Jordan Forrest

Multi-perspective debate for complex decisions. Use when: architectural decisions, design tradeoffs, creative blocks, philosophical questions, feature prioritization, or any problem that benefits from examining multiple angles. Spins up 8 distinct reasoning perspectives plus a chairperson to find what a single viewpoint misses.

Capture decision reasoning for future reference. Use when: making architectural decisions, choosing between options, recording why something was done a certain way, or any time "why did we do it this way?" might come up later. Creates a queryable decision log with full reasoning context.

Project onboarding and CLAUDE.md generation. Use when: starting work on a new codebase, setting up a project for the first time, creating or updating a project CLAUDE.md, generating module summaries, or when opening a project with no CLAUDE.md file. Forges a complete project knowledge base so Claude understands the codebase from day one.

INVOKE THIS SKILL when: making AI-generated images interactive, mapping clickable zones onto generated artwork, warping HTML content onto perspective surfaces in images, defining freeform polygon hotspots, creating hover/click states for elements in AI art, or performing surgical edits on specific regions of generated images. Contains four original techniques: CSI, IQM, HQW, and ADT.

Force counterarguments to your own recommendations. Use when: you've just made a recommendation and want to stress-test it, before committing to an approach, when you suspect confirmation bias, or any time "what am I missing?" needs answering. A cognitive debiasing tool that challenges your own thinking.

Cross-platform desktop notifications from Claude Code. Use when: a long task completes, you need to alert the user, asking a choice via toast buttons, showing progress, or any time a desktop notification would be helpful. Works on WSL (Windows BurntToast), native Linux (notify-send), and macOS (osascript).

INVOKE THIS SKILL when: generating AI images, editing existing images, writing prompts for Gemini image models, performing surgical inpainting, running multi-pass Sequential Grounding, colour matching composites, or any AI image generation pipeline work. Contains the generator tool, prompt engineering framework, and advanced compositing techniques.

Context transfer between sessions, projects, and machines. Use when: saving work context before switching tasks, resuming from a previous session, carrying context across machines, or any time "where was I?" needs answering. Creates portable context snapshots with unique portal ID codes for instant recall.

Search and retrieve from a persistent knowledge base. Use BEFORE web searches or external research — check what you already know first. Use when: looking up previously researched topics, finding API references, checking what past sessions discovered, or any time you need information that might already be in the knowledge base.

Deep technical research that persists. Use when: exploring new technologies, investigating frameworks, comparative analysis of tools, understanding complex systems, or any research task that should be saved for future reference. Invokes Claude's built-in research agent and auto-saves results to a knowledge base for retrieval across sessions.

INVOKE THIS SKILL when: reviewing AI-generated code, understanding unfamiliar codebases, visualizing code logic as flow diagrams, explaining code to non-technical stakeholders, identifying security risks in code, reviewing diffs visually, or when users need to understand code they didn't write. Generates interactive visual code comprehension pages.

INVOKE THIS SKILL when: visualizing regex patterns, debugging regular expressions, explaining regex to users, building regex from natural language, testing regex patterns interactively, or when railroad diagrams would help understand complex patterns. Generates animated railroad diagrams in the browser with live testing.

Break out of conventional thinking. Use when: brainstorming feels predictable, standard approaches have failed, creative challenges need unconventional solutions, or when exploring radical alternatives. Invokes Claude's built-in tail-sampler agent to explore low-probability solution spaces that standard reasoning avoids.

Load this skill at the start of coding sessions. Contains non-negotiable coding standards, the 11 Critical Rules, and quality expectations. Use when: writing code, reviewing code, debugging, making architectural decisions, or refactoring. Enforces production-grade discipline in every line.