Agent skill
shorts-audio
Improve recorded speech using measured levels, restrained noise treatment and listening comparisons against the source.
From timscheuerai/gtm-architecture-template · 51 skill entries · 13 · pushed 2026-09-17
What it does when it runs
Improve recorded speech using measured levels, restrained noise treatment and listening comparisons against the source.
Automated analysis of the skill and the 0 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.
- Keys and connectors you must supply
- None found.
- Hosts it reaches
- No third-party host appears in the skill or its bundled files.
- Tool permissions it declares
- No
allowed-toolsin the frontmatter. It only issues instructions, so there is nothing to bound. - Actions present in the files
- None. Instructions only.
Install it
View source on GitHub ↗git clone --depth 1 --filter=blob:none --sparse https://github.com/timscheuerai/gtm-architecture-template.git /tmp/gtm-architecture-template git -C /tmp/gtm-architecture-template sparse-checkout set ".agents/skills/shorts-audio" mkdir -p ~/.claude/skills/shorts-audio cp -R "/tmp/gtm-architecture-template/.agents/skills/shorts-audio/." ~/.claude/skills/shorts-audio/
Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗
The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.
The skill
Source on GitHub ↗Reproduced in full from timscheuerai/gtm-architecture-template/blob/2c312c9398064ad3730c786647293458cb89632c/.agents/skills/shorts-audio/SKILL.md, which is licensed MIT (repository). 173 words, 1 heading.
Treat the actual audio problem
Listen to the original and measure sample rate, channels, loudness and peaks with the available audio tooling. Identify noise, clipping, uneven delivery, room tone or low level separately. Increasing level is not denoising.
Start with the smallest useful change. A constant gain preserves dynamics when headroom allows. If compression or limiting is needed, make it deliberate and listen for pumping, clipped consonants and lost room tone. Inspect current filter help; a requested linear mode may have constraints.
For noise reduction, use representative silence and compare speech before/after at matched loudness. Reject settings that create burbling or remove the speaker's texture. Do not prescribe a universal denoiser or fixed gain from another recording.
Apply channel conversion, EQ, dynamics and final level in an intentional order. Check the final mix including music and sound effects, especially overlapping peaks and mono/stereo changes.
Measure and listen to the encoded artifact, not just the intermediate PCM. Report the actual treatment, output measurements and audible tradeoffs. Use shorts-qa for the combined video/audio deliverable.
Need help setting it up?
This page tells you what shorts-audio does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.
Book a call →The directory stays free. There is nothing gated behind this.