carterdea/dots
Skill Claude CodeCodex
Design engineering principles and patterns for building polished, accessible web interfaces. Use when building UI components, reviewing frontend code, implementing forms, handling touch interactions, optimizing performance, or creating marketing pages. Triggers on UI polish, input/form validation, button states…
carterdea/dots
Skill Claude CodeCodex
Excalidraw diagrams — create or edit .excalidraw scenes (flowcharts, architecture/workflow diagrams, ERDs), validated locally and published to the user's Excalidraw+ workspace. Use when Excalidraw is named, a .excalidraw file is in play, or an app.excalidraw.com scene URL is given. Not for Mermaid or FigJam.
carterdea/dots
Skill Claude CodeCodex
Work through a plan file task-by-task, checking off items as they complete.
carterdea/dots
Skill Claude CodeCodex
Resolve actionable GitHub pull request review feedback and watch for new comments until approval or a sustained quiet period. Use when the user wants to inspect or continuously poll unresolved review threads, requested changes, inline comments, or PR conversation comments, then automatically implement valid fixes…
carterdea/dots
Skill Claude CodeCodex
Create small, logical commits with conventional commit messages.
carterdea/dots
Skill Claude CodeCodex
Watch a PR's CI checks and fix failures until every check is green.
carterdea/dots
Skill Claude CodeCodex
Review a GitHub PR focusing on correctness, tests, and risk.
carterdea/dots
Skill Claude CodeCodex
Commit, push, and file a concise pull request in one step, or file one for a branch already committed. Use when the user asks to ship or open a PR; babysit-pr takes it from there.
carterdea/dots
Skill Claude CodeCodex
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".
carterdea/dots
Skill Claude CodeCodex
Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
carterdea/dots
Skill Claude CodeCodex
Design, ground, and harden eval suites for LLM/agent systems. Use when the user wants to add evals or regression datasets, fix flaky or vacuous evals, pin agent behavior like tool routing or authorization, add answer-quality guards or deny lists, ground eval expectations in fixtures, set up LLM-as-judge scoring, score…
carterdea/dots
Skill Claude CodeCodex
Generate a continuation prompt so the next session can pick up where this one left off.
carterdea/dots
Skill Claude CodeCodex
Present finished work as a standalone document to read — a writeup, plan, findings, comparison, or a set of UI mocks to pick from. Use when the user asks for something to review, not when they ask to edit HTML, copy, or components inside a project.
carterdea/dots
Skill Claude CodeCodex
Humanize AI-shaped writing. Use for "make this less AI/ChatGPT", AI writing or slop audits, citation/source checks in AI-drafted text, detector concerns, leaked citation tokens, placeholders, broken markup, or wrong target-format cleanup.
carterdea/dots
Skill Claude CodeCodex
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
carterdea/dots
Skill Claude CodeCodex
Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security…
carterdea/dots
Skill Claude CodeCodex
Bring crafted micro-interactions, thoughtful details, and polish to interfaces. Use when building UI, reviewing UI for detail/polish opportunities, making an interface "feel better," or adding tasteful delight and micro-interactions.
carterdea/dots
Skill Claude CodeCodex
Visual-reference-to-app implementation loop for building or restyling a web app screen to match a provided reference image. Use when Codex is asked to take a screenshot/reference/mockup/image and build an app or route that looks like it, especially when the task requires hosting the app, capturing Playwright…
carterdea/dots
Skill Claude CodeCodex
Grill me about specs for the workflows I want to build, within this workspace.
carterdea/dots
Skill Claude CodeCodex
Add tests for the change you're working on.
carterdea/dots
Skill Claude CodeCodex
Rebase current branch onto main/master, resolve merge conflicts, and force-push.
carterdea/dots
Skill Claude CodeCodex
Use this skill when a React component's props have been widened for stories, mocks, tests, or demos and now express states the live application does not enter.
carterdea/dots
Skill Claude CodeCodex
NestJS best practices and architecture patterns for production applications. Use when writing, reviewing, or refactoring NestJS code covering modules, dependency injection, security, and performance.
carterdea/dots
Skill Claude CodeCodex
Aggressively remove comments, docstrings, suppressions, and explanatory clutter that code can express better. Preserve only proven external constraints, required public documentation, and rationale that cannot be encoded.