Claude Skills by OnlyTerp

github.com/OnlyTerp

14 skillsA× 140 installs17 views

TEMPLATEAOne-line description of what this fix does and why it matters.ai-agentsgoapiVotes: 0GitHub stars: 114
Aider 1h TtlAAider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.ai-agentsVotes: 0GitHub stars: 114
Aider Cache Default OnAAider's --cache-prompts is off by default. Flip it on for supported models.ai-agentsgoVotes: 0GitHub stars: 114
Cline Fix Volatile MsgAStop Cline from burning a cache breakpoint on the volatile current user message every turn.ai-agentsgogitVotes: 0GitHub stars: 114
Cline Openai Cache KeyACline OpenAI native provider sends no prompt_cache_key. Add a stable per-task key so cached_tokens stops being zero.ai-agentstypescriptgoVotes: 0GitHub stars: 114
Cline Pin TimestampACline's system prompt includes a timestamp that may be recomputed per request, invalidating the system-prompt cache.ai-agentsgoVotes: 0GitHub stars: 114
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
Continue Enable DefaultsAContinue's prompt caching is opt-in via config and off by default. Flip the default to systemAndTools.ai-agentsapiVotes: 0GitHub stars: 114
Continue Fix Volatile MsgAContinue inherits the Cline-family volatile-message cache bug. Same fix shape.ai-agentsapiVotes: 0GitHub stars: 114
Continue Gemini ExplicitAContinue's Gemini provider doesn't use the cachedContents API at all. Add explicit caching for sessions over the minimum token threshold.ai-agentsgoapiVotes: 0GitHub stars: 114
Opencode Bedrock Doc BlocksAOpenCode places cachePoint on Bedrock messages containing DocumentBlocks, which produces a "nothing available to cache" error.ai-agentsapiVotes: 0GitHub stars: 114
Opencode Detect Openai CompatAOpenCode's caching detection misses OpenAI-compatible proxies routing to Anthropic/Bedrock. Broaden the predicate.ai-agentsgoapiVotes: 0GitHub stars: 114
Opencode Mistral Cache KeyAOpenCode doesn't set prompt_cache_key for Mistral models, missing the documented 10% cached-token discount.ai-agentsgoapiVotes: 0GitHub stars: 114
Roo Bedrock Custom ArnARoo Code's Bedrock provider silently disables caching for custom ARNs. Populate cachableFields to fix.ai-agentsapiVotes: 0GitHub stars: 114
Roo Fix Volatile MsgARoo Code inherits Cline's volatile-message cache bug. Same fix shape, inline location.ai-agentstypescriptgitVotes: 0GitHub stars: 114