Skip to content

jeremylongshore/tons-of-skills-marketplace / plugins/examples/pi-pathfinder/skills/skill-adapter

skill-adapter

Verified

Execute analyzes existing plugins to extract their capabilities, then adapts and applies those skills to the current task. Acts as a universal skill chameleon that learns from other plugins. Activates when you request "skill adapter" functionality. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

assets/plugin_selection_rules.yaml

View on GitHub
# plugin_selection_rules.yaml
# Configuration file for PI Pathfinder plugin selection logic.

# Global settings for plugin selection behavior.
global:
  # Default preference for prioritizing plugins: "speed", "accuracy", "cost"
  default_priority: "accuracy"
  # Maximum number of plugins to consider for a given task.
  max_plugins_considered: 10
  # Minimum relevance score for a plugin to be considered. (0.0 - 1.0)
  minimum_relevance_score: 0.2
  # Enable/Disable verbose logging for debugging.
  verbose_logging: false

# Rules for selecting plugins based on keywords and task descriptions.
keyword_rules:
  # Define keywords and their associated plugin preferences.
  # The higher the weight, the more preferred the plugin is for that keyword.
  - keywords: ["image", "generate", "picture", "visual"]
    plugin_preferences:
      "DALL-E": 0.9  # Example: Prefer DALL-E for image generation
      "Stable Diffusion": 0.8
      "example-value_IMAGE_PLUGIN": 0.5
  - keywords: ["translate", "language", "multilingual"]
    plugin_preferences:
      "Google Translate": 0.95
      "DeepL Translator": 0.9
      "example-value_TRANSLATION_PLUGIN": 0.6
  - keywords: ["code", "programming", "algorithm", "debug"]
    plugin_preferences:
      "Code Interpreter": 0.9
      "GitHub Copilot": 0.85
      "example-value_CODE_PLUGIN": 0.7
  - keywords: ["data analysis", "statistics", "spreadsheet"]
    plugin_preferences:
      "Wolfram Alpha": 0.9
      "Excel Online": 0.8
      "example-value_DATA_PLUGIN": 0.6

# Rules for selecting plugins based on their stated capabilities.
capability_rules:
  # Define capability patterns and their associated plugin preferences.
  # These rules are based on the plugin's description and advertised skills.
  - capability_pattern: "Generates realistic images from text prompts."
    plugin_preferences:
      "DALL-E": 1.0
      "Stable Diffusion": 0.9
  - capability_pattern: "Translates text between multiple languages."
    plugin_preferences:
      "Google Translate": 1.0
      "DeepL Translator": 0.95
  - capability_pattern: "Executes code and analyzes data."
    plugin_preferences:
      "Code Interpreter": 1.0
      "Wolfram Alpha": 0.8

# Rules for handling user preferences.
user_preferences:
  # Default user preferences (can be overridden by user-specific settings).
  defaults:
    priority: "accuracy"  # Default priority: "speed", "accuracy", "cost"
    preferred_plugins: [] # List of plugins the user prefers (e.g., ["DALL-E", "Google Translate"])
    excluded_plugins: []  # List of plugins the user wants to avoid (e.g., ["Expensive Plugin"])

  # Example: User-specific preferences (loaded from a user profile, for example).
  user_id_123:
    priority: "speed"
    preferred_plugins: ["Google Translate"]
    excluded_plugins: ["example-value_EXPENSIVE_PLUGIN"]

# Fallback plugin to use if no other plugin matches the criteria.
fallback_plugin: "Web Search"

# Advanced configuration (for expert users only).
advanced:
  # Weighting factors for combining different rule types.
  keyword_weight: 0.6
  capability_weight: 0.4
  user_preference_weight: 0.2

  # Threshold for considering a plugin "suitable" after applying all rules.
  suitability_threshold: 0.7

  # Plugin specific configurations (example).
  plugin_configurations:
    "DALL-E":
      api_key: "example-value_DALL_E_API_KEY"
      image_size: "1024x1024"
    "Google Translate":
      target_language: "en" # Default target language
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: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated 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: 323kUpdated Claude CodeCodexVerifiedInstall