Claude Skills by petekp

Give the human a fast, plain-English catch-up on what changed in the project: what the agents did, why, and what decisions need their input. Use this whenever the user asks to "catch me up", "what changed", "where are we", "recap", "brief me", "give me the rundown", "what did you do", "summarize the session", "fill me in", or otherwise signals they have been away and want to get back up to speed quickly. Built for someone steering several agent-driven projects at once who does not read the co...

Analyze a provided resource through a Circuit lens. Use when the user provides or points to an article, pasted conversation, X thread, workflow example, GitHub repo, local codebase, product page, paper, or other outside reference and asks what Circuit can learn from it, whether it suggests a possible Circuit flow, whether Circuit can support the workflow today, what product or block changes would be needed, or whether the analysis should be added to Circuit's ideas or flow backlog.

Operate Circuit, the flow engine that runs coding work as structured, evidence-backed flows (Fix, Build, Explore, Review, Prototype). Use this skill at the START of any substantive coding task in a project where Circuit is installed: fixing a bug, building a feature, refactoring, reviewing a diff or PR, investigating a question, or prototyping. Also use it whenever the user mentions Circuit, flows, runs, checkpoints, run folders, the power dial or process override, connectors, or asks to crea...

Audit and fix animation performance issues including layout thrashing, compositor properties, scroll-linked motion, and blur effects. Use when animations stutter, transitions jank, or reviewing CSS/JS animation performance.

First-principles, team-of-experts assessment of a software project that surfaces latent potential; underexploited assets, a sharper north star, missing high-leverage capabilities, better framing and messaging. Produces a prioritized, evidence-grounded report with cheap probes, a reframe candidate, a stop-doing list, and an honest skeptic's case. Use whenever the user wants fresh eyes on a project they have built: "what am I sitting on", "what could this become", "is there a bigger play here",...

Restate dense, jargon-heavy, or hard-to-follow content in plain language so the user actually understands it. Use whenever the user invokes /plain, says something like "explain that more simply", "I don't follow", "what does that actually mean", "in plain English", "break that down", "ELI5", or pastes/points at text they find dense. With no arguments, restate your own previous response. With arguments (pasted text, a file path, or "the part about X"), restate that instead. Trigger even on inf...

Create clear, polished before-and-after screenshots for a GitHub pull request. Use when a UI change needs visual proof: capture matching states, crop to the relevant UI, stitch and caption one comparison image, attach it natively to the PR, and keep the image out of the repository.

Draft short, plainspoken notes in the author's voice that help reviewers understand non-obvious choices, boundaries, and preserved behavior in the author's own pull request or local diff. Use when the user asks to self-review, annotate, or add reviewer context to their PR or changes. Draft locally when no PR exists, and post approved notes as one GitHub review when a PR does exist. Do not use for reviewing someone else's PR, writing code comments, explaining code generally, or drafting a PR d...

Run a spike — a timeboxed, deliberately disposable experiment whose only job is to answer the unknowns in a task before anyone commits to a real implementation. Use whenever the user says "spike", "spike this", "let's spike it", "throwaway", "proof of concept", "POC", "quick and dirty", "just to see if it works", "prototype it", "tracer bullet", or "hack something together". Also use — even without those words — when the user is weighing whether an approach is viable, asks "would this even wo...

Turn the prompt supplied with this skill into a concise, auditable Codex Goal or explain why a Goal is not the right fit. Use when the user asks to draft, formulate, rewrite, tighten, or create a `/goal` from a plain-language task, especially for multi-step work that needs a durable objective, evidence-based completion, constraints, iteration policy, and a default adversarial review loop.

Explore and compare architectural options before committing to a large technical direction. Use when the user wants to evaluate different architectures, compare approaches, choose between competing designs, rethink a subsystem, or understand tradeoffs before a major refactor or migration. Also use for prompts like "explore the architecture", "what are our options", "compare approaches", "what design should we choose", "audit and recommend an improved architecture", or "help me think through a...

