a5c-ai/babysitter / library/specializations/ai-agents-conversational/skills/prompt-compression
prompt-compression
VerifiedToken-efficient prompt compression techniques for cost optimization
SKILL.md
View on GitHub---
name: prompt-compression
description: Token-efficient prompt compression techniques for cost optimization
allowed-tools:
- Read
- Write
- Edit
- Bash
- Glob
- Grep
graph:
domains: [domain:software-engineering]
specializations: [specialization:ai-agents-conversational]
skillAreas: [skill-area:context-management, skill-area:prompt-engineering]
roles: [role:ml-engineer, role:backend-engineer]
workflows: [workflow:ml-model-lifecycle, workflow:feature-development]
---
# Prompt Compression Skill
## Capabilities
- Implement token-efficient prompt compression
- Design context pruning strategies
- Configure selective context inclusion
- Implement LLMLingua-style compression
- Design summary-based compression
- Create compression quality metrics
## Target Processes
- cost-optimization-llm
- agent-performance-optimization
## Implementation Details
### Compression Techniques
1. **LLMLingua**: Token-level compression
2. **Summary Compression**: LLM-based summarization
3. **Selective Context**: Relevant section extraction
4. **Token Pruning**: Remove low-importance tokens
5. **Document Filtering**: Pre-retrieval filtering
### Configuration Options
- Compression ratio targets
- Quality threshold settings
- Token budget constraints
- Compression model selection
- Evaluation metrics
### Best Practices
- Monitor quality vs compression tradeoff
- Test with representative prompts
- Set appropriate compression ratios
- Validate compressed prompt quality
- Track cost savings
### Dependencies
- llmlingua (optional)
- tiktoken
- transformers
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |