Mc AI Tell Audit
The post-generation AI-tell audit (AI 味诊断). Run this on every generated track before accepting it. Covers the fourteen enumerable defaults that generative music models fall into, which of them are machine-measurable and which need ears, why compliance rate and AI-tell count are two separate numbers that must never be merged, the zero-point calibration that sets the pass threshold at 82 rather than 60, the ordered diagnostic path from symptom to owning skill, and the remediation list. Use when a generation comes back and must be accepted or rejected, when a track sounds synthetic but you cannot
Install
/plugin marketplace add jtydhr88/music-composition-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add jtydhr88/music-composition-skills --skill mc-ai-tell-auditgit clone --depth 1 https://github.com/jtydhr88/music-composition-skills.git /tmp/music-composition-skills
mkdir -p ~/.claude/skills
cp -r /tmp/music-composition-skills/plugins/music-composition/skills/mc-ai-tell-audit ~/.claude/skills/mc-ai-tell-auditPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# AI 味诊断(AI-Tell Audit) **生成回来的每一条都要过这个 skill。这是本库的终检。** > **核心命题**:AI 味不是玄学。 > **生成模型不给规格就走默认值,而这些默认值是可枚举的。** > 本 skill 就是那份枚举,加上"每一条怎么查、归谁管"。 ## 按任务读哪几节 | 任务 | 读 | |---|---| | 刚生成完,要验收 | §2 十四条 → §3 判定 | | "听着像 AI 但说不出哪里" | §2(★ **逐条查,不要凭直觉**) | | 照做率很高但结果不好 | §4 | | 要定阈值 | §3.2 零点校准 | | 查出问题了要改 | §5 整改路径 | | 人声的四条怎么查 | §6 | ## 边界 | 不归这里 | 归哪 | |---|---| | 规格**写完**时的检查 | `mc-workflow` §3.0 的 20 条自查表 | | 照做率怎么算 | 本 skill §3.1(定义与标定);honors 三档怎么影响计分见 `mc-render-compile` §6 | | 具体怎么改 | 各 L1/L2 skill(§5 给路由) | | 后端做不到的字段怎么办 | `mc-render-compile` §6、§7 | > ★ **与 20 条自查的分工**: > **自查问"规格写完没有",本 skill 问"生成出来的东西像不像人做的"。** > **两边都看过才算完。** 17 条全过的规格照样可能生成出满是 AI 味的音频。 --- ## 1. 动笔前必填 | 必填 | 问法 | |---|---| | **① 这一版的规格与种子** | 没记录就没法复现,**审计结果也就没用** | | **② 后端的 honors 表** | 哪些项是它做不到的——**那些不算它的账** | | **③ 有没有分轨** | 人声四条(§6)需要先分离人声轨 | --- ## 2. ★ 十四条枚举 **逐条打勾。不要凭整体印象。** | # | AI 味来源(后端默认值) | 对抗的 spec 字段 | 可自动测 | 归谁管 | |---|---|---|---|---| | **1** | 段落全是 8 的整数倍 | `form[].bars` | ✅ 段落边界检测 | `mc-arrangement-arch` §4 | | **2** | **能量曲线单调递增,从不减** | `energy_curve`、`subtraction_events` | ✅ 分段 RMS | `mc-arrangement-arch` §2、§3 | | **3** | 编制从头到尾不变 | `roster[].entry/exit` | ✅ 分轨 onset 密度 | `mc-arrangement-arch` §5 | | **4** | 全曲一个和声循环到底 | bridge 必须离调或转调 | ✅ 和弦识别 | `mc-harmony`、`mc-modulation` | | **5** | fill 刻板落在 4 的倍数 | `fill_policy` | ✅ onset 峰值位置 | `mc-rhythm-section` §8 | | **6** | 没有非人声记忆点 | `hooks.arrangement_hook` | ⚠️ 半自动(重复段落相似度) | `mc-arrangement-arch` §7 |
Details
- Skill name
mc-ai-tell-audit- Repository
- jtydhr88/music-composition-skills
- Path
plugins/music-composition/skills/mc-ai-tell-audit/SKILL.md- License
- MIT
- Repo updated
- 30 October 2026
FAQ
What does the Mc AI Tell Audit skill do?
