← 返回 Skills 市场
jcools1977

Peripheral Vision

作者 John DeVere Cooley · GitHub ↗ · v1.0.0
darwinlinuxwin32 ⚠ suspicious
304
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install peripheral-vision
功能描述
Monitors adjacent systems, upstream dependencies, and downstream consumers for changes that could affect your current work — before they break it. Like biolo...
安全使用建议
This skill describes broad, continuous monitoring of repo, schemas, CI/CD, environment, and upstream services but declares no credentials or concrete scope. Before installing, ask the publisher (or require in the manifest) for: 1) an explicit list of files/paths/APIs the skill will read; 2) any environment variables or external tokens it needs; 3) how it determines 'files currently open' (editor integration or heuristic); 4) whether it will contact external endpoints and which ones; and 5) whether you can restrict it to read-only access and limit scan frequency. If you can't get clear answers, avoid giving this skill tokens or broad agent permissions and consider running it manually in a limited test workspace first.
功能分析
Type: OpenClaw Skill Name: peripheral-vision Version: 1.0.0 The skill bundle describes a 'Peripheral Vision' tool designed to monitor local code, dependencies, and environment for changes. Its stated purpose involves reading local files (code, git history, configuration, schema definitions) and environment variables to detect relevant shifts. Crucially, the documentation explicitly states 'Zero external dependencies. Zero API calls. Pure git and static analysis,' which significantly mitigates risks of data exfiltration or unauthorized remote actions. There is no evidence of malicious intent, prompt injection against the agent, or any high-risk behaviors beyond what is necessary for its stated, legitimate function.
能力评估
Purpose & Capability
The description (monitoring upstream/downstream code, schemas, env, CI) aligns with an agent that can read the repo and git history. However, the skill's stated capabilities also imply access to external services, CI systems, databases, and environment/configuration; none of those accesses are declared (no required env vars, no config paths). That mismatch is important: either the skill assumes broad implicit access from the agent/platform, or it omits needed credentials and scope descriptions.
Instruction Scope
The SKILL.md directs the agent to identify 'files currently open/modified', trace direct and transitive dependencies, scan Git commits by others, detect schema migrations, inspect CI/CD and Docker configs, and detect changes in environment variables and upstream services. These instructions are open-ended (e.g., 'blind spots', 'continuously scans') and would require reading arbitrary repo files, CI systems, and possibly environment/runtime state. The instructions do not enumerate exactly which files/paths to read, which APIs to call, or what credentials (if any) to use, granting the agent broad discretion to access data outside a narrowly scoped need.
Install Mechanism
Instruction-only skill with no install steps and no code files. That minimizes disk-level risk — nothing is downloaded or written by an installer. All runtime behavior would be the agent following the prose in SKILL.md.
Credentials
The skill references inspecting environment variables, CI/CD, deployment/infrastructure, and upstream services, but the registry metadata declares no required environment variables, secrets, or config paths. Monitoring upstream services or CI typically needs tokens or access credentials; the absence of declared credentials is a disproportionate gap. This either means the skill expects the agent to have ambient access (not disclosed) or it will attempt to read unspecified environment variables and configs without the user being warned.
Persistence & Privilege
always is false (normal) and model-invocation is enabled (default). The skill's prose talks about 'continuous' and 'situational awareness', but there is no install or background daemon described. Autonomous invocation could allow the agent to run this skill repeatedly; that's expected platform behavior but increases impact if the skill is granted broad workspace/credential access. There is no indication the skill modifies other skills or agent-wide configs.
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 peripheral-vision
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /peripheral-vision 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
v1.0.0
Initial release
元数据
Slug peripheral-vision
版本 1.0.0
许可证
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Peripheral Vision 是什么?

Monitors adjacent systems, upstream dependencies, and downstream consumers for changes that could affect your current work — before they break it. Like biolo... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 304 次。

如何安装 Peripheral Vision?

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

Peripheral Vision 是免费的吗?

是的,Peripheral Vision 完全免费(开源免费),可自由下载、安装和使用。

Peripheral Vision 支持哪些平台?

Peripheral Vision 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(darwin, linux, win32)。

谁开发了 Peripheral Vision?

由 John DeVere Cooley(@jcools1977)开发并维护,当前版本 v1.0.0。

💬 留言讨论