Launch an isolated Claude reviewer for the current branch, a specific commit, or uncommitted changes. Uses Claude's agent runtime with worktree isolation so the review has an independent read-only view of the code before findings are reported back.

Soft, rounded 3D-like shapes mimicking malleable clay with playful, puffy elements and colorful surfaces.

Simplicity-focused design with ample whitespace, legible typography, and a limited color palette to reduce visual clutter.

Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments

Write clear, human prose. Strips AI patterns, enforces hard constraints, optionally applies a voice style. Use when writing or editing any prose, when asked to "make it sound human," "remove AI tells," "write clearly," or when producing any content that must not read as AI-generated. Load style references for specific voices (Cowen, Koe, Levine-Berry, Lewis, Pirate Wires, OpenEd, Charlie) or social formats (Trung Phan).

Clerk's UI design system. Use when building interfaces inspired by Clerk's aesthetic - light mode, Inter font, 4px grid.

Command-line interface for Shotcut - A stateful command-line interface for video editing, built on the MLT XML format. Designed for AI ag...

Configuration management patterns including file formats, precedence, environment variables, and XDG directories. Use when implementing configuration systems for CLI applications.

Exports project instructions and knowledge files from the current Claude project. Use when users want to clone, copy, backup, or export a project's configuration and files.

Manage the month-end close process with task sequencing, dependencies, and status tracking. Use when planning the close calendar, tracking close progress, identifying blockers, or sequencing close activities by day.

Cloud infrastructure design and deployment patterns for AWS, Azure, and GCP. Use when designing cloud architectures, implementing IaC with Terraform, optimizing costs, or setting up multi-region deployments.

Self-contained deploy automation — invoke directly, do not decompose. Deploys a Vibes app to Cloudflare Workers via the Deploy API. Use when deploying, publishing, going live, pushing to production, or hosting on the edge.

Designs implementation blueprints for features using exploration findings and architectural best practices (converted from agent)

Writing effective code documentation - API docs, README files, inline comments, and technical guides. Use for documenting codebases, APIs, or writing developer guides.

Use Claude's Code Execution tool to run Python in a sandboxed environment as part of a response — for calculation, data analysis, chart generation, and verification. Covers enabling, file upload, persistence across turns, and limitations. Use this skill when building features that need Claude to actually run code (not just write it), such as data analysis, math verification, or chart creation. Activate when: Claude code execution, Python sandbox, run code tool, data analysis agent, code interpreter, code_execution_20250522.

Explores codebases to find relevant files, trace execution paths, and map architecture with team communication capabilities for collaborative analysis (converted from agent)

You are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects. Analyze the codebase to uncover debt, assess its impact, and create acti

Rename symbols across a codebase safely. Use when renaming functions, variables, classes, or other symbols and need to update all references.

Run a local multi-agent code review before pushing or creating a PR. Use this skill whenever the user says 'code-review', 'pre-review', 'review my changes', 'review before push', 'check my branch', 'local review', 'pre-PR review', or wants feedback on their current branch changes before submitting a pull request. Also use when the user asks to 'review the diff', 'check for issues before PR', or mentions wanting to catch review feedback early. This skill spawns multiple specialized review agents in parallel to give comprehensive feedback fast.

Reviews code changes for quality issues. Use when user says "review my changes", "review the diff", "review my code", "check for issues", "sanity check", or asks to find holes, gaps, or simplification opportunities.

Comprehensive code review with parallel specialized agents

Comprehensive checklist for conducting thorough code reviews covering functionality, security, performance, and maintainability

Provides practical guidance for conducting thorough code reviews that identify issues early, promote knowledge sharing, and deliver constructive feedback. This skill should be used when reviewing pull requests, establishing team review standards, or mentoring developers on effective review practices.

Search for patterns inside file contents using ripgrep (rg). Use when searching for code patterns, finding function definitions, locating usages, or when the user asks to search/grep content inside files.

Use this agent when reviewing code changes to ensure they are as simple and minimal as possible. Applies when implementation is complete but before finalizing changes. Triggers on requests like "check for over-engineering", "review for simplicity", "YAGNI review".

Use this agent when you need a final review pass to ensure code changes are as simple and minimal as possible. This agent should be invoked after implementation is complete but before finalizing changes, to identify opportunities for simplification, remove unnecessary complexity, and ensure adherence to YAGNI principles. Examples: <example>Context: The user has just implemented a new feature and wants to ensure it's as simple as possible. user: "I've finished implementing the user authentication system" assistant: "Great! Let me review the implementation for simplicity and minimalism using the code-simplicity-reviewer agent" <commentary>Since implementation is complete, use the code-simplicity-reviewer agent to identify simplification opportunities.</commentary></example> <example>Context: The user has written complex business logic and wants to simplify it. user: "I think this order processing logic might be overly complex" assistant: "I'll use the code-simplicity-reviewer agent to analyze the complexity...

