self-improving
Skill124 starsChanged 8 months agoMITView on GitHub
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
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 33
Use when user request is:
- Distinctive: line 42
Use when request mentions:
- Distinctive: line 150
Keywords: test, playwright, jest, cypress, vitest, e2e
- Distinctive: line 221
Be Proactive: Search before starting complex tasks
- Distinctive: line 222
Verify Quality: Check download counts and official status
- Distinctive: line 223
Ask Permission: Always get user approval before installing
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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
Choose the right search method:
AI-Assisted Search (for vague/broad queries):
prpm ai-search "natural language query"Use when user request is:
- Conceptual or vague (e.g., "help with deployments")
- Describes a problem, not specific tools
- Open-ended exploration
Keyword Search (for specific tools/frameworks):
prpm search "<detected keywords>" --limit 5Use when request mentions:
- Specific technologies (e.g., "pulumi", "react")
- Exact tool names
- Known frameworks
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)
prpm install <package-name> --as claude5. 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 Interactions
Example 1: Specific Technology (Keyword Search)
User: "Help me build Pulumi + Beanstalk infrastructure"
Analysis:
Keywords: Pulumi, Beanstalk, infrastructure (specific tools)
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 taskExample 2: Vague Request (AI-Assisted Search)
User: "I need help with deployments"
Analysis:
Query: Vague, no specific tools mentioned
Search: prpm ai-search "help with deployments"
Found: Multiple relevant packages:
- @prpm/elastic-beanstalk-deployment (Official, 2.1K downloads)
- @sanjeed5/github-actions (Community, 892 downloads)
- @prpm/docker-deployment (Featured, 1.5K downloads)
Response:
"I found several deployment-related packages that might help:
📦 @prpm/elastic-beanstalk-deployment (Official, 2.1K downloads)
- AWS Elastic Beanstalk deployment patterns
📦 @prpm/docker-deployment (Featured, 1.5K downloads)
- Docker containerization and deployment
📦 @sanjeed5/github-actions (Community, 892 downloads)
- GitHub Actions CI/CD workflows
Which deployment platform are you using, or should I install the Elastic Beanstalk one?"
User: "I'm using AWS"
Action:
✅ Installing: prpm install @prpm/elastic-beanstalk-deployment --as claude
✅ Applying AWS deployment best practicesSearch 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
AI-Assisted Search (Semantic Search)
# Natural language queries
prpm ai-search "help me deploy my app to the cloud"
# Problem descriptions
prpm ai-search "I need to improve my code review process"
# Conceptual searches
prpm ai-search "best practices for testing infrastructure"When to use AI search:
- User query is vague or open-ended
- Searching by concept rather than specific tool
- Exploring what's available for a problem domain
- User doesn't know exact package names or tools
Package Search (Keyword Search)
# Basic search
prpm search "keyword1 keyword2"
# Subtype filter (rule, agent, skill, slash-command, prompt)
prpm search "react" --subtype rule
# Limit results
prpm search "github actions" --limit 5
# Sort by downloads
prpm search "testing" --sort downloadsWhen to use keyword search:
- Specific technology names known (pulumi, react, etc.)
- Filtering by package subtype needed
- Need sorting/filtering options
- Exact match searches
Collection Search
# List all collections
prpm collection list
# Search for collections
prpm collection search "frontend"
# Get collection details
prpm collection info essential-dev-agents
# Install a collection (installs all packages in the collection)
prpm install essential-dev-agentsNote: Collections bundle multiple related packages together. Use collections when you need a complete toolkit for a specific domain (e.g., "startup-mvp", "security-review-agents", "essential-dev-agents").
Best Practices
- Be Proactive: Search before starting complex tasks
- Verify Quality: Check download counts and official status
- Ask Permission: Always get user approval before installing
- Apply Knowledge: Immediately use installed package patterns
- 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.
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- JayMeDotDot/jmdd-agent-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository64 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- beanstalk-deployCursor rule
- .cursor/rules/core-principles.mdcCursor rule
- .cursor/rules/creating-agents-md.mdcCursor rule
- .cursor/rules/creating-claude-agents.mdCursor rule
- .cursor/rules/creating-claude-commands.mdCursor rule
- .cursor/rules/creating-claude-hooks.mdCursor rule
- .cursor/rules/creating-continue-packages.mdCursor rule
- .cursor/rules/creating-copilot-packages.mdCursor rule
- .cursor/rules/creating-cursor-commands.mdCursor rule
- .cursor/rules/creating-cursor-rules.mdcCursor rule
- .cursor/rules/creating-kiro-agents.mdcCursor rule
- .cursor/rules/creating-kiro-packages.mdCursor rule
- .cursor/rules/creating-skills.mdcCursor rule
- .cursor/rules/creating-windsurf-packages.mdCursor rule
- .cursor/rules/elastic-beanstalk-deployment.mdCursor rule
- .cursor/rules/format-conversion.mdcCursor rule
- .cursor/rules/github-actions-testing.mdcCursor rule
- .cursor/rules/karen-repo-reviewer.mdcCursor rule
- .cursor/rules/prpm-json-best-practices.mdcCursor rule
- .cursor/rules/self-improve-cursor.mdcCursor rule
- .cursor/rules/testing-patterns.mdcCursor rule
- .cursor/rules/typescript-type-safety.mdcCursor rule
- .cursor/rules/typescript-type-specialist.mdcCursor rule
- creating-agent-skillsSkill
- adding-new-ai-formatSkill
- agent-builderSkill
- aws-beanstalk-expertSkill
- beanstalk-deploySkill
- claude-hook-writerSkill
- creating-agents-mdSkill
- creating-claude-agentsSkill
- creating-claude-commandsSkill
- creating-claude-hooksSkill
- creating-claude-rulesSkill
- creating-continue-packagesSkill
- creating-copilot-packagesSkill
- creating-cursor-commandsSkill
- creating-cursor-rules-skillSkill
- creating-kiro-agentsSkill
- creating-kiro-packagesSkill
- creating-opencode-agentsSkill
- creating-opencode-pluginsSkill
- creating-skillsSkill
- creating-windsurf-packagesSkill
- creating-zed-extensionsSkill
- documentation-standardsSkill
- elastic-beanstalk-deploymentSkill
- github-actions-testingSkill
- human-writingSkill
- integrating-stripe-webhooksSkill
- karen-repo-reviewerSkill
- npm-trusted-publishingSkill
- osgrepSkill
- postgres-migrationsSkill
- prpm-developmentSkill
- prpm-json-best-practicesSkill
- pulumi-troubleshootingSkill
- slash-command-builderSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

