← 返回 Skills 市场
🔌

Convex

作者 OOMOL · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
28
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install oo-convex
功能描述
Convex (convex.dev). Use this skill for ANY Convex request — reading, creating, updating, and deleting data. Whenever a task involves Convex, use this skill...
使用说明 (SKILL.md)

Convex

Operate Convex through your OOMOL-connected account. This skill calls the convex connector with the oo CLI; OOMOL injects credentials server-side, so you never handle raw tokens.

Category: Developer Tools. Exposes 23 action(s).

Running an action

Assume the user has already installed the oo CLI, signed in, and connected Convex. Do not run oo auth login or open the connection URL proactively — just run the action. Fall back to First-time setup only when a command actually fails with an auth or connection error.

1. Inspect the contract to get the authoritative input/output schema before building a payload:

oo connector schema "convex" --action "\x3Caction_name>"

2. Run the action with a JSON payload that matches the input schema:

oo connector run "convex" --action "\x3Caction_name>" --data '\x3Cjson>' --json
  • --data takes a JSON object string or @path/to/file.json; omit it to send {}.
  • The response is { "data": ..., "meta": { "executionId": "..." } }; the execution id lives under meta.executionId.

Each action below links to a reference file with its purpose and exact commands. Read the linked file, then fetch the live schema with oo connector schema before constructing --data.

Available actions

Safety

  • Read actions (get / list / search) are safe to run directly.
  • Create, update, send, or post actions change Convex state — confirm the exact payload and effect with the user before running.
  • Delete or remove actions are destructive — always confirm the target and get explicit approval first.

First-time setup

These are one-time steps — do not repeat them on every call. Run a step only when a command fails for the matching reason.

  • oo: command not found — install the oo CLI (other platforms: \x3Chttps://cli.oomol.com/install-guide.md>):

    curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
    
    irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell
    
  • Not signed in / authentication error — sign in to your OOMOL account once:

    oo auth login
    
  • scope_missing / credential_expired / app_not_ready / app_not_found — Convex is not connected, or the connection expired or lacks a scope. Connect once (auth type: OAuth2, API key) at:

    https://console.oomol.com/app-connections?provider=convex
    
  • HTTP 402 / OOMOL_INSUFFICIENT_CREDIT — billing stop. Recharge at https://console.oomol.com/billing/token-recharge before retrying.

Resources

安全使用建议
Install only if you trust OOMOL and want your agent to operate Convex through an OOMOL-connected account. Confirm exact project, deployment, domain, deploy-key, mutation, action, function, and deletion targets before running them, because these operations can change or delete production data.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The broad Convex capabilities, including project/deployment management, deploy keys, queries, mutations, actions, arbitrary function execution, and deletion, match the stated developer-tools purpose but are high impact.
Instruction Scope
Runtime instructions are scoped to `oo connector schema` and `oo connector run`, and the skill explicitly requires user confirmation before write and destructive actions; users should also treat mutations, actions, and arbitrary function calls as potentially state-changing.
Install Mechanism
The artifact is markdown-only with no executable scripts, but first-time setup includes disclosed remote installer commands for the `oo` CLI if it is missing.
Credentials
Tool access is limited to `Bash(oo *)`, and credential use is described as occurring through OOMOL's connected Convex account rather than raw local token handling by the skill.
Persistence & Privilege
No background workers, persistence hooks, local indexing, privilege escalation, hidden credential harvesting, or unrelated filesystem access were found.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install oo-convex
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /oo-convex 触发
  4. 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
v1.0.0
- Initial `oo-convex` release for operating Convex through an OOMOL-connected account via the `oo` CLI, without handling raw Convex credentials directly. - Adds 23 Convex connector actions covering project discovery and management, deployment lookup, creation, updates, and deletion. - Supports operational metadata workflows for deployment regions, deployment classes, custom domains, deploy keys, and token context. - Enables running Convex queries, mutations, actions, arbitrary functions, and batched queries against deployments through the Convex HTTP API. - Defines a schema-first execution workflow, using `oo connector schema` before constructing payloads and `oo connector run` for JSON execution results. - Includes explicit safety guidance for read, write, and destructive actions, including confirmation requirements before state-changing or deletion operations.
元数据
Slug oo-convex
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Convex 是什么?

Convex (convex.dev). Use this skill for ANY Convex request — reading, creating, updating, and deleting data. Whenever a task involves Convex, use this skill... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 28 次。

如何安装 Convex?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install oo-convex」即可一键安装,无需额外配置。

Convex 是免费的吗?

是的,Convex 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Convex 支持哪些平台?

Convex 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 Convex?

由 OOMOL(@oomol)开发并维护,当前版本 v1.0.0。

💬 留言讨论