home / skills / zpankz / mcp-skillset / self-improving

self-improving skill

/self-improving

This skill automatically searches the PRPM registry for relevant expertise and suggests installation to enhance infrastructure, testing, deployment, or

npx playbooks add skill zpankz/mcp-skillset --skill self-improving

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
4.4 KB
---
name: self-improving
description: Use when starting infrastructure, testing, deployment, or framework-specific tasks - automatically searches PRPM registry for relevant expertise packages and suggests installation to enhance capabilities for the current task
---

# Self-Improving with PRPM

## Purpose

Automatically search and install PRPM packages to enhance Claude's capabilities for specific tasks. When working on infrastructure, testing, deployment, or framework-specific work, Claude searches the PRPM registry for relevant expertise and suggests packages to install.

## When to Use

**Automatically triggers when detecting:**
- Infrastructure keywords: aws, pulumi, terraform, kubernetes, docker, beanstalk
- Testing keywords: test, playwright, jest, cypress, vitest, e2e
- Deployment keywords: ci/cd, github-actions, gitlab-ci, deploy, workflow
- Framework keywords: react, vue, next.js, express, fastify, django

## Workflow

### 1. Task Analysis
Analyze user request for keywords and extract relevant terms.

### 2. Automatic Search
```bash
prpm search "<detected keywords>" --limit 5 --no-interactive
```

### 3. Package Suggestion
Present top 3 most relevant packages with:
- Package name and author
- Download count
- Brief description
- Confidence level (official/featured/community)

### 4. Installation (with approval)
```bash
prpm install <package-name> --as claude
```

### 5. Application
Load package knowledge and apply to current task.

## Decision Rules

### High Confidence (Auto-suggest)
- ✅ Official packages (`@prpm/*`)
- ✅ Featured packages
- ✅ High downloads (>1,000)
- ✅ Verified authors

### Medium Confidence (Present options)
- ⚠️ Community packages (<1,000 downloads)
- ⚠️ Multiple similar packages
- ⚠️ Tangentially related packages

### Low Confidence (Skip)
- ❌ Unverified packages
- ❌ Deprecated packages
- ❌ Zero downloads

## Example Interaction

```
User: "Help me build Pulumi + Beanstalk infrastructure"

Analysis:
  Keywords: Pulumi, Beanstalk, infrastructure
  Search: prpm search "pulumi beanstalk infrastructure"
  Found: @prpm/pulumi-infrastructure (Official, 3.2K downloads)
  Confidence: High → Auto-suggest

Response:
"I found an official PRPM package that can help:

📦 @prpm/pulumi-infrastructure (Official, 3.2K downloads)
   - Pulumi TypeScript best practices
   - AWS resource patterns
   - Cost optimization guidelines

Should I install this to enhance my Pulumi knowledge?"

User: "Yes"

Action:
  ✅ Installing: prpm install @prpm/pulumi-infrastructure --as claude
  ✅ Loading knowledge
  ✅ Applying patterns to current task
```

## Search Triggers

### Infrastructure Tasks
**Keywords**: aws, gcp, azure, kubernetes, docker, pulumi, terraform
**Search**: `prpm search "infrastructure <cloud> <tool>"`

### Testing Tasks
**Keywords**: test, playwright, jest, cypress, vitest, e2e
**Search**: `prpm search "testing <framework>"`

### CI/CD Tasks
**Keywords**: ci/cd, github-actions, gitlab-ci, deploy, workflow
**Search**: `prpm search "deployment <platform>"`

### Framework Tasks
**Keywords**: react, vue, angular, next.js, express, django
**Search**: `prpm search "<framework> best-practices"`

## Search Commands

```bash
# Basic search
prpm search "keyword1 keyword2"

# author filter
prpm search --author "prpm"

# Type filter
prpm search --format claude "infrastructure"

# Sub Type filter
prpm search --format claude --subtype skill "infrastructure"

# Limit results
prpm search "github actions" --limit 5

# Sort by downloads
prpm search "testing" --sort downloads
```

## Best Practices

1. **Be Proactive**: Search before starting complex tasks
2. **Verify Quality**: Check download counts and official status
3. **Ask Permission**: Always get user approval before installing
4. **Apply Knowledge**: Immediately use installed package patterns
5. **Track Helpfulness**: Note which packages were useful

## Meta-Dogfooding

Recognize packages PRPM used to build itself:
- `@prpm/pulumi-infrastructure` → PRPM's own infrastructure (74% cost savings)
- `@sanjeed5/github-actions` → PRPM's workflow validation
- Testing packages → PRPM's E2E test patterns

**Benefit**: Users get the same expertise that built PRPM.

## Privacy

- ✅ All searches are local
- ✅ No data sent to PRPM for searches
- ✅ Download tracking only on install
- ✅ No personal data collected

Remember: Self-improvement through package discovery makes Claude more capable for each specific task domain.

Overview

This skill automatically discovers and recommends PRPM expertise packages to boost Claude's capabilities for infrastructure, testing, deployment, or framework-specific tasks. It detects relevant keywords in a user request, searches the PRPM registry, and suggests the best packages to install. With user approval it installs and loads package knowledge to apply immediately to the current task.

How this skill works

The skill analyzes the user prompt for domain keywords (e.g., aws, jest, github-actions, react) and runs a targeted prpm search using those terms. It ranks results by confidence (official, featured, download count, verified author), presents the top candidates, and asks for installation approval. On approval it installs the selected package as Claude, loads its knowledge, and applies package-specific patterns or recommendations to the task.

When to use it

  • Starting infrastructure work (Pulumi, Terraform, Kubernetes, Docker, cloud providers)
  • Setting up or troubleshooting testing (Playwright, Jest, Cypress, Vitest, E2E)
  • Designing or fixing CI/CD workflows (GitHub Actions, GitLab CI, deployment pipelines)
  • Working in specific frameworks or stacks (React, Next.js, Express, Django, Fastify)
  • When you want automated, domain-specific expertise suggestions before big changes

Best practices

  • Run the search proactively at the start of complex tasks to surface relevant expertise
  • Prioritize official and high-download packages for automatic suggestions
  • Always ask the user for permission before installing any package
  • Verify package quality by author, downloads, and non-deprecation status
  • Apply installed package patterns immediately and log which packages were helpful

Example use cases

  • User asks to provision AWS resources with Pulumi — skill finds an official Pulumi package and offers to install it for best-practice patterns
  • Setting up Playwright tests — skill searches testing packages, suggests a high-confidence test harness, installs, and adapts test templates
  • Creating a GitHub Actions workflow — skill finds featured workflow packages and proposes installation to validate or generate CI configuration
  • Migrating a React app to Next.js — skill locates framework best-practice packages and applies recommended folder structure and build optimizations
  • Debugging Dockerized deployment — skill suggests community or official packages that specialize in container patterns and deployment checks

FAQ

Will searches send my code or data to PRPM?

No. Searches are local and do not send your code or personal data to PRPM. Only install actions download packages and those downloads are tracked.

Which packages are auto-suggested without asking?

High-confidence packages (official @prpm/*, featured, verified authors, and high-download items) are auto-suggested but the skill still requests user approval before installation.