← 返回 Skills 市场
pancake-skills
作者
suminhthanh
· GitHub ↗
· v1.0.0
1747
总下载
3
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install pancake-skills
功能描述
Tương tác với Pancake Platform API để quản lý pages, conversations, messages, customers, statistics, tags, posts, users. Sử dụng khi cần (1) Quản lý pages và tạo access token, (2) Xử lý conversations và messages, (3) Quản lý thông tin customers, (4) Xem statistics và analytics, (5) Quản lý tags và posts, (6) Quản lý users/staff, (7) Upload media content, (8) Chat plugin operations.
安全使用建议
This skill appears to be an honest Pancake API client, but the published metadata omitted required environment variables. Before installing: (1) Confirm you trust the skill author/source (source/homepage unknown). (2) Expect to set USER_ACCESS_TOKEN and PAGE_ACCESS_TOKEN in your environment — do not embed tokens in the repo. (3) Note tokens are passed in query strings (page_access_token/access_token) which can be logged by intermediaries; prefer short-lived or limited-scope tokens and rotate them after use. (4) Keep CONFIRM_WRITE unset until you explicitly want to allow write actions. (5) Review the scripts locally to ensure no unexpected network calls and test in an isolated environment. If the registry metadata were corrected to declare the required env vars and the author/source can be verified, my concerns would be reduced.
功能分析
Type: OpenClaw Skill
Name: pancake-skills
Version: 1.0.0
The skill provides comprehensive functionality to interact with the Pancake Platform API, including read and write operations for pages, conversations, messages, customers, and media uploads. While these capabilities are powerful, the skill includes explicit safety features such as the `CONFIRM_WRITE=YES` guardrail for all write operations and clear instructions in `SKILL.md` and `README.md` that guide the AI agent towards safe usage and warn against common pitfalls (e.g., not saving tokens). The code is straightforward shell scripting without any malicious constructs, obfuscation, or attempts at prompt injection to subvert the agent's behavior for harmful purposes. All API calls are directed to the legitimate `https://pages.fm` domain.
能力评估
Purpose & Capability
The code and SKILL.md implement a Pancake Platform API client (pages, conversations, messages, customers, stats, uploads, etc.) which matches the skill name/description. HOWEVER the registry metadata claims no required environment variables/primary credential while the scripts and SKILL.md clearly require USER_ACCESS_TOKEN and PAGE_ACCESS_TOKEN (and optionally PANCAKE_BASE_URL and CONFIRM_WRITE). This discrepancy is unexpected and should be resolved.
Instruction Scope
Runtime instructions and scripts limit activity to Pancake API endpoints (pages.fm) and to operations described in the README/SKILL.md. They do not attempt to read arbitrary local files or contact unrelated external endpoints. Guardrails (CONFIRM_WRITE, require GET before write described) are present in the docs and enforced by scripts.
Install Mechanism
There is no remote installer; the skill is instruction/code-only (shell scripts and an OpenAPI YAML) and does not download or execute code from external URLs during install. This is a low-risk install model.
Credentials
The scripts require USER_ACCESS_TOKEN and PAGE_ACCESS_TOKEN (and optionally PANCAKE_BASE_URL and CONFIRM_WRITE). The registry metadata incorrectly lists no required env vars/primary credential; that mismatch is a red flag because a user relying on metadata would not be warned to provide sensitive tokens. Also the scripts send tokens as query parameters (page_access_token/access_token) per the API spec — this is functional but increases the chance tokens are logged in transit or by intermediaries compared with using an Authorization header. Tokens are not stored in the repo, and CONFIRM_WRITE defaults to blocking writes, which is good.
Persistence & Privilege
The skill does not request persistent 'always' presence and does not modify other skills or system-wide configuration. It does not persist credentials to disk. Model invocation/autonomy defaults are unchanged (normal).
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 pancake-skills - 安装完成后，直接呼叫该 Skill 的名称或使用
/pancake-skills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
v1.0.0
Initial release with full Pancake Platform API interaction:
- Manage pages, conversations, messages, customers, tags, posts, users, statistics, and media uploads.
- Provides ready-to-use bash script (`scripts/pancake.sh`) for common API operations (GET/WRITE).
- Includes user and page access token setup, with clear security guardrails for write actions.
- Supports various endpoints for sales channel management, analytics, and chat plugin messaging.
- Detailed usage instructions and examples included in the documentation.
元数据
常见问题
pancake-skills 是什么？
Tương tác với Pancake Platform API để quản lý pages, conversations, messages, customers, statistics, tags, posts, users. Sử dụng khi cần (1) Quản lý pages và tạo access token, (2) Xử lý conversations và messages, (3) Quản lý thông tin customers, (4) Xem statistics và analytics, (5) Quản lý tags và posts, (6) Quản lý users/staff, (7) Upload media content, (8) Chat plugin operations. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1747 次。
如何安装 pancake-skills？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install pancake-skills」即可一键安装，无需额外配置。
pancake-skills 是免费的吗？
是的，pancake-skills 完全免费（开源免费），可自由下载、安装和使用。
pancake-skills 支持哪些平台？
pancake-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 pancake-skills？
由 suminhthanh（@suminhthanh）开发并维护，当前版本 v1.0.0。
推荐 Skills