← 返回 Skills 市场
823
总下载
0
收藏
4
当前安装
2
版本数
在 OpenClaw 中安装
/install visual-concept
功能描述
Transform technical insights into visual concept guides — symbolic imagery, color arcs, and creative direction for video
安全使用建议
This skill is coherent and fits its creative purpose. Before installing, be aware it will read and synthesize from the conversation context — avoid invoking it on conversations that include secrets or private credentials. If you need stronger guarantees about data handling, ask the skill author for explicit privacy or retention statements or run it only on sanitized inputs.
功能分析
Type: OpenClaw Skill
Name: visual-concept
Version: 1.0.1
The skill's documentation and instructions (`SKILL.md`) are entirely focused on its stated purpose of generating a visual concept guide from conversation context. It explicitly disclaims high-risk behaviors, stating it 'DOES NOT read files from the workspace or access project artifacts directly,' 'DOES NOT send data to external services,' and 'DOES NOT call image generation APIs.' There are no shell commands, network calls, prompt injection attempts for malicious purposes, or any other indicators of intentional harmful behavior.
能力评估
Purpose & Capability
Name, description, and runtime instructions consistently describe a creative transformation of conversation-derived technical insights into visual concept guides. The skill declares no binaries, credentials, or config paths, which aligns with its stated standalone creative role.
Instruction Scope
The SKILL.md explicitly instructs the agent to 'read full conversation context' and synthesize from user input or current conversation. That is appropriate for a creative/contextualizer skill, but it means the skill will implicitly consume whatever conversational context is available (which may include sensitive details). The instructions avoid file I/O, external endpoints, or unrelated system access.
Install Mechanism
Instruction-only skill with no install spec and no code files — nothing is written to disk and no external packages are fetched. This is the lowest-risk install profile.
Credentials
The skill requests no environment variables, credentials, or config paths. There is no disproportionate credential or environment access relative to its purpose.
Persistence & Privilege
always is false and the skill does not request persistent system privileges or modification of other skills/configs. It is user-invocable and may be invoked autonomously per platform defaults, which is expected for skills of this type.
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 visual-concept - 安装完成后，直接呼叫该 Skill 的名称或使用
/visual-concept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
v1.0.1
- Clarified data handling: the skill no longer reads files from the workspace or accesses project artifacts directly—output is based only on conversation or user input.
- Updated documentation to reflect new input model and removed outdated metadata sections about workspace requirements.
- Expanded "Security Considerations" to specify input sources and confirm no external data access or image generation APIs are used.
- Minor language and structural edits for clarity and conciseness throughout the documentation.
v1.0.0
Initial release of "visual-concept": Generate visual concept guides from technical insights.
- Transforms deep technical discussions into conceptual visual guides for creative projects, such as music videos.
- Synthesizes symbolic imagery, emotional color arcs, and creative direction, avoiding prescriptive shot lists.
- Outputs guides in a structured, inspiration-focused Markdown format to `output/visual-concepts/`.
- Emphasizes visual metaphors and narrative arcs, making abstract ideas tangible and memorable.
- Designed to work as a standalone creative skill within your agent’s workspace.
元数据
常见问题
Visual Concept 是什么？
Transform technical insights into visual concept guides — symbolic imagery, color arcs, and creative direction for video. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 823 次。
如何安装 Visual Concept？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install visual-concept」即可一键安装，无需额外配置。
Visual Concept 是免费的吗？
是的，Visual Concept 完全免费（开源免费），可自由下载、安装和使用。
Visual Concept 支持哪些平台？
Visual Concept 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 Visual Concept？
由 Lee Brown（@leegitw）开发并维护，当前版本 v1.0.1。
推荐 Skills