agentleFS
timscheueraitimscheuerai/gtm-architecture-template/.agents/skills/shorts-audio/SKILL.md

shorts-audio

Skill2 starsChanged 2 months agoMITView on GitHub

Improve recorded speech using measured levels, restrained noise treatment and listening comparisons against the source.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start with the smallest useful change.

    line 10

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.