automatic-stateful-prompt-improver

Automatically intercepts and optimizes prompts using the prompt-learning MCP server. Learns from performance over time via embedding-indexed history. Uses APE, OPRO, DSPy patterns. Activate on "optimize prompt", "improve this prompt", "prompt engineering", or ANY complex task request. Requires prompt-learning MCP server. NOT for simple questions (just answer them), NOT for direct commands (just execute them), NOT for conversational responses (no optimization needed).

85 stars

bycuriositech

View on GitHub Installation ↓

Best use case

automatic-stateful-prompt-improver is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Teams using automatic-stateful-prompt-improver should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/automatic-stateful-prompt-improver/SKILL.md --create-dirs "https://raw.githubusercontent.com/curiositech/some_claude_skills/main/.claude/skills/automatic-stateful-prompt-improver/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/automatic-stateful-prompt-improver/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How automatic-stateful-prompt-improver Compares

Feature / Agent	automatic-stateful-prompt-improver	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Automatic Stateful Prompt Improver

## MANDATORY AUTOMATIC BEHAVIOR

**When this skill is active, I MUST follow these rules:**

### Auto-Optimization Triggers

I AUTOMATICALLY call `mcp__prompt-learning__optimize_prompt` BEFORE responding when:

1. **Complex task** (multi-step, requires reasoning)
2. **Technical output** (code, analysis, structured data)
3. **Reusable content** (system prompts, templates, instructions)
4. **Explicit request** ("improve", "better", "optimize")
5. **Ambiguous requirements** (underspecified, multiple interpretations)
6. **Precision-critical** (code, legal, medical, financial)

### Auto-Optimization Process

```
1. INTERCEPT the user's request
2. CALL: mcp__prompt-learning__optimize_prompt
   - prompt: [user's original request]
   - domain: [inferred domain]
   - max_iterations: [3-20 based on complexity]
3. RECEIVE: optimized prompt + improvement details
4. INFORM user briefly: "I've refined your request for [reason]"
5. PROCEED with the OPTIMIZED version
```

### Do NOT Optimize

- Simple questions ("what is X?")
- Direct commands ("run npm install")
- Conversational responses ("hello", "thanks")
- File operations without reasoning
- Already-optimized prompts

## Learning Loop (Post-Response)

After completing ANY significant task:

```
1. ASSESS: Did the response achieve the goal?
2. CALL: mcp__prompt-learning__record_feedback
   - prompt_id: [from optimization response]
   - success: [true/false]
   - quality_score: [0.0-1.0]
3. This enables future retrievals to learn from outcomes
```

## Quick Reference

### Iteration Decision

| Factor | Low (3-5) | Medium (5-10) | High (10-20) |
|--------|-----------|---------------|--------------|
| Complexity | Simple | Multi-step | Agent/pipeline |
| Ambiguity | Clear | Some | Underspecified |
| Domain | Known | Moderate | Novel |
| Stakes | Low | Moderate | Critical |

### Convergence (When to Stop)

- Improvement &lt; 1% for 3 iterations
- User satisfied
- Token budget exhausted
- 20 iterations reached
- Validation score &gt; 0.95

### Performance Expectations

| Scenario | Improvement | Iterations |
|----------|-------------|------------|
| Simple task | 10-20% | 3-5 |
| Complex reasoning | 20-40% | 10-15 |
| Agent/pipeline | 30-50% | 15-20 |
| With history | +10-15% bonus | Varies |

## Anti-Patterns

### Over-Optimization

| What it looks like | Why it's wrong |
|--------------------|----------------|
| Prompt becomes overly complex with many constraints | Causes brittleness, model confusion, token waste |
| **Instead**: Apply Occam's Razor - simplest sufficient prompt wins |

### Template Obsession

| What it looks like | Why it's wrong |
|--------------------|----------------|
| Focusing on templates rather than task understanding | Templates don't generalize; understanding does |
| **Instead**: Focus on WHAT the task requires, not HOW to format it |

### Iteration Without Measurement

| What it looks like | Why it's wrong |
|--------------------|----------------|
| Multiple rewrites without tracking improvements | Can't know if changes help without metrics |
| **Instead**: Always define success criteria before optimizing |

### Ignoring Model Capabilities

| What it looks like | Why it's wrong |
|--------------------|----------------|
| Assumes model can't do things it can | Over-scaffolding wastes tokens |
| **Instead**: Test capabilities before heavy prompting |

## Reference Files

Load for detailed implementations:

| File | Contents |
|------|----------|
| `references/optimization-techniques.md` | APE, OPRO, CoT, instruction rewriting, constraint engineering |
| `references/learning-architecture.md` | Warm start, embedding retrieval, MCP setup, drift detection |
| `references/iteration-strategy.md` | Decision matrices, complexity scoring, convergence algorithms |

---

**Goal**: Simplest prompt that achieves the outcome reliably. Optimize for clarity, specificity, and measurable improvement.

