software designer
Pete Petrash is a software designer whose most popular skills help AI agents cut unnecessary interface copy, such as redundant captions, pre-emptive hints and leftover warnings, and produce before-and-after screenshot comparisons for GitHub pull requests. His other skills cover running disposable feasibility spikes, conducting alignment interviews before non-trivial tasks, auditing Claude Code sessions for workflow gains, formally verifying architectural constraints in a codebase, and producing cited deep research.
Claude Code Setup
20 skills · 49 stars · MIT
Calldiff Call-graph evidence from git via the calldiff CLI: which functions reach a symbol, and how a chan…
Catch Up Give the human a fast, plain-English catch-up on what changed in the project: what the agents did…
Claude Code Audit Forensic audit of the user's recent Claude Code sessions to surface step-change workflow improvem…
Clean Copy Cut interface copy that should not exist.
Code Comments Write clear, plain-spoken code comments and documentation that lives alongside the code.
Deep Research Investigate a question that requires sustained research across sources and produce cited findings.
Discernment Nudge Suggest a few specific follow-up questions when consequential advice depends on unresolved assump…
Exhaustive Systems Analysis Perform evidence-driven, multi-subsystem audits of real codebases to find correctness bugs, race…
Frame Check Check whether the stated problem is the right problem before work commits to it.
Herdr Names Rename Herdr tabs, panes, and agents so each sidebar entry says in a few words what that session…
Latent Potential First-principles, team-of-experts assessment of a software project that surfaces latent potential…
Plain Restate dense text in plain language.
Pr Description Write or update a GitHub PR description as a short, skimmable list of key points grounded in the…
Pr Screenshot Comparison Create clear, polished before-and-after screenshots from the actual running product for a GitHub…
Pr Self Review Draft explanatory author notes for the user's own PR or local diff.
React Change Review Review a React or TypeScript UI diff for concrete behavior, accessibility, and performance risks.
Refine Prose Refine prose so it says what the writer means to a specific reader: cut the text that should not…
Spike Run a disposable experiment to resolve a specific feasibility question.
Vignette Todo Run Run a batch of Vignette TODO items as a multi-agent worktree run.
Write Goal Turn the prompt supplied with this skill into a concise, auditable Codex Goal or explain why a Go…
Agent Skills
46 skills · 10 stars
Aesthetic Guide Research a UI design aesthetic and produce exhaustive, implementation-ready design guidelines for…
Agent Changelog Compile an agent-optimized changelog by cross-referencing git history with plans and documentation.
Agent Telemetry Make application behavior visible to coding agents by exposing structured logs and telemetry.
Agentic Docs Write clear, plain-spoken code comments and documentation that lives alongside the code.
Architectural Refactor Execute architectural refactoring from an assessment document with deterministic, chunked operati…
Architecture Scaffold Build a compilable type-level skeleton from a high-level architecture spec before writing any imp…
Autonomous Agent Readiness Assess a codebase's readiness for autonomous agent development and provide tailored recommendations.
Blog Drafter Interview-driven blog post drafting for technical product audiences.
Capture Learning Analyze recent conversation context and capture learnings to project knowledge files (for project…
Checkpoint Meta-cognitive decision support that analyzes current context and surfaces intelligent next-step…
Codebase Study Guide Generate a pedagogically-grounded study guide for learning an unfamiliar codebase.
Data Sleuth Identify non-obvious signals, hidden patterns, and clever correlations in datasets using investig…
De Slop Remove LLM-isms and AI writing patterns from text.
Dead Code Sweep This skill should be used when cleaning up codebases that have accumulated dead code, redundant i…
Deep Research Conduct exhaustive, citation-rich research on any topic using all available tools: web search, br…
Deep Work Structured development workflow that separates research, planning, and implementation into distin…
Docs Changelog Write changelog entries for open source documentation sites using Keep a Changelog format.
Exhaustive Systems Analysis Perform comprehensive, deep analysis of a system and its subsystems to identify bugs, race condit…
Explainer Visuals Create high-quality animated explainer visuals for essays and blog posts.
Explanatory Playground Build interactive debugging interfaces that reveal internal system behavior.
Fixer Cold, methodical diagnostician for when you're stuck in agent-assisted app development.
Formal Verify Continuous formal verification of architectural constraints and code quality.
Handoff Generate a smart bootstrap prompt to continue the current conversation in a fresh session.
Hierarchical Matching Systems Expertise in architecting, implementing, reviewing, and debugging hierarchical matching systems.
Interaction Design Design intuitive, meaningful interactions grounded in user goals and cognitive principles.
Interactive Study Guide Transform a codebase study guide into a polished interactive web experience.
Kickoff Conduct a thorough alignment interview to deeply understand a task before starting work.
Literate Guide Create a narrative guide to a codebase or feature in the style of Knuth's Literate Programming —…
Macos App Design Use when designing or building native macOS applications with SwiftUI or AppKit.
Manual Testing Guide users step-by-step through manually testing whatever is currently being worked on.
Model First Reasoning Apply Model-First Reasoning (MFR) to code generation tasks.
Multi Model Meta Analysis Synthesize outputs from multiple AI models into a comprehensive, verified assessment.
Optimize Agent Docs Build a retrieval-optimized knowledge layer over agent documentation in dotfiles (.claude, .codex…
Posthog Analytics Product analytics expert using PostHog MCP.
Process Hunter CAVEMAN HUNT BAD PROCESS!
Proposal Review Facilitate methodical review of proposals (technical designs, product specs, feature requests).
Record Todos Enter todo recording mode to capture ideas without acting on them.
Research Prompt Craft a high-quality prompt for a deep research agent (like ChatGPT Deep Research) through adapti…
Review Package Create a self-contained review package of current work for external review by another AI model or…
Rust Robust Rust patterns for file-backed data, parsing, persistence, FFI boundaries, and system integ…
Seam Ripper Ruthlessly analyze architectural seams—the interfaces, boundaries, and contracts between system c…
Simplicity Audit First-principles simplification analysis for codebases.
Tuning Panel Create visual parameter tuning panels for iterative adjustment of animations, layouts, colors, ty…
Typography Apply professional typography principles to create readable, hierarchical, and aesthetically refi…
Unix Macos Engineer Expert Unix and macOS systems engineer for shell scripting, system administration, command-line t…
Write Goal Compile a plain-language task into a concise, auditable Codex or Claude Code `/goal`, or explain…