Simplify and clean up code after changes are complete. Reduces complexity, improves readability, and ensures consistency.

Extract a code pattern from the current codebase into Nathan's pantry repo as a reusable recipe. Use when Nathan says 'add to pantry', 'save this code pattern', or wants to preserve a technique for reuse.

Run large codebase migrations and multi-file refactors. Uses the Composio CLI to coordinate issue tracking, batched PRs, and CI verification while the agent executes the transforms locally across hundreds of files.

Codeium's UI design system. Use when building interfaces inspired by Codeium's aesthetic - dark mode, Inter font, 4px grid.

Execute Codex CLI for code analysis, refactoring, and automated code changes. Use when you need to delegate complex code tasks to Codex AI with file references (@syntax) and structured output.

Orchestrates a dual-AI engineering loop where Claude Code plans and implements, while Codex validates and reviews, with continuous feedback for optimal code quality

Independent cross-model code review via Codex CLI. Codex reviews code changes (PR, branch, or staged files), the active agent addresses findings directly, user controls the loop. Use after implementation, before merge.

Independent cross-model plan review via Codex CLI. Codex reviews spec.md + prd.json, the active agent revises them directly, user controls the loop. Use after /workflows-plan or /workflows-deepen-plan, before /workflows-work.

This skill provides language-agnostic coding principles for maintainability, readability, and quality. Automatically loaded when implementing features, refactoring code, reviewing code quality, or when the user mentions "clean code", "best practices", "code quality", or "maintainability".

Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.

Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.

Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.

Provides guidance on reducing Lambda cold start times through binary optimization, lazy initialization, and deployment strategies. Activates when users discuss cold starts or deployment configuration.

Vibrant, high-contrast palettes and gradients for engaging, memorable, and modern user experiences.

Discover and cache all installed ComfyUI models, custom nodes, and system capabilities. Works online (API queries) and offline (directory scanning). Use before generating workflows to verify available resources.

Diagnose ComfyUI errors, workflow failures, and quality issues. Suggests fixes based on error patterns, missing dependencies, and community-known workarounds. Use when ComfyUI workflows fail or produce unexpected results.

Teaches the command pattern for decoupling task execution from invocation. Use when you need undo/redo functionality, queued operations, or want to decouple the object that invokes an operation from the one that performs it.

Creates a conventional git commit using git-agent. This skill should be used when the user requests "commit", "git commit", "create commit", or wants to commit staged and unstaged changes following the conventional commits format. The executing AI auto-derives its own co-author string from its runtime model identity (e.g., `Claude Opus 4.7 <[email protected]>`) and passes it to `--co-author`. `$ARGUMENTS`, if provided, overrides the auto-derived value.

Creates semantic git commits with conventional commit format, stages changes, and pushes to remote. Handles pre-commit hooks and writes meaningful commit messages. Make sure to use this skill whenever the user says "commit", "push changes", "save to git", "commit this", or wants to create a git commit — even if they just say "save my work." Also proactively offer after any implementation task wraps up.

Creates conventional git commits using git-agent and pushes to the remote repository. This skill should be used when the user asks to "commit and push", "push my changes", or wants to commit and immediately push to remote. The executing AI auto-derives its own co-author string from its runtime model identity (e.g., `Claude Opus 4.7 <[email protected]>`) and passes it to `--co-author`. `$ARGUMENTS`, if provided, overrides the auto-derived value.

ALWAYS USE if you are the verifier or gardener. Use after any build cycle to audit documentation accuracy — check diagram drift, living doc freshness, ARCHITECTURE.md currency, cross-link integrity, and plan status. Gardener uses broadly across the full doc tree; verifier uses post-build to confirm the builder did its doc duty.

Use this skill when the user needs to build a user community, start a Discord or forum, create a community strategy, reduce support load through peer-to-peer help, or use community as a growth channel. Covers community platform selection, launch strategy, engagement tactics, and scaling community without it consuming all your time.

Generate strategic analysis for competition entries and auto-persist to GitHub issue. Identifies winning tone, themes, and angles based on sponsor type and brand voice.

End-to-end automated daily competition workflow. Orchestrates scrape, analyze, compose, and notify skills - all unattended for cron execution.

Set up ongoing competitor monitoring. Use when: defining tracked competitors, scan frequency, change detection alerts.