Related Skills

prompt-engineer

from curiositech/some_claude_skills

Expert prompt optimization for LLMs and AI systems. Use PROACTIVELY when building AI features, improving agent performance, or crafting system prompts. Masters prompt patterns and techniques.

skill-coach

from curiositech/some_claude_skills

Guides creation of high-quality Agent Skills with domain expertise, anti-pattern detection, and progressive disclosure best practices. Use when creating skills, reviewing existing skills, or when users mention improving skill quality, encoding expertise, or avoiding common AI tooling mistakes. Activate on keywords: create skill, review skill, skill quality, skill best practices, skill anti-patterns. NOT for general coding advice or non-skill Claude Code features.

3d-cv-labeling-2026

from curiositech/some_claude_skills

Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).

wisdom-accountability-coach

from curiositech/some_claude_skills

Longitudinal memory tracking, philosophy teaching, and personal accountability with compassion. Expert in pattern recognition, Stoicism/Buddhism, and growth guidance. Activate on 'accountability', 'philosophy', 'Stoicism', 'Buddhism', 'personal growth', 'commitment tracking', 'wisdom teaching'. NOT for therapy or mental health treatment (refer to professionals), crisis intervention, or replacing professional coaching credentials.

windows-95-web-designer

from curiositech/some_claude_skills

Modern web applications with authentic Windows 95 aesthetic. Gradient title bars, Start menu paradigm, taskbar patterns, 3D beveled chrome. Extrapolates Win95 to AI chatbots, mobile UIs, responsive layouts. Activate on 'windows 95', 'win95', 'start menu', 'taskbar', 'retro desktop', '95 aesthetic', 'clippy'. NOT for Windows 3.1 (use windows-3-1-web-designer), vaporwave/synthwave, macOS, flat design.

windows-3-1-web-designer

from curiositech/some_claude_skills

Modern web applications with authentic Windows 3.1 aesthetic. Solid navy title bars, Program Manager navigation, beveled borders, single window controls. Extrapolates Win31 to AI chatbots (Cue Card paradigm), mobile UIs (pocket computing). Activate on 'windows 3.1', 'win31', 'program manager', 'retro desktop', '90s aesthetic', 'beveled'. NOT for Windows 95 (use windows-95-web-designer - has gradients, Start menu), vaporwave/synthwave, macOS, flat design.

win31-pixel-art-designer

from curiositech/some_claude_skills

Expert in Windows 3.1 era pixel art and graphics. Creates icons, banners, splash screens, and UI assets with authentic 16/256-color palettes, dithering patterns, and Program Manager styling. Activate on 'win31 icons', 'pixel art 90s', 'retro icons', '16-color', 'dithering', 'program manager icons', 'VGA palette'. NOT for modern flat icons, vaporwave art, or high-res illustrations.

win31-audio-design

from curiositech/some_claude_skills

Expert in Windows 3.1 era sound vocabulary for modern web/mobile apps. Creates satisfying retro UI sounds using CC-licensed 8-bit audio, Web Audio API, and haptic coordination. Activate on 'win31 sounds', 'retro audio', '90s sound effects', 'chimes', 'tada', 'ding', 'satisfying UI sounds'. NOT for modern flat UI sounds, voice synthesis, or music composition.

wedding-immortalist

from curiositech/some_claude_skills

Transform thousands of wedding photos and hours of footage into an immersive 3D Gaussian Splatting experience with theatre mode replay, face-clustered guest roster, and AI-curated best photos per person. Expert in 3DGS pipelines, face clustering, aesthetic scoring, and adaptive design matching the couple's wedding theme (disco, rustic, modern, LGBTQ+ celebrations). Activate on "wedding photos", "wedding video", "3D wedding", "Gaussian Splatting wedding", "wedding memory", "wedding immortalize", "face clustering wedding", "best wedding photos". NOT for general photo editing (use native-app-designer), non-wedding 3DGS (use drone-inspection-specialist), or event planning (not a wedding planner).

websocket-streaming

from curiositech/some_claude_skills

Implements real-time bidirectional communication between DAG execution engines and visualization dashboards via WebSocket. Covers connection management, typed event protocols, reconnection with backoff, and React hook integration. Activate on "WebSocket", "real-time updates", "live streaming", "execution events", "state streaming", "push notifications". NOT for HTTP REST APIs, server-sent events (SSE), or general networking.

webapp-testing

from curiositech/some_claude_skills

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs. Activate on: Playwright, webapp testing, browser automation, E2E testing, UI testing. NOT for API-only testing without browser, unit tests, or mobile app testing.

web-weather-creator

from curiositech/some_claude_skills

Master of stylized atmospheric effects using SVG filters and CSS animations. Creates clouds, waves, lightning, rain, fog, aurora borealis, god rays, lens flares, twilight skies, and ocean spray—all with a premium aesthetic that's stylized but never cheap-looking.