What should your AI get better at?
Pick where you work with AI and see which skills and prompts to install first.
Get my skill picksor browse all 44 resources
Custom Instructions for a Non-Technical Builder
Have your assistant handle accessible steps directly, explain changes in plain language, and give clear click-by-click steps when an action needs you.
Custom instructionsStarterLearn Git and GitHub While Your AI Works
Your assistant explains each Git and GitHub step in plain words as it does your work, defines each new term, and stops to ask before anything hard to undo.
SkillStarter
Build and Maintain a PARA Second Brain
Build a source-connected knowledge system with project briefs, useful retrieval, a working capture routine, and a clear way to maintain it.
SkillStarter
Find Use Cases Based on What You Know About Me
Find where AI could save meaningful time in your recurring work, then try the most promising opportunity with a ready-to-paste starter prompt.
PromptStarter
Single Source of Truth: Shared Instructions for Your AI Tools
Organize your AI instructions by domain, separate global guidance from project requirements, and check that each tool follows the right current files.
SkillPracticedStartup Audit: Reduce Context Bloat
Find what your AI loads before you give it a task, even when you just say hi, and reduce the clutter while preserving necessary instructions.
SkillPracticedRouting Audit: Load the Right Instructions
Check that important instructions load when they apply and stay out when they do not. Find false positives, false negatives, and rules that arrive too late.
SkillAdvancedSimple - Update Skills, Memories, and Context for New Models
Improve context for your current model by replacing recurring causes. Get copy-ready updates and a clear HTML audit.
PromptStarterLearn from AI Mistakes
Find the decisions and workflow defaults behind repeated mistakes, then replace their causes while preserving your requirements.
SkillPracticedLearn from What Went Well
Learn which decisions made your work useful, then preserve their benefits without copying incidental wording, layouts, or tools.
SkillPracticedFix a Recurring Problem from Its History
Use earlier attempts to repair one recurring problem and replace the workflow that keeps producing it.
SkillPracticedThorough - Context Hygiene With New Model Releases
Repair obsolete advice and conflicting workflows for your current model, with exact changes and a clear HTML audit.
SkillStarterAudit and Maintain Your AI Workflows
Inventory your skills, instruction files, agents, and scheduled jobs with their purpose, triggers, and recent output, test the important ones on past tasks, and decide which to keep, revise, combine, or retire.
SkillPracticed
Comprehensive Security Hardening and Audit
Secure your computer, apps, and accounts, including code projects when present. Get verified fixes, before-and-after ratings, and clear recommended actions for remaining gaps.
SkillPracticedAnalyze Mozilla HTTP Observatory Security Findings
Scan a public production site, explain each HTTP security finding, and plan compatible header fixes that preserve working user journeys.
PromptAdvancedSet Up and Review Access for People and AI Agents
Map which people and AI agents can read, draft, send, change, or delete in each business account, set roles and connection scopes to match, and test that the denied actions are blocked.
SkillPracticed
Research Best Practices
Research guidance for any task, examine evidence and criticism, and apply practices that fit your goals and circumstances.
SkillPracticedBuild Trustworthy Business Reporting
Define each metric's calculation, period, and included records, reconcile totals across the business systems and source records your figures come from, and build a report that shows each figure's source, calculation, and missing data.
SkillPracticed
Anti-AI Slop Writing
Applies Tom's writing criteria and exact bans to plan, draft, lint, and review your writing, bringing its style closer to Tom's preferences.
SkillPracticedWrite in Your Own Voice
Drafts and revises writing from your own drafts, examples, and instructions so it sounds like you or your brand, and maintains a voice guide when the same kind of work recurs.
SkillPracticed
Reduce AI Induced Cognitive Load
Make writing, interfaces, and learning experiences easier to understand and use while preserving information, depth, functionality, and quality.
SkillStarterThree Design Concepts
Explore three distinct design directions as runnable prototypes, with real content, responsive layouts, and a clear choice between them.
