Agent skill
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).
Install this agent skill to your Project
npx add-skill https://github.com/curiositech/some_claude_skills/tree/main/.claude/skills/automatic-stateful-prompt-improver
Metadata
Additional technical details for this skill
- tags
-
prompts optimization learning embeddings dspy
- category
- AI & Machine Learning
- pairs with
-
[ { "skill": "skill-coach", "reason": "Optimize skill prompts systematically" }, { "skill": "skill-logger", "reason": "Track prompt performance over time" } ]
SKILL.md
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:
- Complex task (multi-step, requires reasoning)
- Technical output (code, analysis, structured data)
- Reusable content (system prompts, templates, instructions)
- Explicit request ("improve", "better", "optimize")
- Ambiguous requirements (underspecified, multiple interpretations)
- 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 < 1% for 3 iterations
- User satisfied
- Token budget exhausted
- 20 iterations reached
- Validation score > 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.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
curiositech/some_claude_skills
3d-cv-labeling-2026
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).
curiositech/some_claude_skills
project-management-guru-adhd
Expert project manager for ADHD engineers managing multiple concurrent projects. Specializes in hyperfocus management, context-switching minimization, and parakeet-style gentle reminders. Activate on 'ADHD project management', 'context switching', 'hyperfocus', 'task prioritization', 'multiple projects', 'productivity for ADHD', 'task chunking', 'deadline management'. NOT for neurotypical project management, rigid waterfall processes, or general productivity advice without ADHD context.
curiositech/some_claude_skills
large-scale-map-visualization
Master of high-performance web map implementations handling 5,000-100,000+ geographic data points. Specializes in Leaflet.js optimization, Supercluster algorithms, viewport-based loading, canvas rendering, and progressive disclosure UX patterns.
curiositech/some_claude_skills
adhd-design-expert
Designs digital experiences for ADHD brains using neuroscience research and UX principles. Expert in reducing cognitive load, time blindness solutions, dopamine-driven engagement, and compassionate design patterns. Activate on 'ADHD design', 'cognitive load', 'accessibility', 'neurodivergent UX', 'time blindness', 'dopamine-driven', 'executive function'. NOT for general accessibility (WCAG only), neurotypical UX design, or simple UI styling without ADHD context.
curiositech/some_claude_skills
liaison
Translate multi-agent ecosystem activity into human-readable status briefings, decision requests, and progress summaries. Use for 'status update', 'brief me', 'what happened', 'summarize progress'. NOT for project planning (use project-management-guru-adhd), code review, or technical documentation.
curiositech/some_claude_skills
windows-95-web-designer
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.
Didn't find tool you were looking for?