Skip to content

jeremylongshore/tons-of-skills-marketplace / plugins/packages/ai-ml-engineering-pack/skills/optimizing-prompts

optimizing-prompts

Unverified

Execute this skill optimizes prompts for large language models (llms) to reduce token usage, lower costs, and improve performance. it analyzes the prompt, identifies areas for simplification and redundancy removal, and rewrites the prompt to be more conci... Use when optimizing performance. Trigger with phrases like 'optimize', 'performance', or 'speed up'.

FileKindSize
SKILL.mdskill md4.1 KB
assets/README.mdmarkdown299 B
assets/example_prompts.mdmarkdown8.4 KB
assets/optimization_report_template.mdmarkdown5.5 KB
assets/prompt_template.jsonconfig2.8 KB
references/README.mdmarkdown65 B
scripts/README.mdmarkdown409 B

assets/prompt_template.json

View on GitHub
{
  "_comment": "Prompt template for the AI/ML Engineering Pack plugin.  This defines the structure and keys for prompt inputs.",
  "template_name": "default_template",
  "description": "A general-purpose prompt template for various AI/ML tasks.",
  "version": "1.0",
  "author": "AI/ML Engineering Pack Team",
  "input_parameters": [
    {
      "name": "task_objective",
      "type": "string",
      "description": "A clear and concise description of the desired task.",
      "required": true,
      "example": "Summarize the provided research paper on transformer architectures."
    },
    {
      "name": "context",
      "type": "string",
      "description": "Relevant information or data needed to complete the task.  This could include documents, code snippets, or data samples.",
      "required": true,
      "example": "Research paper text: ... (insert paper content here)"
    },
    {
      "name": "output_format",
      "type": "string",
      "description": "The desired format for the output.  Specify the structure, data types, and any specific formatting requirements.",
      "required": false,
      "default": "Plain text summary",
      "example": "Bullet points with key findings and their supporting evidence."
    },
    {
      "name": "constraints",
      "type": "string",
      "description": "Any limitations or constraints that should be considered during the task. This is especially important for AI safety.",
      "required": false,
      "example": "Ensure the summary avoids generating any harmful or biased content.  Focus solely on the factual information presented in the paper."
    },
    {
      "name": "ai_safety_guidelines",
      "type": "string",
      "description": "Specific AI safety guidelines to follow. This helps to mitigate potential risks and ensure ethical AI behavior.",
      "required": false,
      "default": "Follow the principles of harmlessness, honesty, and helpfulness.",
      "example": "Avoid generating responses that promote discrimination, violence, or misinformation."
    }
  ],
  "prompt_structure": "You are an AI assistant tasked with {task_objective}. Here is the context: {context}. Please provide the output in the following format: {output_format}. Consider the following constraints: {constraints}. Adhere to these AI safety guidelines: {ai_safety_guidelines}.",
  "example_prompt": {
    "task_objective": "Generate a Python function to calculate the factorial of a number.",
    "context": "The factorial of a number n is the product of all positive integers less than or equal to n.",
    "output_format": "A Python function with appropriate comments and docstrings.",
    "constraints": "The function should handle invalid inputs (e.g., negative numbers) gracefully.",
    "ai_safety_guidelines": "Ensure the code is safe and does not contain any malicious logic."
  }
}
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