AI Agent Skills

Run and validate AutoVideo-Agent Markdown-to-video workflows, including the v0.1-compatible deterministic offline command and v0.2 provider mode with ComfyUI media, Mock…

Use when the user has concrete failing cases in code or a guardrail/classifier/filter/prompt/API they own — a red-team failure catalogue OR a CI/CD test-failure report (…

Design, generate, and deliver client performance reports across all channels, covering quarterly reports, tax reporting, portal integration, and compliance review. Use w…

Use when the user wants an iterative, self-checking exploratory analysis of a dataset — surfacing findings that are each verified by re-running the computation, not asse…

An index of PDF-centric corpora

Create Chinese academic literature-report PPTs from real paper/SI figures. Use for journal-club, thesis-defense, paper-to-PPT, and slide-review tasks, especially when Im…

Playwright TypeScript Framework: a robust solution for testing Web (Desktop & Mobile), API, and Electron apps. With customized utilities, linting, logging, webhooks, and…

Builds the Voice DNA document — a per-character voice specification that the writer uses to differentiate every character. Includes global narrative voice, per-character…

Backend-implementation dedicated review framework. Called by BackendReviewer to professionally analyze BackendDev's API contract & implementation (contract quality/desig…

Frontend-implementation dedicated review framework. Called by FrontendReviewer to professionally analyze FrontendDev's output (UI/API-contract fit/component quality/unit…

Test-artifact dedicated review framework. Called by TestReviewer to professionally analyze Tester's cases/report/coverage doc (coverage depth/acceptance mapping/coverage…

The demo skill owns turning a product concept, release artifact, checklist, or named demo into a convincing, self-contained local try-it experience. It stages only missi…

The Arbor executor workflow: clone the repo from the git bundle your brief hands you, implement and evaluate exactly ONE hypothesis with the file tools, then report stru…

DECIDE-phase doctrine for an Arbor research run: when to merge, prune, combine, or finalize; how the held-out merge gate works; and the rule that the final report uses T…

Pressure-test an existing plan or design artifact until it is coherent enough for the next workflow step or plainly blocked. Use when the user wants to be grilled on a p…

Read, capture, or interact with browser-rendered websites through AdsCrawl. Use when an AI agent needs to extract a page as Markdown, structured article JSON, or HTML; c…