Agent skills
Install the KugelAudio agent skills from the Python or JavaScript SDK so coding agents like Claude Code, Cursor or Codex follow the KugelAudio integration rules.
On this page
The Python and JavaScript SDKs ship agent skills: SKILL.md files that
teach coding agents (Claude Code, Cursor, Codex) how to build on KugelAudio.
| Skill | What it teaches |
|---|---|
kugelaudio-tts | A correct, low-latency text to speech integration in your own app: when to flush a streaming session, which latency levers matter, how to write text that sounds right |
Agents load skills from a skills directory such as .claude/skills/; they do
not look inside installed packages. So installing the SDK is not enough: one
command copies the skills where the agent will find them.
Install into a project
npm install kugelaudio
npx kugelaudio-skills installuv add kugelaudio
uv run kugelaudio-skills installpip install kugelaudio
kugelaudio-skills install# Maven has no install hook, so pull the skills from the npm package
npx -p kugelaudio kugelaudio-skills installThis writes the skills into ./.claude/skills/, one folder each. Claude Code picks up a skill added to a
skills directory it already watches without a restart. If the install created
that directory in the first place and the skills don't show up, restart once so
it starts watching it.
| Flag | Effect |
|---|---|
--global | Install into ~/.claude/skills/ instead of the current directory |
--dest <dir> | Install into another directory (for agents that read a different path) |
--force | Overwrite an existing copy; without it, your edits are preserved |
Run npx kugelaudio-skills list (npm), uv run kugelaudio-skills list (uv), or
kugelaudio-skills list (pip) to see what a package version bundles.
What kugelaudio-tts covers
- The four mistakes behind most bad integrations: per-sentence flushing, a new
session per sentence, no pre-connect, unset
language. - The latency levers in priority order, and the chunk-size ordering.
- Writing text for speech: no markdown or emoji,
!and ALL-CAPS as prosody cues,<break>snapping to the trained pause lengths,<spell>, and a drop-in LLM system-prompt block. - Which API surface fits which situation.
- Choosing between the hosted API and an on-premise deployment: a Helm chart your team installs and operates with KugelAudio support, which needs outbound HTTPS to the hosted API.
The skills are mostly behavioral guidance. They name the current model ID
and the main SDK methods, so re-install them with --force
after upgrading the SDK; for details they link to these docs.
Commit them or not
Committing the skill folders in .claude/skills/ pins the guidance for everyone on the team and
for cloud agent sessions, which do not read your machine's ~/.claude/skills/.
Re-run the install command with --force after upgrading the SDK to pick up
newer versions of the skills.