From speak-pack
Optimize Speak costs through tier selection, usage monitoring, and efficient lesson design. Use when analyzing Speak billing, reducing API costs, or implementing usage monitoring and budget alerts for language learning apps. Trigger with phrases like "speak cost", "speak billing", "reduce speak costs", "speak pricing", "speak expensive", "speak budget".
How this skill is triggered — by the user, by Claude, or both
Slash command
/speak-pack:speak-cost-tuningThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Optimize Speak costs through smart tier selection, efficient lesson design, and usage monitoring.
Optimize Speak costs through smart tier selection, efficient lesson design, and usage monitoring.
For full implementation details, load: Read(${CLAUDE_SKILL_DIR}/references/implementation-guide.md)
| Issue | Cause | Solution |
|---|---|---|
| Unexpected charges | Untracked usage | Implement monitoring |
| Overage fees | Wrong tier | Upgrade tier |
| Budget exceeded | No alerts | Set up alerts |
| Inefficient audio | No preprocessing | Add client-side optimization |
const usage = usageMonitor.getUsageReport();
const estimate = estimateSpeakCost(usage.lessons, usage.audioMinutes, 'personal');
console.log(`Current spend: $${estimate.totalCost.toFixed(2)}`);
console.log(`Base: $${estimate.baseCost} | Overage: $${estimate.overageCost.toFixed(2)}`);
if (estimate.recommendation) {
console.log(`Recommendation: ${estimate.recommendation}`);
}
For architecture patterns, see speak-reference-architecture.
npx claudepluginhub terrylica/claude-code-plugins-plus --plugin speak-packGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Synthesizes the current conversation into a structured spec (PRD) and publishes it to the project issue tracker with a ready-for-agent label, without interviewing the user.
4plugins reuse this skill
First indexed Jul 11, 2026