Unstructured web search can turn stale or repeated claims into false confidence. This skill routes verification through target types, source tiers, freshness checks, and abstention rules.

Creators need speech output across local and online voice engines. This skill gives Claude, Codex, and Claude Code one workflow for Qwen3, Edge-style, and OpenAI TTS.

Ambiguous prompts often blend facts, emotions, action requests, and verification needs. This skill routes the prompt by structure before the assistant answers.

Judgment-heavy answers often blur facts, assumptions, recommendations, and missing evidence. This skill gives Claude, Codex, and Claude Code internal checks for cleaner decisions.

Svelte 5 syntax changes can be hard to check by memory. This skill points agents to CLI documentation and autofix commands.

Agents often lack credentials for live data and external APIs. treg searches priced endpoints and calls approved services through one authenticated interface.

Video scripts often exceed runtime limits or conflict with the footage. This skill writes natural spoken copy that fits each clip and visual beat.

Video models need different motion, camera, timing, reference, and audio instructions. This skill converts settled clip concepts into focused prompts for supported model families.

Creating consistent AI video across multiple clips requires careful planning and model selection. This skill coordinates prompts, references, generation, and stitching.

Producing coherent creator videos requires coordinated scripts, casting, storyboards, and clips. This skill manages the full workflow and returns one stitched product video.

Video concepts can lose continuity when clips are planned separately. This skill creates sequential storyboard sheets that preserve characters, products, settings, and visual states.

Creating consistent product imagery requires careful control of identity, lighting, composition, and output format. This skill analyzes a reference and directs generation across ten commercial photography modes.

Image requests often fail because prompts and model choices do not match the intended result. This skill routes each brief and builds a model-specific prompt.

Producing natural speech requires careful voice, model, pronunciation, and pacing choices. This skill guides script preparation and consistent text-to-speech generation.

Campaign teams need consistent fictional talent without supplying a person photograph. This skill creates one detailed adult identity that can guide later image and video generation.

Product pages and photos often contain scattered details that lead to inaccurate creative outputs. This skill extracts consistent product facts, usage mechanics, visual details, and reference images for downstream generation.

Parallel AI coding work is hard to track across branches, logs, and pull requests. This skill gives practical Vibe Kanban setup guidance for local boards, MCP connections, worktree isolation, and review flow.

Documentation teams need clear product help that users can follow without support. This skill structures onboarding guides, how-to articles, tutorials, and FAQs for end users.

Frontend teams often repeat component decisions across projects. This skill guides Claude, Codex, and Claude Code to design reusable React components with clear props.

Software teams need clear test coverage before releases and refactors. This skill helps Claude, Codex, and Claude Code plan practical testing layers, tools, and quality gates.