一键导入
local-llm
Use OpenAI-compatible endpoints (Ollama, vLLM, LM Studio) with this studio: base URL, model name, limits, and anti-hallucination rules for wx/tt APIs.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use OpenAI-compatible endpoints (Ollama, vLLM, LM Studio) with this studio: base URL, model name, limits, and anti-hallucination rules for wx/tt APIs.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Creates an Architecture Decision Record (ADR) documenting a significant technical decision, its context, alternatives considered, and consequences. Every major technical choice should have an ADR.
Audits game assets for compliance with naming conventions, file size budgets, format standards, and pipeline requirements. Identifies orphaned assets, missing references, and standard violations.
Analyzes game balance data files, formulas, and configuration to identify outliers, broken progressions, degenerate strategies, and economy imbalances. Use after modifying any balance-related data or design.
Guided game concept ideation — from zero idea to a structured game concept document. Uses professional studio ideation techniques, player psychology frameworks, and structured creative exploration.
Creates a structured bug report from a description, or analyzes code to identify potential bugs. Ensures every bug report has full reproduction steps, severity assessment, and context.
Auto-generates a changelog from git commits, sprint data, and design documents. Produces both internal and player-facing versions.
| name | local-llm |
| description | Use OpenAI-compatible endpoints (Ollama, vLLM, LM Studio) with this studio: base URL, model name, limits, and anti-hallucination rules for wx/tt APIs. |
| argument-hint | [no args] |
| user-invocable | true |
| allowed-tools | Read, Glob, Grep |
Point any OpenAI-compatible client at your local server:
baseURL http://127.0.0.1:11434/v1,apiKey 通常为占位字符串(依客户端要求)。/v1 地址与端口。Always set:
STUDIO.md at session start when acting as a coding agent..claude/skills/*/SKILL.md as workflow SOPs even when the UI has no Slash menu: the skill name field is the stable command id.Set the editor’s custom OpenAI-compatible provider to the same baseURL. Cursor model dropdown labels vary by version; the important part is the HTTP compatibility, not the product name.