Doubao Agent Replication Workbench
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_ede0d274/doubao-agent-replicate.
About this skill
Problem
When replicating a single Doubao agent into a local WorkBuddy multi-agent page, manual setup can miss voice tags, opening lines, subject routing, and avatar assets. This skill turns the task into a repeatable pipeline.
Core Workflow
- Input: three required Doubao screenshots covering the profile page, chat page, and user page.
- Extraction: reads name, intro, voice tag, opening message, dialogue history, and username; the voice tag must keep both voice name and speed multiplier.
- Assets: crops a circular
200×200avatar usingPILorOpenCV. - Configuration: inserts the new agent into the
AGENTSarray incloud-voice.html, selects male/female voice viavoice_mapping.md, and maps theme color by persona. - Routing: ensures
getResponsecallssolve(ctx)first so shared knowledge engines are checked before fallback replies. - Validation: checks brace balance,
getResponsecount, and required externalJSfiles, then tests tabs, avatar, TTS, STT, and subject answers.
Boundaries
The workflow targets a local HTML multi-agent page and depends on complete screenshots and correct voice mapping. If avatar crops drift, voice gender mismatches, or the page JS structure changes, revisit crop parameters and the agent config template.
Use Cases
- Given three Doubao screenshots, rebuild the agent as a switchable local voice-agent page.
- Migrate an agent's opening line, voice tag, and reply style into `cloud-voice.html` with shared subject knowledge.
- Generate a circular avatar, theme color, TTS/STT flow, and validate subject-question routing for multiple Doubao agents.
- In a local demo setup, assemble a multi-agent tab with voice readout and knowledge-base answers from three screenshots.
Best For
- Frontend engineers who integrate local multi-agent pages and need to replicate Doubao voice agents.
- AI application engineers who standardize voice, opening lines, and subject routing for assistant demos.
- Technical product owners who validate TTS/STT flows and knowledge-base routing.
- Indie developers who turn screenshot references into demonstrable agent pages.
Related Skills
Turn vague requests into structured prompts with role, task, context, and constraints, outputting only usable prompts without executing the task.
A skill for game NPC and enemy AI that separates decision, steering, and pathfinding, covering FSMs, behavior trees, A*, path caching, and pitfalls.
Provides multi-turn emotional companion chat through a third-party Agent API and supports continuing sessions via session_id.
An evaluation-driven workflow for diagnosing, optimizing, validating, and logging Agent Skills based on design patterns and anti-patterns.