Skip to content

aiskillstore/marketplace / skills/aaronabuusama/prompting

prompting

Verified

Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio.

FileKindSize
SKILL.mdskill md2.6 KB
skill-report.jsonconfig18.5 KB
workflows/create-prompt.mdmarkdown1.1 KB
workflows/optimize-prompt.mdmarkdown1.4 KB

workflows/optimize-prompt.md

View on GitHub
# Optimize Prompt Workflow

## Trigger
User says: "optimize this prompt", "improve my prompt", "make this prompt better"

## Purpose
Improve an existing prompt using context engineering principles.

## Workflow

1. **Analyze Current Prompt**
   - Identify verbose language
   - Find redundant information
   - Look for vague instructions
   - Note missing structure

2. **Apply Optimization Techniques**
   - **Remove Redundancy**: Cut duplicate information
   - **Increase Directness**: Convert suggestions to imperatives
   - **Add Structure**: Use clear markdown sections
   - **Sharpen Language**: Replace verbose with concise

3. **Context Optimization**
   - Move lengthy examples to references
   - Use just-in-time loading for details
   - Create structured sections vs paragraphs

4. **Before/After Comparison**
   - Show token count reduction
   - Verify clarity maintained/improved
   - Ensure all requirements covered

5. **Test Results**
   - Compare outputs before/after
   - Measure performance improvement
   - Iterate if needed

## Common Patterns

**Verbose → Direct**
- ❌ "You should consider using..."
- ✅ "Use X tool for Y"

**Paragraph → List**
- ❌ Long paragraph of requirements
- ✅ Bulleted constraint list

**Full Data → Reference**
- ❌ Entire JSON schema in prompt
- ✅ "See schema.json for structure"

## Reference
See main prompting skill for detailed optimization principles.
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall