Agent skill
prompt-optimizer-vuralserhat86-antigravity-agentic
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/prompt-optimizer-vuralserhat86-antigravity-agentic
SKILL.md
⚡ Prompt Optimizer
Prompt verimliliğini artırma ve token maliyeti düşürme metodolojisi.
Prompt Optimizer v1.1 - Enhanced
🔄 Workflow
Aşama 1: Analysis & Benchmarking
- Analyze: Mevcut promptun nerede hata yaptığını veya neden çok token harcadığını belirle.
- Baseline: Başarı oranını ve ortalama token sayısını kaydet.
Aşama 2: Rewriting & Compression
- Clarity: Gereksiz yan cümleleri at, net emir kipleri kullan.
- Compression: Anlam kaybı olmadan token sayısını azalt (Stopwords temizliği vb.).
- Prompt Chaining: Tek bir dev prompt yerine görevleri küçük, zincirleme promptlara böl.
Aşama 3: Verification (A/B Test)
- Test: Optimize edilmiş promptu eskisiyle aynı inputlar üzerinde kıyasla.
- Score: Yanıt doğruluğu, hızı ve maliyeti üzerinden puanla.
Kontrol Noktaları
| Aşama | Doğrulama |
|---|---|
| 1 | Token tasarrufu >%20 sağlandı mı? |
| 2 | Başarı oranı (Accuracy) düştü mü? |
| 3 | Modelin çıktı formatı tutarlı kalmaya devam ediyor mu? |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?