DYAI2025

Spreadsheet work often fails when formulas, formatting, and source data are handled separately. This skill guides Claude, Codex, and Claude Code through reliable workbook creation, editing, analysis, and validation.

AI skill instructions can be vague, untested, and hard to reuse. This skill guides test-first skill writing with subagent pressure tests.

Detailed engineering handoffs are hard when implementers lack context. This skill turns completed designs into step-by-step plans with files, tests, commands, and checkpoints.

Local web apps can be hard to inspect after JavaScript renders the page. This skill guides Playwright automation for screenshots, selector discovery, console logs, and repeatable UI checks.

Online videos can be hard to review when connections are unreliable or content changes. This skill guides allowed downloads, quality choices, audio extraction, playlists, and organized saved files.

AI agents can overstate progress when they rely on assumptions instead of fresh evidence. This skill enforces a clear verification gate before completion, fix, or passing claims.

Agents can miss required skill workflows when tasks start quickly. This skill gives a clear process for finding, announcing, and following relevant skills.

Feature work can disrupt current branches and make baseline failures hard to trace. This skill guides Claude, Codex, and Claude Code through safe Git worktree setup and verification.

Teams often need consistent visual design across slides, reports, pages, and documents. Theme Factory provides preset palettes and font pairings that Claude, Codex, or Claude Code can apply to an artifact.

Process skills often fail when agents face time pressure, authority pressure, or sunk cost. This skill gives a repeatable subagent test workflow to expose failures and improve instructions.

Poor tests often verify mocks instead of real application behavior. This skill gives Claude, Codex, and Claude Code a checklist for safer TDD, focused mocks, and cleaner test design.

Teams can skip failing tests and ship changes without proof that tests verify behavior. This skill guides Claude, Codex, and Claude Code through strict red-green-refactor work.

Starting a new AI skill can be inconsistent without a clear file structure. This template provides a minimal SKILL.md scaffold for Claude, Codex, and Claude Code users.

Random fixes waste time and can create new defects. This skill guides Claude, Codex, and Claude Code through disciplined root cause debugging.

Complex implementation plans can lose quality when one agent keeps too much context. This skill assigns each task to a fresh subagent and adds review checkpoints before progress continues.

Slack GIFs often fail because file size, dimensions, or frame counts are wrong. This skill provides animation templates, validators, and optimization helpers for Slack-ready GIFs.

Reusable skills often stay local because contributors lack a clear publishing workflow. This skill gives Claude, Codex, and Claude Code a structured process for preparing a branch, commit, push, and pull request.

Complex bugs often appear far from their original trigger. This skill guides backward tracing, targeted instrumentation, and test isolation to find the source.

Late review feedback can delay releases and hide important defects. This skill guides Claude, Codex, or Claude Code to request structured reviews before work continues.

Code review feedback can be unclear, incomplete, or technically wrong for the current codebase. This skill helps Claude, Codex, and Claude Code verify feedback before making focused changes.

Selecting giveaway winners manually can look biased and take extra time. This skill helps Claude, Codex, and Claude Code choose random winners from lists or spreadsheets with clear selection details.

Chrome extension teams need safe Manifest V3 architecture, permissions, and review support. This skill guides Claude, Codex, and Claude Code through secure design, implementation, testing, and publishing tasks.

Building PowerPoint decks by hand is slow and error-prone. This skill guides Claude, Codex, and Claude Code through PPTX creation, editing, validation, and thumbnail review.

PDF work often requires repetitive extraction, merging, and form filling across several tools. This skill gives Claude, Codex, and Claude Code structured guidance and scripts for local PDF processing.