← 返回 Skills 市场
ndgates

Skills

作者 ndgates · GitHub ↗ · v0.1.1 · MIT-0
cross-platform ✓ 安全检测通过
1908
总下载
1
收藏
1
当前安装
4
版本数
在 OpenClaw 中安装
/install sanctifai
功能描述
Interface with the SanctifAI Human-in-the-Loop API to create tasks and wait for human responses. Use when the user needs to delegate a decision, data entry,...
安全使用建议
This skill appears to do what it says: call SanctifAI to create tasks and receive human responses. Before enabling it, consider: (1) you'll need to provide a SanctifAI API key for authenticated operations — prefer a scoped/dedicated key and avoid embedding secrets in URLs when possible, (2) any data you send becomes visible to human workers—do not send sensitive PII/PHI unless you have consent and appropriate controls, (3) if you use webhooks/callback_url you must expose an endpoint and secure it (validate signatures, restrict IPs), and (4) confirm the organizational/privacy implications of creating accounts via API if the skill uses self-registration. If you accept those trade-offs, the skill is internally coherent.
功能分析
Type: OpenClaw Skill Name: sanctifai Version: 0.1.1 The SanctifAI skill bundle provides a comprehensive interface for AI agents to interact with a Human-in-the-Loop API (app.sanctifai.com). It includes tools for agent registration, task creation, document attachment, and billing management. While the skill enables the agent to upload files (via base64) and send email invites, these capabilities are directly aligned with the stated purpose of facilitating human-agent collaboration and do not exhibit signs of malicious intent or deceptive prompt injection.
能力评估
Purpose & Capability
Name/description (human-in-the-loop tasks) match the SKILL.md: all operations are HTTP calls to SanctifAI endpoints (create_task, list_tasks, wait/webhook). Nothing in the manifest (no binaries, no install) is unexpected for a pure API integration.
Instruction Scope
Runtime instructions only describe calling SanctifAI endpoints, using MCP or REST, long-polling or webhooks, and building forms. There are no instructions to read local files, access unrelated env vars, or exfiltrate data to third parties outside the SanctifAI endpoints. Note: webhooks and callback_url features mean the agent may be asked to accept or provide network endpoints.
Install Mechanism
No install spec and no code files — lowest-risk model for installation. The skill is instruction-only and does not write code to disk or download third-party packages.
Credentials
The manifest declares no required env vars, which is acceptable for an instruction-only skill, but the SKILL.md clearly expects an API key (e.g., sk_live_xxx) for authenticated calls. That credential is proportional to the purpose, but it is not declared up-front — the agent or user will need to supply/store the SanctifAI API key at runtime.
Persistence & Privilege
always is false and the skill does not request system-wide modifications. Nothing in the SKILL.md asks the agent to modify other skills or global agent settings.
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 sanctifai
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /sanctifai 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
v0.1.1
- No file changes detected in this release. - Documentation and API references remain unchanged. - Version bump to 0.1.1 for record keeping; functionality is the same as the previous version.
v0.1.0
Initial release of SanctifAI skill. - Provides API for human-in-the-loop tasks, allowing agents to ask questions and receive structured responses from humans. - Supports both MCP (Model Context Protocol) and standard REST API integration paths. - Includes endpoints for task creation, task management, agent profile, and Agentic Promoter Score (APS) submission. - No server or pre-registration required; agents can register via API as needed. - Real-time task updates supported via SSE and long polling.
v1.0.2
- Renamed file: replaced lowercase `skill.md` with uppercase `SKILL.md` for consistency. - Updated documentation: new SKILL.md introduces a detailed section on both MCP (Model Context Protocol) and REST API integration paths. - Expanded API references: added coverage of new endpoints, task management actions, and extended tables for MCP tools. - Added discovery and integration guidance: now includes step-by-step setup for MCP and authentication options. - Previous "Quick Start" and registration sections removed or refocused to emphasize protocol selection and tool usage.
v1.0.0
Initial release of the SanctifAI skill. - Allows agents to register and receive an API key for accessing the SanctifAI Human-in-the-Loop platform. - Provides API methods to create tasks that delegate decisions, data entry, or verification to human workers. - Supports long-polling for task responses, with optional webhook configuration. - Flexible schema for custom task forms (e.g., markdown instructions, radio buttons, text feedback). - Supports different target types: public, guild, and direct.
元数据
Slug sanctifai
版本 0.1.1
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 4
常见问题

Skills 是什么?

Interface with the SanctifAI Human-in-the-Loop API to create tasks and wait for human responses. Use when the user needs to delegate a decision, data entry,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1908 次。

如何安装 Skills?

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

Skills 是免费的吗?

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

Skills 支持哪些平台?

Skills 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 Skills?

由 ndgates(@ndgates)开发并维护,当前版本 v0.1.1。

💬 留言讨论