Monitor competitor product releases and new feature announcements. Use this skill when the user wants to track what competitors are shipping, find the latest product launches in their industry, or generate a competitor release report. Triggers include phrases like "track competitor releases", "what are my competitors launching", "monitor competitor products", "competitor product report", or any request to watch a rival company's product updates.

Complete all TODO-marked code in specified area with test-first approach. Use when finishing incomplete implementations, converting TODO placeholders to working code, or completing test-driven development cycles.

Use when writing or reviewing Jetpack Compose code with bare local var in a @Composable, remember { mutableStateOf(...) }, mutableStateListOf/mutableStateMapOf, or @ReadOnlyComposable.

Enforce extreme brevity and high signal-to-noise ratio. Every word must justify its existence. Eliminates verbose explanations, filler phrases, and unnecessary elaboration.

Concurrency debugging skill for diagnosing data races and deadlocks. Use when reading TSan race reports, debugging deadlocks with GDB thread inspection, analyzing lock-order graphs with Helgrind, identifying std::atomic misuse patterns, or reasoning about happens-before in C++ and Rust. Activates on queries about data races, TSan reports, deadlocks, Helgrind, lock ordering, thread sanitizer output, or atomic ordering issues.

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

Force honest confidence assessment. Express confidence as percentage, explain gaps, validate assumptions before presenting conclusions.

Guides users through configuring Tauri command scopes for security, including filesystem restrictions, URL patterns, dynamic scope management, and capability-based access control.

Resolves git conflicts in progress — for both rebases and merges. Invoke immediately whenever the user says "help with rebase", "rebase conflict", "merge conflict", "I have conflicts", "rebase is stuck", "resolve this conflict", "rebase went wrong", or is mid-rebase or mid-merge and needs guidance on what to keep. Don't wait for the user to ask explicitly — if git status shows conflict markers or a rebase/merge is active, invoke this skill. Analyzes the commit history of every branch involved via parallel sub-agents to understand each side's intent before touching any conflict marker.

Structured disagreement protocols that expose weaknesses, test assumptions, and generate alternatives. Use when stress-testing proposals, playing devil's advocate, challenging architectural decisions, or auditing assumptions before finalizing plans.

Current-era minimalist design with bento grids, dark mode support, and high-performance accessible layouts.

Generate structured ContentSummary JSON from analyzed content. Use after media-reviewer to produce final output with all 16 fields.

Generate content ideas rooted in positioning. Use when someone needs "content ideas," "what should I post," "blog topics," "LinkedIn ideas," or is stuck on what to create.

Use this skill when creating structured educational content. Provides templates for chapters, exercises, projects, labs, slides, and assessments. Trigger phrases include "content template", "chapter structure", "exercise format", "lab template", "slide template", "quiz format".

Apply context-driven testing principles where practices are chosen based on project context, not universal 'best practices'. Use when making testing decisions, questioning dogma, or adapting approaches to specific project needs.

Filter data at the source before it enters context. Use when querying APIs, CLIs, or databases where the full output would be large. Prefer structured output + jq/python filtering over dumping and scanning. Trigger phrases: "find the entity for", "get the ID of", "which service handles", "what's the value of", or any time you'd otherwise dump a large dataset to find one thing.

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

Supplementary context protocol for agents executing in a repo that has a CLAUDE.md / AGENTS.md (or equivalent config). Use to make an execution agent read project conventions first, treat inputs by trust level, surface plan-vs-convention conflicts instead of silently picking a side, and reuse existing patterns before writing new code.

This skill should be used when the user asks to "set up a status line", "configure the footer", "show context window usage", "add a statusline", "visualize context window", "customize the Claude Code footer", or wants to display token counts, cost, or session metrics in the Claude Code terminal footer.

Resume an active AIDLC workflow from checkpoint

This skill should be used when the user asks to 'extract patterns from this session', 'save what we learned', 'create a skill from this workflow', 'learn from this conversation', 'capture reusable knowledge', or wants to turn session patterns into reusable skills.

Convert any data file to another format: CSV, Parquet, JSON, Excel, GeoJSON, and more. Use when the user says "convert to parquet", "save as xlsx", "export as JSON", "make this a CSV", "turn into parquet", or any variation of format-to-format conversion for data files. Also triggers when the user wants to write Parquet, Excel, or other binary formats that Claude cannot produce natively.

Convertkit's UI design system. Use when building interfaces inspired by Convertkit's aesthetic - light mode, Inter font, 4px grid.

