BF 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。
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 +…
As a process F 41/100 · Will not run — References files that are not bundled: scripts/adapters/
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
✓ No critical or high findings
Medium and low: 2
-
low Secrets in code
secret-high-entropy-token_core/cache.py:38High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)_embedding_model = SentenceTransformer('para…-v2')quoted -
low Secrets in code
secret-high-entropy-tokenscripts/cache.py:38High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)_embedding_model = SentenceTransformer('para…-v2')quoted
Files scanned: 28. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5837 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 41/100
- 0Tools and files. 1 referenced file(s) missing: scripts/adapters/
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 5837 tokens
- 100Steps. 45 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low 17 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -216 emoji in the instructions: noise for the model
- -33 of 13 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 355: enough signal without eating the budget
- +4Structure: 39 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (34 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.