OpenSkillIndex← back to search
claude-codeopenclawproductivity

Skills promptcache

Estimate the cost savings from caching frequently-used prompts across AI models.

install
source · Clone the upstream repo
git clone https://github.com/openclaw/skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/avale-slai/promptcache" ~/.claude/skills/openclaw-skills-promptcache && rm -rf "$T"
OpenClaw · Install into ~/.openclaw/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/avale-slai/promptcache" ~/.openclaw/skills/openclaw-skills-promptcache && rm -rf "$T"
manifest: skills/avale-slai/promptcache/SKILL.md
tags
#cost-analysis#prompt-optimization#caching#ai-economics#performance
source content

promptcache — LoomLens Advisor

What It Does

Estimates the cost savings from caching frequently-used prompts. Compares the cost of re-sending full context every call vs. cached prompt mode across all major models.

When to Use

  • When you run the same system prompt repeatedly
  • Before enabling prompt caching on a production pipeline
  • When evaluating cost savings from prompt template reuse

Syntax

/promptcache "You are an expert radiologist..." --calls-per-day 50
/promptcache "Summarize this in 3 bullets" --model openai/gpt-4o-mini

Free Tier

3 analyses/day free with any Signalloom API key.

Get your free key: https://signalloomai.com/signup