📦 Model-Selector — 智能选模型
v1.0.0在任务执行前，先分析查询意图与成本，自动挑选 Elite/Balanced/Basic 三档中最合适的 LLM，实现又快又省的模型路由。
0· 344·2 当前·2 累计
by 下载技能包
最后更新
2026/2/26
安全扫描
OpenClaw
可疑
medium confidenceNULL
评估建议
This skill appears to do what it claims (choose a model tier) but has a few red flags you should consider before installing:
- Code/instruction mismatch: SKILL.md references get_optimal_model and analyze_and_route, but the code provides ModelRouter.route(). Confirm the actual tool interface the agent will call and update the README or code so they match.
- Local logging: It writes query_history.json with users' queries. If prompts may contain secrets or sensitive data, disable or audit this log...详细分析 ▾
ℹ 用途与能力
The skill's name/description (model routing between Elite/Balanced/Basic) aligns with the included Python code which contains a ModelRouter and training helper. However the registry/README claims ClawHub-optimized tiers and 'Multi-Provider Support' while the skill itself only returns model identifiers (it does not perform provider authentication or API calls). The requirements.txt includes 'litellm' even though the code never imports or uses it — this is unnecessary and disproportionate to the stated functionality.
⚠ 指令范围
SKILL.md instructs agents to call a tool named get_optimal_model / shows an example using router.analyze_and_route(), but the provided code exposes ModelRouter.route() (no analyze_and_route or get_optimal_model). This mismatch means the SKILL.md and code are inconsistent. The code logs every routed query to a local file (query_history.json) and exposes a 'refine_keywords' / train_router.py flow that reads that history; storing user queries on disk is a privacy risk and could be used later to aggregate sensitive inputs. The 'refine' flow mentions using an external LLM to suggest new keywords — that could lead to sending logged queries to third-party models if implemented later (the current code does not itself send data externally, but the design enables it).
ℹ 安装机制
There is no install spec (instruction-only install), so nothing is automatically downloaded or executed by an installer; this lowers supply-chain risk. However the bundle includes a requirements.txt declaring heavy ML libraries (torch, sentence-transformers) which are large and may be installed by a user; those are plausible for the code but could be unexpected. No network download URLs or extract steps are present in the skill metadata.
✓ 凭证需求
The skill requests no environment variables or credentials (none declared), which is proportionate for a router that only suggests model identifiers. Note: to actually execute calls against the named providers the agent/host will need provider-specific API keys separate from this skill; those are not requested by the skill itself.
ℹ 持久化与权限
The skill writes and reads a local file query_history.json for rolling adjustment and can keep up to 1000 entries. It does not request always:true and does not modify other skills. Persisting user queries to disk is a modest persistence/privacy concern (sensitive prompts could be retained).
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.0.02026/2/26
NULL
● 无害
安装命令
点击复制官方npx clawhub@latest install model-selector
镜像加速npx clawhub@latest install model-selector --registry https://cn.longxiaskill.com