← 返回 Skills 市场
leegitw

TED Talk

作者 Lee Brown · GitHub ↗ · v1.0.2
cross-platform ✓ 安全检测通过
464
总下载
1
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install ted-talk
功能描述
Transform technical insights into full 40-50 minute TED-style talks with concrete examples and Q&A
安全使用建议
This skill appears coherent and low-risk because it has no install steps and asks for no credentials. Before using it: (1) avoid including any secrets, passwords, or private data in the conversation context you ask the skill to synthesize (the skill will read the full conversation), and (2) check any concrete examples the skill generates for accuracy and privacy (it should not invent specifics, but validate outputs before sharing). If you need the talk to reference code or files, save/remove sensitive data first because the skill states it won't read project files automatically.
功能分析
Type: OpenClaw Skill Name: ted-talk Version: 1.0.2 The skill is designed to transform conversational context into a TED-style talk. The `SKILL.md` explicitly states that the skill 'does NOT read files from the workspace or access project artifacts directly' and 'does NOT send data to external services'. There are no instructions for malicious execution, data exfiltration, persistence, or harmful prompt injection against the agent. All instructions are focused on guiding the agent's content generation process and establishing quality guardrails.
能力评估
Purpose & Capability
The name/description (generate full TED-style talks from technical conversations) aligns with the instructions: the SKILL.md defines steps to synthesize conversation context into a narrative, lists no unrelated dependencies, and declares it does not read workspace files or require credentials.
Instruction Scope
Runtime instructions direct the agent to 'read full conversation context' and extract concrete details/decisions from that context. This is coherent for a talk-generation skill, but it means any sensitive information present in the conversation can be used in outputs. The skill explicitly states it will not read files or project artifacts, which matches the registry metadata.
Install Mechanism
There is no install spec and no code files—this is instruction-only, so nothing will be downloaded or written to disk. That minimizes filesystem and supply-chain risk.
Credentials
The skill declares no required environment variables, credentials, or config paths. There is no request for unrelated secrets or cloud credentials, which is proportionate to the stated purpose.
Persistence & Privilege
The skill is not always-included and is user-invocable; it does not request elevated or persistent agent privileges. Autonomous invocation is enabled by default (normal), but combined with the lack of extra privileges this is expected and not concerning.
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 ted-talk
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /ted-talk 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
v1.0.2
- Clarified that concrete context and real examples must come from user input, not from files or assumptions. - Revised prerequisites and section examples to emphasize grounding talks in specific, user-provided details. - Updated Output Format and Talk Rules to specify use of real scenarios over hypothetical or file-based details. - Adjusted language in context checklists and core logic to reflect a tighter focus on actual user context.
v1.0.1
- Clarified data handling: the skill no longer reads from workspace files or accesses project artifacts, operating solely on user-supplied input or conversation context. - Updated output description: results are now returned to the invoking agent, not written to output directories. - Removed OpenClaw workspace directory requirement from metadata. - No changes to core functionality, usage, or talk structure.
v1.0.0
ted-talk 1.0.0 – Initial release - Generate full-length (40–50 minute) TED-style technical talks from conversations or specified topics. - Structure talks with hooks, narrative arc, concrete examples, broader implications, and Q&A preparation. - Outputs detailed scripts in markdown format to output/ted-talks/. - Emphasizes real-world examples, decisions, metrics, and thoughtful objection handling. - Designed for creative storytelling, teaching, and effective knowledge transfer.
元数据
Slug ted-talk
版本 1.0.2
许可证
累计安装 0
当前安装数 0
历史版本数 3
常见问题

TED Talk 是什么?

Transform technical insights into full 40-50 minute TED-style talks with concrete examples and Q&A. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 464 次。

如何安装 TED Talk?

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

TED Talk 是免费的吗?

是的,TED Talk 完全免费(开源免费),可自由下载、安装和使用。

TED Talk 支持哪些平台?

TED Talk 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 TED Talk?

由 Lee Brown(@leegitw)开发并维护,当前版本 v1.0.2。

💬 留言讨论