Skip to main content
ANY
SkillFreeBy GameSkill · tuned

earshot: ears for coding agents (judge, find, time-align and make game sound on CPU)

/earshot

Let an agent hear: rank sound-effect candidates against a description, find the clean trim in a long recording, tell real recordings from code-synthesised sound, check that every hit lands on its picture cut, and render effects from a bank of 252 code-made sounds. Runs locally on CPU with two open audio models (~1.1 GB, downloaded once); no API key needed.

License
MIT
By
By GameSkill
Download ZIP

Listed from the author's README. GameSkill has not run this end to end yet. Agent support and install steps are as documented by the author.

What this skill does

When it triggers

Listen with earshot whenever you must judge, choose, trim, verify or compare sound you cannot hear - picking a sound effect, music or ambience from candidates, finding the cleanest moment in a recording …

GameSkill's tested copy

GameSkill's tuned build of this skill: the skill files from commit 591fa3e02803, plus our runnable example, test report, self-check list and Chinese guide, put through our skill process.

License: based on Leonxlnx/earshot by Leonxlnx, under MIT. The ZIP keeps the license files (LICENSE) and lists everything GameSkill added in CHANGES.md.

earshot: ears for coding agents (judge, find, time-align and make game sound on CPU)

Self-check

  • 说声音怎么样之前先跑 earshot,并引用数字 / Run earshot before saying how anything sounds, and quote the number
  • z >= 3 才算强匹配 / Only z >= 3 is a strong match
  • 用 find 给出的干净片段,不用 head cut 或 tail cut / Use clean trims from find, never a head or tail cut
  • 每个画面切点都要有声音落在一帧以内 / Every picture cut gets a sound within one frame
  • 上传音频给 Gemini 前先问用户 / Ask before uploading audio to Gemini

Install

Tell your AI

Install the skill from https://gameskill.dev/skills/earshot/install.md

GameSkill's tested copy

Tested copy into .claude/skills/
mkdir -p .claude/skills
curl -fsSL https://gameskill.dev/dl/skills/earshot.zip -o /tmp/gameskill-earshot.zip
unzip -oq /tmp/gameskill-earshot.zip -d .claude/skills
rm /tmp/gameskill-earshot.zip

What you get

  • describe, match, rank and find: what a sound sounds like, with calibrated scores, and the best trims in a long file
  • realness: real or pro-produced recording versus code-synthesised sound, with its evidence
  • timeline and sheet: events, loudness and sync of a film's sound to its picture cuts, as text and as a PNG
  • sfx and kit: 252 code-made sounds (15 fitted from CC0 recordings) rendered to WAV, aimed at the picture
  • An MCP server with the same tools, so the models load once

Good fit

  • Picking sound effects for a game from a folder of candidates
  • Checking a trailer or cutscene: does each hit land on its cut, how loud is it
  • Telling whether a downloaded effect is a real recording or a cheap synth

Not for

  • Composing music
  • Machines without about 3 GB free (torch CPU plus the two models)

Try this prompt

Prompt
Here are four candidate sounds for the moment the lantern lights in my trailer. Pick the one that sounds like a small bright bell, check it is clean, and tell me whether it lands on the cut at 1.0 s.

About this skill

earshot gives a coding agent a way to judge sound it cannot hear. Every command returns numbers (calibrated match scores, LUFS, sync offsets in milliseconds) and a plain summary, and SKILL.md teaches the agent never to say how something sounds without one of those numbers behind it.

For game work the useful loops are: shortlist effects from a folder by description (rank), cut the clean moment out of a long recording (find), check that a downloaded effect is a real recording (realness), and listen through a trailer or cutscene to see whether each hit lands on its picture cut (timeline, sheet). The bank of 252 code-made sounds (sfx, kit) covers clicks, pops, whooshes, hits, risers and UI tones without any download.

It runs on CPU with two open models, LAION CLAP (Apache-2.0) and the MIT AST AudioSet tagger (BSD-3-Clause), pinned to fixed revisions and downloaded once (about 1.1 GB).

Requirements

  • Python 3.10+ and ffmpeg
  • torch (CPU wheel) and transformers, about 1.7 GB installed
  • About 1.1 GB for the two audio models (CLAP Apache-2.0, AST BSD-3-Clause), downloaded once from Hugging Face at pinned revisions

FAQ

Based on Leonxlnx/earshot by Leonxlnx (MIT). The author's LICENSE and NOTICE files ship in the ZIP; ATTRIBUTION.md and CHANGES.md list the source commit and what GameSkill added.

Works well with

Skills the author points to as related or as the better fit for neighbouring tasks.

Similar skills