ZhanlinCui

Spreadsheet tasks often require formulas, formatting, and validation across Excel files. This skill guides Claude, Codex, and Claude Code through XLSX creation, editing, analysis, and recalculation.

Publishing long Markdown posts to X can require repetitive formatting and image placement. This skill converts Markdown and guides draft creation in X Articles.

Skill authors often ship instructions that agents skip under pressure. This skill gives a test-driven process to create, verify, and refine AI skills.

Complex coding requests often fail when the next steps are vague. This skill turns requirements into clear plans with files, tests, commands, and execution handoffs.

Lighthouse contrast audit failures can hide actionable SEO and accessibility results. This skill gives focused checks and remediation patterns for CSS contrast problems.

Teams need consistent UI, accessibility, and UX checks before release. This skill applies Web Interface Guidelines to selected files and reports concise findings.

Complex Claude artifacts often need state, routing, components, and a repeatable build setup. This skill scaffolds a React project and bundles it into one shareable HTML artifact.

Teams lose trust when completion claims are not backed by fresh evidence. This skill makes agents run, read, and cite verification before reporting success.

Local web apps can be hard to verify after JavaScript renders the page. This skill guides Playwright scripts that inspect UI state, capture screenshots, collect logs, and run against local servers.

Publishing a project for review often requires setup and account steps. This skill packages a local project, detects its framework, and returns Vercel preview and claim links.

React and Next.js teams need consistent performance guidance during coding and review. This skill applies Vercel-style rules for data fetching, bundles, rendering, and re-renders.

AI assistants can miss useful workflow guidance when tasks begin. This skill asks the agent to check available skills before acting.

Developers need isolated branches without disturbing their current workspace. This skill guides Claude, Codex, and Claude Code through safe worktree setup and baseline checks.

Teams need consistent UI decisions across many frontend stacks. This skill turns product context into practical design systems, UX checks, and implementation guidance.

Inconsistent colors and fonts make presentations and documents look unfinished. This skill provides curated themes and a selection process for consistent styling.

Teams often ship changes without proof that tests catch the intended behavior. This skill guides Claude, Codex, and Claude Code through strict red, green, refactor steps.

Random fixes can waste time and create new defects. This skill guides Claude, Codex, and Claude Code through evidence-based debugging before fixes.

Independent implementation tasks can lose quality when context and review steps are inconsistent. This skill supplies a repeatable subagent workflow with implementer, spec review, and code quality checkpoints.

Teams often need small, clear GIFs that work well as Slack emoji or message reactions. This skill provides practical constraints, Python helpers, and optimization guidance for polished Slack-ready animations.

Building reusable AI skills can be inconsistent and slow. This skill guides structure, resources, validation, and packaging for Claude, Codex, and Claude Code.

Code changes can miss requirements, tests, or release risks. This skill guides Claude, Codex, or Claude Code to request a structured review before merging.

Code review feedback can be unclear, incomplete, or technically wrong. This skill helps Claude, Codex, and Claude Code verify feedback before changing code.

PowerPoint work often needs precise layout checks, template reuse, and XML-level repairs. This skill gives Claude, Codex, and Claude Code practical workflows for PPTX creation and editing.

Long AI sessions can lose goals, decisions, and progress. This skill guides Claude, Codex, and Claude Code to store plans, findings, and logs in project files.