← 返回 Skills 市场
382
总下载
2
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install typefully-skill
功能描述
Create, schedule, list, edit, and delete drafts on Typefully. Supports single tweets, threads, and multi-platform posts (X, LinkedIn, Threads, Bluesky, Masto...
安全使用建议
This skill appears to implement exactly what it says (managing Typefully drafts) and its code only talks to api.typefully.com, but the registry metadata omits the required API key. Before installing: 1) Verify the skill source (check the GitHub homepage and confirm the repo and author). 2) Confirm you are comfortable granting TYPEFULLY_API_KEY — this key allows creating, scheduling, editing, and deleting posts (including publishing immediately). Prefer creating a key with minimal scope or be ready to revoke it. 3) Test with read-only commands first (list-social-sets, list-drafts) to confirm expected behavior. 4) Ask the skill publisher to update the registry metadata to declare TYPEFULLY_API_KEY and TYPEFULLY_SOCIAL_SET_ID so automated systems and other reviewers are not misled. If you plan to allow autonomous agent actions, be explicit in policy about 'publish_at: "now"' since the agent could publish content immediately.
功能分析
Type: OpenClaw Skill
Name: typefully-skill
Version: 1.0.0
The OpenClaw Typefully skill is benign. It provides functionality to manage Typefully drafts via its API, as described in SKILL.md and README.md. The `scripts/typefully.sh` script uses `curl` for API interaction and `python3` for JSON parsing and robust input sanitization (`json.dumps`) to prevent injection vulnerabilities. It retrieves API keys from environment variables or the `pass` utility, which is a standard and expected practice for a skill requiring authentication. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, prompt injection attempts in SKILL.md, or obfuscation. All actions are aligned with the stated purpose.
能力评估
Purpose & Capability
The skill name/description (manage Typefully drafts: create, schedule, list, edit, delete) matches the included script and SKILL.md. However, the registry metadata in the provided manifest lists no required environment variables or primary credential, while SKILL.md and scripts/typefully.sh clearly require TYPEFULLY_API_KEY (and optionally TYPEFULLY_SOCIAL_SET_ID). This mismatch is an integrity/metadata concern (likely an authoring or packaging oversight) but not, by itself, evidence of malicious intent.
Instruction Scope
SKILL.md and scripts/typefully.sh confine actions to Typefully's v2 API (https://api.typefully.com/v2). The script only reads TYPEFULLY_API_KEY (or a specific pass store entry) and TYPEFULLY_SOCIAL_SET_ID (or a specific pass entry), performs HTTP calls to the Typefully API, and prints JSON. It does not read arbitrary files, send data to unrelated endpoints, or perform hidden/background tasks. It does invoke 'pass' when used, but only for the explicit keys 'typefully/api-key' and 'typefully/social-set-id'.
Install Mechanism
There is no install spec — this is instruction-only with an included shell script. Nothing is downloaded from external or untrusted URLs during install. The included script is plain shell; no archive downloads, no brew/npm installs are invoked by the skill itself.
Credentials
The actual runtime requires TYPEFULLY_API_KEY (and optionally TYPEFULLY_SOCIAL_SET_ID); those are proportional to the stated purpose. The concern is that the registry metadata lists 'Required env vars: none' and 'Primary credential: none' which is inconsistent with SKILL.md/scripts. This mismatch could lead users or automated systems to install the skill without realizing it needs an API key, or to grant credentials incorrectly. No unrelated secrets or broad system credentials are requested by the script.
Persistence & Privilege
The skill does not request always:true and does not modify other skills or system-wide agent settings. It can be invoked autonomously (disable-model-invocation is false) which is normal; note that autonomous invocation plus a provided API key gives the agent the ability to create/schedule/publish social posts on your behalf — this is expected for a posting skill but worth explicit user consideration.
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 typefully-skill - 安装完成后，直接呼叫该 Skill 的名称或使用
/typefully-skill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: create/edit/schedule/delete Typefully drafts, threads, multi-platform (X, LinkedIn, Threads, Bluesky, Mastodon). Input validation, dynamic social_set_id, proper error handling.
元数据
常见问题
Typefully Skill 是什么？
Create, schedule, list, edit, and delete drafts on Typefully. Supports single tweets, threads, and multi-platform posts (X, LinkedIn, Threads, Bluesky, Masto... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 382 次。
如何安装 Typefully Skill？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install typefully-skill」即可一键安装，无需额外配置。
Typefully Skill 是免费的吗？
是的，Typefully Skill 完全免费（开源免费），可自由下载、安装和使用。
Typefully Skill 支持哪些平台？
Typefully Skill 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 Typefully Skill？
由 chapati（@chapati23）开发并维护，当前版本 v1.0.0。
推荐 Skills