SkillPracticedUI Masterpiece Simple
Build refined, responsive UI from a live route, screenshot, or accepted mockup, then verify its design and interactions.
SkillAdvancedAnti-AI Slop Design That Fits Your Product
Derive design principles from your product's accepted screens and design system, plan each page's hierarchy and states, build with its existing components, then test the rendered pages and run accessibility and style checks.
SkillPracticed
Graph Engineering Workflow Creator
Create a coherent workflow, group compatible work into shared calls, and keep each result accountable, with an editable graph backed by portable files.
SkillAdvancedBuild a Proactive Recurring Workflow
Run a recurring task once and save its output, then schedule it so each run compares new results with stored history, flags changes and open actions, skips duplicate alerts on retries, and reports failed runs.
SkillPracticed
Better Compaction Handoff Prompt
Carry the goal, decisions, progress, and next action into a new chat without inventing missing history.
PromptStarterAudit Claude Code Token Use Without Reducing Quality
Find avoidable token consumption in your recent Claude Code work. Get evidence-backed proposals that preserve quality, completeness, and reliability.
SkillPracticedAtomic Commits
Turn a mixed working tree into the smallest truthful set of cohesive commits without sweeping unrelated work into the history.
SkillPracticedBetter Coding Flow - RPIVR
Research, Plan, Implement, Verify, Refactor. Build features with clear responsibilities, safe renames, and behavior checks, and keep project guidance accurate as requirements change.
SkillAdvancedRebuild an App Without Losing Features
Extract what an app or feature must do, assess its data, logic, and UI, then guide a rebuild that accounts for every capability.
SkillPracticedReadability-First Refactoring
Find and fix unclear names, functions, components, modules, and folders in React and TypeScript without changing observable behavior.
SkillAdvancedSetup Codex Plugin to Review Claude's Output
Install Codex as a Claude Code reviewer and verify a completed manual review. Add automatic reviews when you choose.
PromptPracticedCreate a Plan for Another Coding Agent
Prepare a complete plan another coding agent can follow, with the decisions, files, and checks it needs.
PromptAdvanced
Fix Bugs and Prevent Recurrence
Find the responsible software and workflow causes, fix them, and verify the result while preserving valid requirements.
SkillPracticed
Explore and Build Realtime Features with Pusher Channels
Find useful live updates and collaboration features for your app, then set up Pusher Channels with private access, saved data, and recovery after disconnects.
SkillPracticedSet Up Vercel Web Analytics and Speed Insights
Link the right Vercel project, add both official tracking packages, and verify that production traffic and real-user speed data can be collected.
PromptPracticedAnalyze Vercel Traffic and Real-User Speed Data
Find the routes users rely on, compare their real-user Web Vitals, and turn the strongest evidence into a prioritized improvement plan.
PromptAdvancedSet Up Supabase CLI and Database Advisors
Install the supported Supabase CLI, link the correct project, and establish read-only access to database linting and advisor evidence.
PromptPracticedAnalyze Supabase Security and Performance Advisor Findings
Translate Supabase Advisor findings into verified risks, context-dependent warnings, safe migrations, and production-ready checks.
PromptAdvancedSet Up Repeatable Lighthouse CLI Audits
Install Lighthouse with the project, create repeatable mobile and desktop commands, and verify JSON and HTML reports on a real page.
PromptPracticedAnalyze Lighthouse Reports for High-Traffic Pages
Audit the pages real users depend on, separate repeatable findings from run noise, and prioritize fixes without flattening the site's experience.
PromptAdvancedSet Up Sentry Error Monitoring with Production-Only Alerts
Install Sentry and its command-line tool, keep development noise out, preserve intentional staging, and verify production alerts when the app is ready.
PromptPracticedFix Production Web App Bugs Reported by Sentry
Investigate a real production issue, prove its root cause, make the smallest safe fix, and verify the new release without hiding the error.
PromptAdvanced
