Master Your AI Workflow with our Prompt Library

1. Better Prompts

Make your prompts better before you start. A good prompt means you get the right answer faster. Choose the tool that works best for you and the detail you need.

Optimise LLM Prompts

Provides expert strategies and tactics for optimising Large Language Model prompts, enhancing clarity, relevance, and output quality.

Prompt Optimiser — 4-D Framework

Rebuilds any prompt using the 4-D methodology (Deconstruct, Diagnose, Develop, Deliver): extracts intent, audits clarity gaps, selects the optimal technique (few-shot, chain-of-thought, constraint-based), and outputs a refined prompt with implementation guidance tailored to the target AI platform.

Optimise Prompts

Analyses and refines any given prompt based on clarity, structure, context, and output specifications, providing an improved version and explanation.

Iterative Prompt Co-Engineering

Acts as a dedicated prompt engineer in a conversational refinement loop: each turn produces a revised prompt alongside targeted clarifying questions, continuing until the user confirms the result meets their needs.

2. Writing and Fixing Code

The main part of your work. Use these tools to build new features with tests or to find and fix bugs. Choose the best tool for your task: tests for new features, finding bugs, or quick code for testing ideas.

Test-Driven Development

Instructs the AI to develop code using a strict test-driven workflow, writing integration-style tests against public interfaces before implementing functionality. Use when adding new features or refactoring modules. Expects a feature specification or requirements. Outputs verified code that passes tests at the boundary seam.

Structured Bug Diagnosis

Guides the systematic reproduction, hypothesising, instrumenting, and fixing of complex codebase bugs. Use when encountering hard-to-reproduce, performance-related, or non-deterministic issues. Expects details of the bug symptoms and access to the codebase. Outputs a verified code fix and a regression test, ensuring all temporary debug instrumentation is removed.

Throwaway Code Prototyping

Creates throwaway code to answer specific technical or design questions. Branches into either a terminal state-machine application for logic verification or switchable visual UI variations. Use when exploring unproven state models or layout ideas. Expects a specific question or feature goal. Outputs a minimal, functional prototype isolated from production code.

3. Keep the Context

AI can get confused during long chats. Use these tools to save the main points and start work in a new chat. Pick the tool that fits your style – saving notes inside the chat or in a new file.

Conversation Continuity Checkpoint

Use this when the chat context is full or at the end of the day. It helps you create a dense summary so you can start again in a new chat.

Session Handoff Documentation

Generates a handoff document in the OS temporary directory summarizing the active conversation context, suggestions for subsequent skills, and next steps for a fresh AI session. Use when transitioning tasks or starting a new session. Expects active session history. Outputs a markdown handoff file.

4. Save What You Learn

Save "Gotchas" (small tips) at the end of each chat. When you have many tips, merge them into one list.

High-Fidelity Gotcha Extractor

Use this at the end of a task or session. It helps you capture important technical notes and "traps" so you do not make the same mistakes again.

Technical Knowledge Consolidation Pipeline

Run this sometimes to clean up documentation debt. It helps you merge and sort technical notes into a clear and organized knowledge base.

5. Work and Commits

Use these tools while you work to keep your commits clean and your code safe. Pick the tools that match your project and how much safety you want.

Atomic Conventional Commit Orchestrator

Use this when you finish a logical part of work. It helps you create a clear and atomic commit message to keep the project history easy to read.

Dangerous Git Command Blocker

Sets up a PreToolUse hook configuration that intercepts and blocks dangerous commands (e.g. git push, hard reset, force clean, branch deletion) before execution. Use to prevent accidental data loss in development. Expects git repository access. Outputs a configured hook script in the repository configuration.

Pre-Commit Hook Setup

Configures Git pre-commit hooks using Husky, lint-staged, and Prettier to automatically lint, format, typecheck, and test staged code before commits. Use to enforce code quality standards. Expects node project access. Outputs hook configurations and updated package.json scripts.

6. Release

Create missing files and release the new version of your code.

Automated Changeset Generator & History Auditor

Use this before a release to find changes without documentation. It helps you create changesets that explain the benefits of your work to users.

Automated Release Cycle Orchestrator

Use this when you want to publish a new version. It helps you manage version numbers, clean up changelogs, and create the final release commit safely.