Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Prompt Cache Optimizer Skill · miosa-osa | DecimalAI

ai mlby miosa-osa

Prompt Cache Optimizer Skill

miosa-osa/prompt-cache-optimizer

Source miosa-osa/canopy ↗License Not recorded

Optimize token usage through prompt caching and compression

SkillScore82Maintained

Automatic

AI Engineer pack

Last verified 8/27/2026

What it changes

Passed 18 of 22 test cases with the skill, and 10 of 22 without it.

Without skill45%

With skill82%

Checks it passed that the model alone missed

Limits accuracy impact to under 5%
Achieves 50x to 100x document reduction
Preserves the first 4 tokens as attention sinks

and 5 more in the full report

8 fixed10 passed either way4 still failing0 broke

Pass-rate lift: +36 pp
Tokens: -6%
Agent turns: 0%
Response time: -36%

Model gemini-3.6-flashMeasured 8/27/2026v118 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/miosa-osa-prompt-cache-optimizer/SKILL.md https://app.decimal.ai/s/miosa-osa-prompt-cache-optimizer/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add miosa-osa-prompt-cache-optimizer, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/miosa-osa-prompt-cache-optimizer/ and pins it in .decimal/skills.lock

decimalai skills add miosa-osa-prompt-cache-optimizer

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/miosa-osa-prompt-cache-optimizer/SKILL.md https://app.decimal.ai/s/miosa-osa-prompt-cache-optimizer/SKILL.md

Raw file: /s/miosa-osa-prompt-cache-optimizer/SKILL.md ↗ · machine-readable summary at /s/miosa-osa-prompt-cache-optimizer.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

In a multi-level context memory system, what tier holds recent message exchanges right after working memory?

What was checked, without and with the skill
Checked	Without skill	With skill
Places recent message exchanges in a FIFO queue cache tier	Missed	Passed

case-22 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md91 linessingle file

Prompt Cache Optimizer Skill

Reduces token costs by 50-90% through intelligent caching and compression.

When to Activate

Large context windows (>50K tokens)
Repeated similar queries
Long-running sessions
Cost-conscious operations

Optimization Layers

Layer 1: Semantic Caching

Query → Embedding → Similarity Search → Cache Hit/Miss
         ↓              ↓
    Vector Store    Return cached or call LLM

Cache hits provide 100% token savings with near-instant response.

Layer 2: Prompt Compression (LLMLingua-2)

Light: 2-3x reduction, <5% accuracy impact
Moderate: 5-7x reduction, 5-15% accuracy impact
Aggressive: 10-20x reduction, requires validation

Layer 3: Strategic Context Placement

Mitigate "lost in the middle" problem:

Place most important information at START and END
Middle content has 30-50% lower retention

Layer 4: Hierarchical Memory Tiering

Working Memory (registers)  → Always in context
FIFO Queue (L1/L2 cache)    → Recent exchanges
Archival Memory (disk)      → Semantic search only

Implementation Workflow

Track record

Benchmark

18 / 22

test cases passed, vs 10 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

miosa-osa / canopy

library/skills/ai-patterns/prompt-cache-optimizer/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Prompt Cache Optimizer Skill

When to Activate

Optimization Layers

Layer 1: Semantic Caching

Layer 2: Prompt Compression (LLMLingua-2)

Layer 3: Strategic Context Placement

Layer 4: Hierarchical Memory Tiering

Implementation Workflow

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills