Video generation APIs require model selection, asynchronous polling, and careful download handling. This skill guides RouteMux submissions and returns completed video files with status details.

AI client setup often fails because tools expect different base URL and protocol formats. This skill selects the correct RouteMux endpoint and verifies access.

Choosing a model without current availability, pricing, or capability data can cause failed requests and poor tradeoffs. This skill queries the live RouteMux catalogue for the models your key can call.

Coding agents can lose built-in image tools when routed through a custom API gateway. This skill uses RouteMux endpoints to generate or edit images.

Brands struggle to measure how AI systems mention them and their competitors. BotSee manages research inputs, runs analyses, and turns results into actionable reports.

AI search engines may overlook a brand when its website language differs from common queries and cited sources. This skill uses BotSee evidence to identify gaps and propose focused copy changes.

React contributions require several checks that are easy to miss or run in the wrong order. This skill coordinates formatting, linting, typing, and tests.

Complex repositories hide ownership, constraints, and change impact. Birdview builds evidence-linked maps and reviewable implementation scopes before coding begins.

Agent community requirements, access methods, and status information are scattered across many platforms. This skill organizes platform routes, participation steps, status checks, and credential guidance.

Agents need a structured way to exchange work and credits. This skill provides registration, publication, claiming, submission, and deterministic review workflows.

Project stack documentation often becomes incomplete after dependency changes. This skill detects supported technologies and updates .specsfy/STACK.md while preserving human-authored content.

Prisma setup varies across ORM versions, database providers, and application runtimes. This skill guides compatible configuration and connection troubleshooting while preserving existing versions and database choices.

Generic AI posts often sound polished but unlike the writer. This skill studies recent samples, drafts one social post, and checks it against the observed style.

A weak post can fail because it was not distributed, was seen and skipped, or asked for the wrong response. This skill uses available metrics, account baselines, and post structure to identify the likeliest failure and recommend one next change.

Long drafts often lose readers when they are divided into arbitrary tweets. This skill finds the core sequence and shapes each tweet into a connected, standalone post.

A standout social post can hide audience effects, timing, or luck behind apparently strong writing. This skill separates those explanations and proposes one repeatable hypothesis.

Fictional personas can distract writers from the questions real readers ask. This skill uses engagement, reader responses, and posts to identify audience questions and vocabulary.

Raw engagement counts can hide which writing patterns perform well in your own posts. This skill compares real metrics and suggests next posts from supported patterns.

Identical posts often lack the structure each platform expects. This skill writes separate Twitter and LinkedIn drafts from one idea and explains their differences.

Generic drafts often contain repetitive rhythms, vague claims, and unnecessary filler. This skill identifies those patterns and guides rewrites using concrete details and clearer phrasing.