onlyterp/prompt-cache-skills
14 skills
$npx skills add onlyterp/prompt-cache-skillsSkillInstalls
_TEMPLATEaider-1h-ttlAider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.aider-cache-default-onAider's --cache-prompts is off by default. Flip it on for supported models.cline-fix-volatile-msgStop Cline from burning a cache breakpoint on the volatile current user message every turn.cline-openai-cache-keyCline OpenAI native provider sends no prompt_cache_key. Add a stable per-task key so cached_tokens stops being zero.cline-pin-timestampCline's system prompt includes a timestamp that may be recomputed per request, invalidating the system-prompt cache.continue-enable-defaultsContinue's prompt caching is opt-in via config and off by default. Flip the default to systemAndTools.continue-fix-volatile-msgContinue inherits the Cline-family volatile-message cache bug. Same fix shape.continue-gemini-explicitContinue's Gemini provider doesn't use the cachedContents API at all. Add explicit caching for sessions over the minimum token threshold.opencode-bedrock-doc-blocksOpenCode places cachePoint on Bedrock messages containing DocumentBlocks, which produces a "nothing available to cache" error.opencode-detect-openai-compatOpenCode's caching detection misses OpenAI-compatible proxies routing to Anthropic/Bedrock. Broaden the predicate.opencode-mistral-cache-keyOpenCode doesn't set prompt_cache_key for Mistral models, missing the documented 10% cached-token discount.roo-bedrock-custom-arnRoo Code's Bedrock provider silently disables caching for custom ARNs. Populate cachableFields to fix.roo-fix-volatile-msgRoo Code inherits Cline's volatile-message cache bug. Same fix shape, inline location.