Build a compilable type-level skeleton from a high-level architecture spec before writing any implementation logic. Use when you have an architectural assessment, design doc, or restructuring plan and need to prove the new architecture is sound before migrating code. Also use when asked to "scaffold the new architecture", "create type stubs", "build the shell", "flesh out this spec", "skeleton the modules", or any request to turn architectural intent into verified structure. This skill follow...

Slice-based, evidence-driven framework for explicit codebase migrations and convergence programs. Use when the user is moving from a named source to a named target, running a multi-session standardization effort across a codebase, consolidating parallel implementations into one target architecture, or asking for a migration playbook with slices, ratchets, handoffs, and release closeout. Do not trigger for normal refactors, routine cleanup, or one-off architecture improvements that are not fra...

Comprehensively manually test the Circuit plugin's user-facing surface in either Claude Code or Codex. Use this skill whenever the user asks to "manually test Circuit", "QA the Circuit plugin", "exercise the Circuit surface", "run the Circuit checklist", "smoke test Circuit", "find regressions in Circuit", "test the Claude Circuit plugin", "test the Codex Circuit plugin", or when preparing a Circuit release for marketplace publication. Argument is the host package to test — `claude` or `codex...

Install session-level guardrails when the user hands off to autonomous overnight execution. Fires when the first user prompt contains "going to bed", "headed to sleep", "full autonomy", "overnight", "continue as you were", or similar handoff-to-autonomy language. Enforces commit-per-slice, halt-on-3-consecutive-errors, max-wall-time cap, and a wake-time summary block. Exists because audited overnight sessions showed 348 Bash calls and 9 tool errors with no structural brake — the user explicit...

Render a 4-line human orientation card (Goal / Last commit / Next / Blocker) as the FIRST visible assistant output on any resumed session. Fires when the first user prompt is "resume", "resume handoff", "continue from handoff", or any /circuit:handoff resume invocation. Exists because the continuity system stores state perfectly for machines but leaves the human disoriented after breaks — at least two 2026-04 sessions ended with the user explicitly saying "I've forgotten what we're doing". Th...

Enforces one-subtask-per-session discipline for long Claude Code workflows. Use at the start of any prompt that begins a new subtask, or when the current session has already exceeded 60 tool uses or 45 minutes. Proposes a handoff + new session instead of continuing to pile work into the current thread. Especially valuable for users running Circuit or Codex workflows who tend to accumulate 100+ tool uses per session and then pay heavy re-entry cost on the next resume.

Reviews ~/.claude/skills/ against the last N days of actual session transcripts to identify skills that never triggered and are paying context-noise cost for no value. Produces a disable/archive recommendation per skill. Use when the user has 30+ skills installed and wants to reduce trigger-time noise, or when the user asks to "clean up my skills", "find unused skills", or "which skills never fire".

Codify the user's standard overnight-autonomy contract so it doesn't have to be retyped every session. Triggers on phrases that signal "I'm leaving Claude running while I sleep": "i'm going to sleep", "i'm headed to bed", "i have to go back to sleep", "drive this forward overnight", "go full autonomy", "keep going until morning", "autonomously follow through", or any combination including "claude" + "sleep/bed/morning". Establishes the overnight contract, writes an autonomy manifest to the pr...

Produce a 5-line situational summary on demand or whenever the user is resuming a session, catching up, or lost. Triggers on "resume", "where are we", "what were we doing", "status", "remind me", "catch me up", or immediately on SessionStart:resume. Replaces Claude's default behavior of dumping the entire saved continuity record back at the user — instead, always outputs exactly 5 lines in a fixed shape so the user can reorient in under a second. Pairs with circuit:handoff continuity records ...