The post-generation AI-tell audit (AI 味诊断). Run this on every generated track before accepting it. Covers the fourteen enumerable defaults that generative music models fall into, which of them are machine-measurable and which need ears, why compliance rate and AI-tell count are two separate numbers that must never be merged, the zero-point calibration that sets the pass threshold at 82 rather than 60, the ordered diagnostic path from symptom to owning skill, and the remediation list. Use when a generation comes back and must be accepted or rejected, when a track sounds synthetic but you cannot
How do I install the Mc AI Tell Audit skill?
Claude Code plugin: /plugin marketplace add jtydhr88/music-composition-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Mc AI Tell Audit popular?
It lives in jtydhr88/music-composition-skills, which has 224 GitHub stars and 25 forks.
Related skills
Mc Arrangement Arch
224jtydhr88/music-composition-skills
Arrangement architecture (编曲结构学) - the shape of a track over time rather than its notes. Energy curve and dramatic arc, subtractive arranging, layering as form (instrument entry/exit events), formal skeletons and section proportion, arrangement-hook placement, why the second verse must not be a copy, and how to end. Use when the user is arranging a song and asks how to structure it, when a track "goes nowhere" or "sounds flat", when every section sounds the same, when a generated track sounds like AI (monotonic energy, unchanging instrumentation, no subtraction), when deciding where instrument
Mc Case Studies
224jtydhr88/music-composition-skills
The corpus layer (语料层) - how real recordings are made to testify for or against the textbook rules. Covers the reverse ARR-SPEC as the unit of the corpus, the corroboration table that turns rules times corpus into hit rates and tiers them as strong rule / tendency / not a rule, the two honesty constraints that keep the table from being circular, why naturally sampled corpora beat curated ones, what this corpus can and cannot measure, and how to look up a worked example. Use when checking whether a rule actually holds in real music, when adding a rule, when a rule and the data disagree, when an
Mc Counterpoint
224jtydhr88/music-composition-skills
Counterpoint and voice writing (对位与声部写作) - writing a second line that is genuinely independent rather than a harmony part. The four complementarity axes that make two lines combine (rhythmic density, interval colour, contrary/oblique/similar motion, staggered peaks), contrast between unlike versus like characters, the melodic constraints a contrapuntal line must obey, the five species, and invertible counterpoint for varying a repeat. Use when writing a counter-melody or obbligato, when checking voice leading in a multi-part passage (parallel fifths and octaves, hidden fifths, voice crossing a
Mc Progressions
224jtydhr88/music-composition-skills
Chord progression lookup library (和弦进行速查库) - the eight famous named progressions with their variants and what each one actually does, a mood reverse-lookup, the eight variation techniques that turn one standard progression into ten, and an explicit warning list of the progressions generative models default to. This is a lookup skill, not a teaching skill - it answers "give me a progression that does X". Harmonizing a melody, choosing chords bar by bar, or reharmonizing is mc-harmony, and a full track needs mc-harmony first and this table second. Use when you need a progression for a specific m
Tavern Card Builder
224LiarMTTT/TavernWeave
Plan and author SillyTavern text, MVU Zod, and hybrid cards with required greetings and worldbooks, character design, player profiles and agency, optional character stages, portrayal diagnosis and corrections, worldbuilding, variables, and prompt routing. Use for new or inherited cards, standalone rolecard prompt rules, opening style, small in-card creative pieces, author-facing assessment, character material, worldbuilding, state systems, and field tracing. Route independent worldbook design and writing, packaging, exact APIs, live debugging, embedded UI implementation, and workshop infrastru
Mc Sound Design
224jtydhr88/music-composition-skills
Synth and timbre design as an arrangement decision (音色设计) - deciding what a sound must be before touching a knob. The four-question intent checklist (percussive or pitched / register / envelope shape / bright or dark) and its mapping to oscillator, tune, amp EG and filter; resetting to an unprocessed starting state instead of browsing presets; the sculpting model of subtractive synthesis; filter selection; and why a pure sine bass vanishes on small speakers (difference tones). Use when choosing or designing a patch, when a synth sound is generic or preset-sounding, when a bass disappears on ph
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.