Real Skill packageSource verifiedClawHub registry

cn-llm-router

国产大模型统一路由。把 DeepSeek、通义千问、智谱 GLM、Kimi、腾讯混元、字节豆包、百度文心、讯飞星火、MiniMax、零一万物 Yi、百川、阶跃 Step 等 12 家国产大模型 + Qwen-VL/GLM-4V/豆包视觉 3 家视觉模型收敛成一个命令入口；支持文本 + 图片多模态任务路由；按任务类型（代码/推理/长文/翻译/摘要/抽取/图像识别）结合能力画像自动或手动选择最合适、最省钱的模型；支持流式输出、自动统计跨厂商 token 成本、硬件自适应限流（不拖累电脑）、本地语义缓存省 token、全链路离线 Mock 调试、技能更新提醒。当用户需要「调用国产大模型」「多模型比价/降本」「统一管理多个模型 Key」「本地跑大模型路由」「不想被某一家厂商绑定」「识别图片/音频内容」时使用。

Identity and source

Publisher attributionfyniujinregistry owner unverified by skillvetai
Functional categoryAwaiting category reviewreview pending · 0% rule confidence
Package forminstruction with code39 recorded files
Canonical sourceClawHub registryclawhub:fyniujin:cn-llm-router
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/25/2026.claude/skills/cn-llm-router

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/25/2026.agents/skills/cn-llm-router

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/25/2026skills/cn-llm-router

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @fyniujin/cn-llm-router
clawhub inspect @fyniujin/cn-llm-router --version 2.5.0

Security evidence

SkillVetAI static result: high signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
39 / 39 inspected as text
Checked
8/25/2026, 1:54:37 AM
Scanner
0.1.3
Policy
1.0.3
1 automated finding
highDynamic code or shell execution is present_core/calibrate.py:97 · confidence 78%eval(
1 High/Critical review queue entry
STATIC_DYNAMIC_CODE_EXECUTIONpending
Open human review queue →
4 inferred permission indicators
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
13 dependency and API indicators
  • api: aip.baidubce.com
  • api: api.baichuan-ai.com
  • api: api.hunyuan.cloud.tencent.com
  • api: api.lingyiwanwu.com
  • api: api.minimax.chat
  • api: api.moonshot.cn
  • api: api.stepfun.com
  • api: ark.cn-beijing.volces.com
  • api: clawhub.ai
  • api: dashscope.aliyuncs.com
  • api: open.bigmodel.cn
  • api: qianfan.baidubce.com
  • api: skillhub.cn
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
8/24/2026, 4:36:00 PM
Release binding
Matches this record
  • vt: clean
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:28c5ce74ab13c6cc1fbc3fc151f6677c5e18e30323d349a49f06ee13e1e07428
Show up to 30 recorded paths
  • _core_lock.json
  • _core/adapters/__init__.py
  • _core/adapters/base.py
  • _core/adapters/ernie.py
  • _core/adapters/openai_compat.py
  • _core/adapters/spark.py
  • _core/cache.py
  • _core/calibrate.py
  • _core/config.py
  • _core/cost_tracker.py
  • _core/health_check.py
  • _core/version.json
  • _core/yaml_simple.py
  • config.example.json
  • references/mock_data.json
  • references/models.yaml
  • references/routing-rules.md
  • scripts/__init__.py
  • scripts/adapters/__init__.py
  • scripts/adapters/base.py
  • scripts/adapters/ernie.py
  • scripts/adapters/openai_compat.py
  • scripts/adapters/spark.py
  • scripts/cache.py
  • scripts/classifier.py
  • scripts/config.py
  • scripts/cost_tracker.py
  • scripts/hardware.py
  • scripts/health_check.py
  • scripts/meta.py

Source changelog

**Core refactor: All main modules are now moved into the new _core/ directory, improving structure and maintainability.** - Major refactor: Scripts and adapters relocated from scripts/ to _core/ and _core/adapters/. - Added new internal modules for config, cache, cost tracking, health checks, version management, and simple YAML parsing in _core/. - Updated internal imports and references to accommodate the new file structure. - Removed legacy/duplicate documentation file (skill-card.md).

Release security diff

highCompared fixed releases 2.4.0 and 2.5.0; 1 finding and 0 permission indicators were added.

Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.

Change reasons and limitations
  • new high finding
  • finding surface changed
  • file surface changed
  • content hash changed

Observed release history

These older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.

2.4.08/16/2026sha256:7f347bb64d618ab66f45858a033542948f02670581ab0e253a0d14101f62c699