Forensic audit of the user's recent Claude Code sessions to surface step-change workflow improvements — not marginal ones. Use when the user asks to "audit my Claude Code sessions", "analyze how I use Claude Code", "find patterns in my usage", "improve my Claude Code workflow", "review my sessions", "find leverage in my setup", or wants to understand where their Claude Code setup is leaking time. Samples dozens of real transcripts, extracts quantitative signal via scripts, uses parallel subag...

Clean Architecture principles and best practices from Robert C. Martin's book. This skill should be used when designing software systems, reviewing code structure, or refactoring applications to achieve better separation of concerns. Triggers on tasks involving layers, boundaries, dependency direction, entities, use cases, or system architecture.

MANDATORY handoff to the local Codex CLI. Triggers when (a) the user's message begins with `/codex` as a command, or (b) the user issues an explicit handoff directive like "hand this to codex", "run this through codex", "ask codex", or "have codex do X". On trigger, pipe the user's prompt verbatim to `codex exec` and return Codex's final message verbatim. Treat this like a shell alias the user is executing through you. Do NOT interpret the task, inspect files, gather context, attempt the work...

This skill should be used when cleaning up codebases that have accumulated dead code, redundant implementations, and orphaned artifacts — especially codebases maintained by coding agents. Triggers on "find dead code", "clean up unused code", "remove redundant code", "prune this codebase", "dead code sweep", "code cleanup", or when a codebase has gone through multiple agent-driven refactors and likely contains overlooked remnants. Systematically identifies cruft, categorizes findings, and remo...

Query DeepWiki for repository documentation and structure. Use to understand open source projects, find API docs, and explore codebases.

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

Continuous formal verification of architectural constraints and code quality. Use when asked to verify, audit, or validate codebase integrity. Runs automatically via hooks on every edit (structural) and pre-commit (full). Catches ownership violations, boundary crossings, state machine bugs, and code smells that grep ratchets miss. Triggers: "verify", "formal verify", "check architecture", "audit code quality", "run verification", "/verify", "/verify --bootstrap", "/verify --grade".

Route `/gemini ...` requests to the Cursor headless CLI for one-shot autonomous execution. Use when the user explicitly invokes `/gemini` or asks to hand a task off to Cursor agent. Preserves the prompt verbatim, runs in headless print mode, and returns Cursor's output.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more AI-navigable.

Create a narrative guide to a codebase or feature in the style of Knuth's Literate Programming — code and prose interwoven as a single essay, ordered for human understanding rather than compiler needs. Use when the user asks to 'explain this codebase as a story', 'write a literate guide', 'create a narrative walkthrough', 'tell the story of this code', 'Knuth-style documentation', 'weave a guide for this feature', or when they want deep, readable documentation that treats the program as liter...

Review recent React, Next.js, or TypeScript UI code changes for hardening before merge or commit. Use when asked to review recent React code changes, audit a React diff, harden a feature, check a PR or branch for React issues, or produce a stack-ranked list of nonredundant findings and a recommended fix plan using react-doctor, Vercel React best practices, Vercel composition patterns, and React useEffect guidance.

Ruthlessly analyze architectural seams—the interfaces, boundaries, and contracts between system components—to expose coupling problems, abstraction leaks, and design failures. Use when asked to review architecture, analyze coupling, find interface problems, improve module boundaries, audit dependencies, or redesign system structure. Produces uncompromising redesign proposals that prioritize correctness over backwards compatibility.

Manage, audit, and maintain your skill ecosystem. Use when the user asks to "check my skills", "audit skills", "find duplicate skills", "which skills am I using", "prune unused skills", "are my skills synced", "check for skill updates", "skill report", "skill health", or mentions skill maintenance, cleanup, or organization.

Build, refactor, review, and debug native Apple-platform software in Swift. Use when working on `.swift` files, SwiftUI views, Observation-based state, `@Bindable` and binding flow, SwiftData-backed UI, scenes and windows, search/navigation structures, UIKit/AppKit interop, Liquid Glass adoption, macOS-native UX, or SwiftUI performance/accessibility. Trigger on requests to create or polish iOS, iPadOS, macOS, or visionOS features; clean up SwiftUI view structure; diagnose jank or invalidation...

