … [--target-z …]. Screenshot-only FR → qualitative. → rules/tonal-mapping.md, rules/source-gear-eval.md.
  6. Corroborate — transducer: technicalities from consensus, style-weighted (measurement-backed high-trust regardless of source; impression-led bias-corrected), N/M agreement, flag conflicts → rules/technicalities-from-reviews.md. source: engineering + transparency verdict.
  7. Synthesize — class-discriminated profile + render: compact bilingual summary OR a ~4000字 长文 (rules/longform-review.md); both render only from evidence; tag claims measured|consensus|prior + confidence; gaps "证据不足". → rules/literary-rendering.md, compare → rules/comparison-mode.md.
  8. Self-verifypython3 scripts/validate_output.py ; emit trace; never pass a FAIL.

Always obey rules/accuracy-guardrails.md: never invent a dB/curve; flag

incompatible rig/target comparisons; record dissent.

Modules

FileWhen to load
--------------------
rules/retrieval-playbook.mdStep 3 — find curves/reviews/specs per class; squig/screenshot; stop rule
rules/data-cleaning.mdStep 4 — dedup / de-market / normalize / reconcile / flag / provenance
rules/tonal-mapping.mdStep 5 transducer — bands, dB→量感, 风格, tilt, peaks, target/rig select
rules/technicalities-from-reviews.mdStep 6 transducer — review-only attrs, consensus + style weight
rules/source-gear-eval.mdStep 5–6 source — SINAD/THD/Zout/power tiers, transparency, matching
rules/accuracy-guardrails.mdAlways — rig/target match, never-invent, conflicts, EOL
rules/literary-rendering.mdStep 7 — anchored 文学化, provenance, bilingual, no over-claims
rules/comparison-mode.mdCompare — target/rig alignment, per-band delta, not-comparable
rules/longform-review.mdStep 7 — ~4000字 长文: structure / length / anchoring
references/*.json + signature-glossary.mdsingle sources of truth + glossary

Scripts

FileUsage
-------------
fr_analyze.py --target --rig transducer → 量感 / 风格 / tilt / peak-dip features
source_analyze.py --sinad N --zout N [--power --target-z --target-sens]source → tier + drive/damping matching
compare.py --target two devices → band + tilt deltas, rig guard
infer_target.py --rig guess intended target (ranks same-rig targets)
validate_output.py schema + traceability gate (exit 1)
check_longform.py --class [--backing json]长文 QA: 字 + sections + backing gate

版本历史

共 1 个版本

  • v1.0.0 从ClawHub迁移发布 当前
    2026-06-07 12:34 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

professional

A股量化 AkShare

mbpz
A股量化数据分析工具,基于AkShare库获取A股行情、财务数据、板块信息等。用于回答关于A股股票查询、行情数据、财务分析、选股等问题。
★ 185 📥 61,910
professional

All-Market Financial Data Hub

financial-ai-analyst
基于东方财富数据库,支持自然语言查询金融数据,覆盖A股、港股、美股、基金、债券等资产,提供实时行情、公司信息、估值、财务报表等,适用于投资研究、交易复盘、市场监控、行业分析、信用研究、财报审计、资产配置等场景,满足机构与个人需求。返回结果为
★ 122 📥 41,298
design-media

agnes-image-gen

user_15292d5a
使用 Agnes AI 的图片生成模型生成图片,支持文生图(agnes-image-2.1-flash)和图生图(agnes-image-2.0-flash)。支持自定义 API Key,用户可使用自己的 Agnes Key。优化重点:降低
★ 0 📥 127