Provides instructions for the Better Auth admin plugin in Convex projects. Use when adding admin capabilities, user management, role-based access control, banning users, managing sessions, impersonation, or custom permissions.

Copy Ai's UI design system. Use when building interfaces inspired by Copy Ai's aesthetic - light mode, Inter font, 4px grid.

Copy a feature flag from one PostHog project to one or more target projects in the same organization. Use when the user wants to duplicate a flag, promote a flag from staging to production, sync flags across projects, or replicate a flag configuration in a different workspace. Covers cohort remapping, scheduled-change handling, encrypted payloads, and the safe defaults (disabled in target, no scheduled changes).

Write marketing copy for any page type: landing pages, product pages, about pages, sales pages, ads, and more. Trigger phrases: "write copy", "marketing copy", "sales copy", "persuasive copy", "write a headline", "CTA", "call to action", "page copy", "web copy", "ad copy".

Use this skill when the user needs to write headlines, CTAs, button text, error messages, onboarding copy, or any UI text. Also use when the user says 'write copy for,' 'what should this say,' 'help me with the wording,' or is building any page or component that needs text. Covers headline formulas, microcopy best practices, benefit-driven copy, and SaaS writing style.

Use when planning new projects, onboarding, or reviewing architectural decisions. Core principles and project structure for React 19 SPA development. Covers stack overview, project organization, agent execution rules, and authoritative sources.

# {{SERVICE_NAME_PASCAL}} Service Skill

Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, testing, or when explicit patterns are needed. Contains session protocols, git conventions, security checklists, testing strategy, and communication standards.

Professional, brand-aligned design with structured grids, minimalist layouts, and consistent enterprise patterns.

Install Snowflake CLI and Cortex Code CLI. Use when cortex is not installed, when the user asks to set up Cortex Code, or when routing fails because the CLI is missing. Triggers: setup cortex, install cortex, cortex not found, CLI not installed, set up snowflake.

Drives the cortex skills recommend-feedback-rate loop. Use when a context change occurs (new file types, domain shift, task pivot) or when a task completes and skill effectiveness should be recorded.

Apply a simple code transform via agent-booster's WASM engine — sub-millisecond, deterministic, $0 (no LLM call). Companion to cost-booster-route.

Multi-perspective analysis methodology for complex decisions. Dynamically generates relevant expert viewpoints, consults each perspective systematically, and synthesizes insights into balanced recommendations. Use when users face decisions with multiple considerations, tradeoffs, or competing values.

C++20 coroutines skill for understanding coroutine mechanics and debugging. Use when working with co_await, co_yield, co_return, implementing promise_type, understanding coroutine frame layout, debugging suspended coroutines in GDB, or inspecting frame allocation with Compiler Explorer. Activates on queries about C++20 coroutines, co_await, co_yield, promise_type, coroutine_handle, coroutine suspension, or coroutine frame.

C++ template skill for reading template errors and optimizing compile times. Use when deciphering template error stacks, setting -ftemplate-backtrace-limit, writing concepts and requires-clauses, understanding SFINAE vs concepts, or profiling template instantiation bottlenecks with Templight. Activates on queries about C++ templates, template error messages, concepts, requires expressions, SFINAE, template metaprogramming, or slow template compilation.

Use when implementing CQRS pattern, separating read and write models, optimizing query performance, or asking about "CQRS", "Command Query Responsibility Segregation", "read model", "write model", "command bus", "query bus"

Search and discover R packages on CRAN by topic or task. Use this skill when: - User needs to find R packages for a specific task - Looking up CRAN Task Views for a domain - Checking package dependencies or reverse dependencies - Comparing packages for the same purpose - User says "what R package for...", "find an R package", "CRAN search"

Add Crashlytics plugin's read-only commands to your settings.json allowlist (no more permission prompts during /crash-report). Use when the user invokes /install-permissions.

Build a `BaseDynamicContextProvider` that injects a named, titled block into an agent's system prompt at every `run()` — current time, user identity, retrieved RAG docs, session state, cached DB schema. Use when the user asks to "add a context provider", "inject X into the prompt", "give the agent dynamic context", "wire up RAG", "make a `BaseDynamicContextProvider`", or runs `/atomic-agents:create-atomic-context-provider`.

Creates Amplitude charts from natural language descriptions, handling event selection, filters, groupings, and visualization choices. Use when you know what you want to measure but prefer not to build the chart manually.

Create interactive Our World In Data style charts using the owid-grapher-py Python library. Use this skill when the user wants to visualize data as charts (line charts, bar charts, scatter plots, maps, etc.) in a Jupyter notebook, standalone HTML, or export charts to PNG/SVG.