← 返回 Skills 市场
126
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install model-registry-manager
功能描述
Detect provider models, deduplicate them, remove unusable ones, register missing models into OpenClaw, and safely keep provider-native model ids/names during...
安全使用建议
This skill appears to do what it says: read your OpenClaw config (~/.openclaw/openclaw.json), call provider /models and /chat/completions using provider.apiKey entries from that config, produce reports under reports/model-registry, update agents.defaults.models in the config, and optionally restart the gateway. Before installing or scheduling it:
- Back up ~/.openclaw/openclaw.json so you can revert config changes.
- Run a dry run first (use the --dry-run flag when running scripts) and run the validation script to confirm behavior before enabling recurring sync.
- Confirm that provider.apiKey values in your config are correct and intended to be used by this tool; the skill uses those keys to contact provider endpoints.
- Note SKILL.md asks the agent to auto-write a `.learnings/` archive; the bundled scripts do not implement that, but the instruction could be followed by an agent — decide whether you want automatic writebacks to home/workspace.
- Ensure the agent environment has a modern Node runtime (fetch is used) and that you are comfortable with the script calling 'openclaw gateway restart' when --restart is provided.
- Review and/or run the JavaScript files in a safe environment to confirm no local-policy conflicts before enabling scheduled runs.
功能分析
Type: OpenClaw Skill
Name: model-registry-manager
Version: 1.3.0
The skill manages the OpenClaw model registry by reading and writing the main configuration file (openclaw.json), which contains sensitive provider API keys. It includes scripts (sync-models.js, validate-model-sync.js) that perform network requests using these keys and execute shell commands (openclaw gateway restart) to apply changes. Additionally, SKILL.md instructs the agent to establish recurring cron jobs with broad 'exec' and 'read' permissions. While these actions are aligned with the stated purpose of model synchronization, the high-privilege access to credentials and system configuration constitutes a significant security risk.
能力评估
Purpose & Capability
Name/description match the implementation: scripts fetch /models from provider.baseUrl, deduplicate by provider id, probe models, update agents.defaults.models in ~/.openclaw/openclaw.json, and write reports. No unrelated credentials or tools are requested.
Instruction Scope
SKILL.md instructs the agent to inspect config, fetch remote models, validate before writing, schedule recurring jobs, and maintain a `.learnings/` archive automatically. The provided scripts implement the core fetch/deduplicate/probe/register/report behavior and write reports under the skill's reports path, but they do not implement the automatic `.learnings/` archival behavior described in SKILL.md (minor mismatch). The instructions also recommend scheduling jobs and allowing exec/read for those jobs; the sync script can run 'openclaw gateway restart' when --restart is passed, which is consistent with the recommendation but grants the skill permission to execute a restart command.
Install Mechanism
No install spec — instruction-only with two included Node scripts. Nothing is downloaded from external URLs or written during an install step.
Credentials
No required env vars are declared. The scripts read provider.apiKey entries from the OpenClaw config file (cfg.models.providers[].apiKey) to call provider endpoints; that is expected for this purpose and no unrelated secrets are requested.
Persistence & Privilege
always:false (good). The skill intentionally modifies the OpenClaw config file (~/.openclaw/openclaw.json) and can run 'openclaw gateway restart' when asked; these are within the skill's purpose but are privileged actions (configuration writes and a restart). Autonomous invocation is allowed by default (not flagged on its own).
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install model-registry-manager - 安装完成后，直接呼叫该 Skill 的名称或使用
/model-registry-manager触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.3.0
Document automatic recurring job installation for OpenClaw agent sessions via first-class cron tool; add validation safety-net and 6-hour sync scheduling guidance.
v1.2.0
Pure registry sync/validate, allowlist/denylist, diff reports, provider stats.
v1.1.0
Generalized provider-wide model sync, generic fallback selection, and merged failover policy guidance.
元数据
常见问题
Model Registry Manager 是什么？
Detect provider models, deduplicate them, remove unusable ones, register missing models into OpenClaw, and safely keep provider-native model ids/names during... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 126 次。
如何安装 Model Registry Manager？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install model-registry-manager」即可一键安装，无需额外配置。
Model Registry Manager 是免费的吗？
是的，Model Registry Manager 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Model Registry Manager 支持哪些平台？
Model Registry Manager 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Model Registry Manager？
由 Qihong（@zqh2333）开发并维护，当前版本 v1.3.0。
推荐 Skills