DYAI2025

Meeting transcripts contain useful signals, but reviewing them manually takes time. This skill turns transcripts into focused communication feedback with examples and next steps.

MCP integrations are hard to design well because agents need concise, reliable tools. This skill guides research, implementation, review, and evaluation for Python and TypeScript MCP servers.

Sales teams often lose time researching accounts that do not match their market. This skill builds focused lead lists with fit scores and outreach guidance.

Low-quality screenshots can make documentation, presentations, and social posts hard to read. This skill guides enhancement, upscaling, sharpening, artifact reduction, and output choices.

Finishing branch work often leaves unclear choices about merge, pull request, cleanup, or discard. This skill gives Claude, Codex, and Claude Code a structured completion workflow.

Messy folders make files hard to find and backups harder to trust. This skill reviews local folders, proposes a clear structure, and guides safe moves, renames, archiving, and duplicate cleanup.

Large implementation plans can fail when agents skip review or push through blockers. This skill keeps work controlled through critical plan review, small execution batches, verification, and feedback checkpoints.

Choosing a memorable domain can slow a launch and lead to weak brand choices. This skill generates focused name ideas, compares TLD options, and guides availability checks.

Professional DOCX work often requires preserving comments, tracked changes, layout, and raw OOXML details. This skill guides Claude, Codex, and Claude Code through creation, editing, validation, and conversion workflows.

Independent failures take too long when one agent investigates them one by one. This skill shows how to split work across focused Claude, Codex, or Claude Code agents and integrate results safely.

Developers often miss patterns in their recent AI-assisted work. This skill reviews Claude Code history and builds a focused growth report with resources.

Invalid data often bypasses a single validation point and fails later in execution. This skill guides Claude, Codex, and Claude Code to add layered checks that make recurring bugs harder to reintroduce.

Long-form writing often stalls when research, structure, citations, and revision happen in separate steps. This skill guides Claude, Codex, or Claude Code through outlining, source gathering, drafting feedback, and final polish.

Flaky tests often fail because they guess how long async work takes. This skill shows Claude, Codex, and Claude Code how to wait for real conditions instead of fixed delays.

Competitive ad research can be slow and inconsistent. This skill extracts ad examples and turns messaging, creative patterns, and campaign themes into clear insights.

Release notes are slow when commit messages are technical or inconsistent. This skill turns git history into clear changelogs for customers, teams, and release channels.

Design-heavy requests often need a clear visual philosophy before production starts. This skill guides Claude, Codex, and Claude Code through philosophy, canvas composition, and final polish.

Teams need consistent visual styling when creating branded artifacts. This skill provides Anthropic colors, typography, and usage guidance for Claude, Codex, and Claude Code workflows.

Rough ideas often turn into weak plans when teams skip discovery. This skill guides Claude, Codex, or Claude Code through focused questions, option comparison, and staged design validation.

Complex HTML artifacts need project structure, reusable components, and reliable bundling. This skill creates a React workspace and packages it into one HTML artifact for Claude conversations.