Test-driven development for features, bug fixes, regressions, and safe refactors using a failing-test-first workflow. Use when Codex needs to add or change behavior with proof, reproduce a bug in a test, write regression or characterization tests, make a refactor safer, or respond to prompts like "use TDD", "red-green-refactor", "write the test first", "add a regression test", "reproduce this in a test", "prove the fix", "cover this change with tests", or "make this safe to refactor". Prefer ...

Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".

Compile an agent-optimized changelog by cross-referencing git history with plans and documentation. Use when asked to "update changelog", "compile history", "document project evolution", or proactively after major milestones, architectural changes, or when stale/deprecated information is detected that could confuse coding agents.

Guide for assistant-ui library - AI chat UI components. Use when asking about architecture, debugging, or understanding the codebase.

Assess a codebase's readiness for autonomous agent development and provide tailored recommendations. Use when asked to evaluate how well a project supports unattended agent execution, assess development practices for agent autonomy, audit infrastructure for agent reliability, or improve a codebase for autonomous agent workflows. Triggers on requests like "assess this project for agent readiness", "how autonomous-ready is this codebase", "evaluate agent infrastructure", or "improve development...

Interview-driven blog post drafting for technical product audiences. Use when user wants to write a blog post, article, or essay and needs help developing their thesis, structure, and initial draft. Triggers on "write a blog post", "draft an article", "help me write about X", "blog drafter", or when user has a topic they want to turn into written content. Conducts structured interviews using AskUserQuestion to extract the user's unique insights before generating drafts.

This skill should be used when the user asks to "create a bootstrap prompt", "handoff", "save session state", "continue in new session", "create handoff", "session summary for continuation", "bootstrap for fresh session", or wants to capture the current session state for resumption in a new Claude Code session.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.

Analyze recent conversation context and capture learnings to project knowledge files (for project-specific insights) or skills/commands/subagents (for cross-project patterns). Use when the user asks to "capture this learning", "update the docs with this", "remember this for next time", "document this issue", "add this to CLAUDE.md", "save this knowledge", or "update project knowledge". Also triggers after resolving build/setup issues, discovering non-obvious patterns, or completing debugging ...

Meta-cognitive decision support that analyzes current context and surfaces intelligent next-step options to the user. Use this skill when: (1) User explicitly invokes /checkpoint, (2) Significant work has been completed and a checkpoint is valuable, (3) Uncertainty or ambiguity exists about requirements or approach, (4) Task complexity has expanded beyond initial scope, (5) Before finalizing or committing to ensure nothing is missed. This skill pauses execution, assesses the situation holisti...

This skill should be used when the user asks to "create a CLAUDE.md", "write a CLAUDE.md", "set up CLAUDE.md", "configure Claude for this project", "add project instructions for Claude", "initialize Claude context", or mentions needing project-specific Claude instructions.

Critique UI/UX designs for clarity, hierarchy, interaction, accessibility, and craft. Use for design reviews, PR feedback on UI changes, evaluating mockups, checking if a component is ship-ready, or when honest feedback is needed on whether something meets a high bar.

Expert motion and interaction design auditor based on Emil Kowalski, Jakub Krehel, and Jhey Tompkins' techniques. Use when reviewing UI animations, transitions, hover states, or any motion design work. Provides per-designer perspectives with context-aware weighting.

Start development servers with intelligent port management. Use when asked to "start the dev server", "run dev", "start development", "launch the server", "spin up the app", "get this running", "boot the frontend", or any request to run a local development server. Handles port conflicts, detects project type, cleans up stale processes, and opens the browser automatically.

Think expansively and imaginatively without practical constraints. Use when brainstorming ambitious ideas, exploring what's possible, challenging assumptions, envisioning ideal futures, or when the user needs to break out of incremental thinking and imagine boldly.