菜单
Use when running Chat2API provider and model matrix tests using live /v1/models discovery and management API attribution.
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
Use when converting OpenAI-compatible client HAR files into sanitized replayable Chat2API tool-calling fixtures.
Use when operating Chat2API Manager's management API for testing, including health checks, config snapshots, temporary API keys, model mappings, sessions, logs, and cleanup verification.
Use when validating Chat2API Manager proxy behavior across dialogue, tool calling, context, provider routing, request logs, and live client replay workflows.
Use when replaying sanitized client tool-calling fixtures against Chat2API with client-specific pass/fail rules.
| name | chat2api-provider-model-matrix |
| description | Use when running Chat2API provider and model matrix tests using live /v1/models discovery and management API attribution. |
Use this skill when model coverage must follow the live /v1/models surface.
GET /v1/models as the primary model source.CHAT2API_BASE_URL=http://127.0.0.1:8080 \
CHAT2API_MGMT_SECRET=mgmt_xxx \
CHAT2API_API_KEY=sk_xxx \
node skills/chat2api-provider-model-matrix/scripts/run-model-matrix.mjs \
--fixture backup/har/cherry-studio-fixture.json \
--profile cherry-studio
The default model source is GET /v1/models. Use --provider, --model, and --fail-fast-provider N to narrow live runs.