Skip to content

mohitagw15856/pm-claude-skills / plugins/pm-ai-native/skills/prompt-library-builder

prompt-library-builder

Verified

Build a personal library of reusable prompts for the things you ask AI again and again — so you stop rewriting the same request from scratch. Use when asked help me build a prompt library, save my best prompts, I keep writing the same prompts, or organize my AI prompts. Produces a captured set of your recurring AI tasks turned into reusable, parameterized prompt templates, an organization scheme so you can find them, guidance on what makes a prompt reusable (clear role, inputs, output format), and how to store and improve them — turning ad-hoc prompting into a personal toolkit that compounds.

Prompt-Library Builder

If you use AI regularly, you retype variations of the same requests constantly — the email rewriter, the meeting summarizer, the code explainer. A prompt library captures your best versions once, parameterized and organized, so you invoke them instead of reinventing them. This builds yours: identifies your recurring tasks, turns them into reusable templates, and sets up a system to store and improve them — a toolkit that gets more valuable every time you add to it.

What This Skill Produces

  • Your recurring tasks, captured — the AI requests you make repeatedly, identified and listed
  • Reusable prompt templates — each turned into a clean, parameterized template (clear role, the inputs to fill in, and the desired output format) instead of a one-off
  • An organization scheme — a simple way to categorize and find prompts (by task, by domain, by frequency)
  • The reusability principles — what makes a prompt reusable and reliable (specific role, explicit inputs, defined output, examples where helpful)
  • A storage & improvement system — where to keep them (a doc, snippets, a tool) and how to refine each as you use it
  • A starter set — a few of your most-used prompts, templated and ready

Required Inputs

Ask for these if not provided:

  • Your recurring AI tasks — the things you ask AI to do often (or a prompt to help surface them)
  • A few examples — prompts you've written that worked, to templatize
  • Your tools — where you'll store/use them (a notes app, snippet manager, the AI tool itself)
  • Your domains — work, personal, coding, writing (for organizing)

Framework: Capture, Templatize, Organize

  1. Find the repeats. Identify the requests you make again and again — these are the highest-value candidates to templatize.
  2. Templatize for reuse. Turn each into a clean template: a clear role/instruction, the variable inputs to fill in [like this], and the output format you want — so it works every time with just the specifics swapped.
  3. Add what makes it reliable. Specific instructions, an output format, and an example or two where the task is fuzzy — the difference between a prompt that mostly works and one that always does.
  4. Organize for retrieval. A simple scheme (by task type or domain) so you can actually find the right prompt when you need it — a library you can't search is a graveyard.
  5. Store where you'll use it. Match storage to your workflow (a snippet tool, a doc, saved prompts) so invoking one is faster than rewriting.
  6. Improve continuously. Refine each template as you notice what's missing — and add new ones as new repeats emerge. The library compounds.

Output Format

Prompt library: domains [x] · store in [y]

Your recurring tasks: [the repeats, identified]. Templated (starter set)

[Task name]: [role/instruction] · inputs: [fill these] · output: [format]. — reusable. [Task name]: …

What makes them reusable: clear role · explicit [inputs] · defined output · an example where fuzzy. Organize by: [task type / domain] so you can find them. Store in: [snippets / doc / saved prompts] for fast invoking. Improve: refine each as you use it; add new repeats as they emerge.

Quality Checks

  • Identifies the person's genuinely recurring AI tasks
  • Turns them into parameterized, reusable templates (role/inputs/output)
  • Explains what makes a prompt reliably reusable
  • Provides an organization scheme for retrieval
  • Matches storage to the person's workflow
  • Includes a starter set and an improvement loop

Anti-Patterns

  • Saving one-off prompts verbatim with no parameterization.
  • A pile with no organization — can't find anything.
  • Vague templates missing the output format.
  • Storing where it's slower to retrieve than to rewrite.
  • Never refining the templates.

Example Trigger Phrases

  • "Help me build a library of my most-used AI prompts."
  • "I keep rewriting the same prompts — turn them into reusable templates."
  • "Organize my prompts so I can actually find and reuse them."
  • "Templatize this prompt I use all the time."
  • "Set up a personal prompt toolkit."

Run this skill in your browser: https://mohitagw15856.github.io/pm-claude-skills/skill/prompt-library-builder.html

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: 471kUpdated 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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated 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: 322kUpdated Claude CodeCodexVerifiedInstall