← 返回 Skills 市场
86
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install skvm-jit
功能描述
Trigger `skvm jit-optimize` with post-task evidence so it generates a reviewable optimization proposal for a skill. Use after finishing a task that was drive...
安全使用建议
This skill is an on-demand helper that tells the agent how to run your local `skvm jit-optimize` against a skill folder and a short report. Before using it: (1) confirm you have the `skvm` CLI installed and accessible to the agent, (2) ensure any model-provider credentials `skvm` needs (for example OpenRouter API keys) are already configured outside the skill, (3) review and redact any secrets from logs per the instructions, and (4) only run this when the task used a disk-backed skill and you want an automated optimization proposal. If you cannot or do not want the agent to probe the listed skill directories, provide the exact skill path when prompted instead of letting it search automatically.
功能分析
Type: OpenClaw Skill
Name: skvm-jit
Version: 0.1.0
The skill facilitates 'JIT optimization' of AI agent skills by executing shell commands (`skvm jit-optimize`) and performing broad file system discovery across various sensitive directories (e.g., `~/.claude/skills`, `~/.hermes/skills`). It collects conversation logs and transmits them to an external LLM provider (OpenRouter) for analysis. While these actions are aligned with the stated purpose of improving skill performance, the combination of shell execution, cross-application file access, and data transmission (logs) constitutes a high-risk profile. Additionally, the documentation references a `curl | sh` installation pattern for the underlying `skvm` tool (IOC: skillvm.ai).
能力标签
能力评估
Purpose & Capability
The name/description match the instructions: the skill tells the agent how to locate a skill folder, prepare a structured failure/trace report, and call `skvm jit-optimize`. It does not request unrelated binaries, credentials, or config paths.
Instruction Scope
Runtime instructions stay on-task: locating SKILL.md files in well-known adapter paths, building a JSON or JSONL report, redacting secrets, and invoking `skvm jit-optimize --detach` with explicit arguments. The instructions explicitly avoid guessing paths and warn not to run in bench flows. They do not instruct reading arbitrary user files or environment variables beyond locating skill directories.
Install Mechanism
This is instruction-only with no install spec or code to download, so nothing is written to disk by the skill itself. The only external dependency is the expectation that a local `skvm` CLI is available; that is reasonable for a helper that drives the CLI.
Credentials
The skill does not request environment variables or credentials. One practical caveat: the chosen optimizer-model (example: openrouter/z-ai/glm-5.1) implies the optimizer process may make outbound network calls and may require the user's model-provider API key/configuration (e.g., OpenRouter credentials) for `skvm` to work. That requirement is plausible but not declared in the skill metadata — the user should ensure their `skvm` installation and model credentials are configured beforehand.
Persistence & Privilege
The skill is not always-loaded and does not request elevated presence. It does not attempt to modify other skills or system-wide agent settings; it instructs spawning a background optimizer but that is standard for a CLI-driven optimization flow.
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 skvm-jit - 安装完成后，直接呼叫该 Skill 的名称或使用
/skvm-jit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
v0.1.0
initial release
元数据
常见问题
SkVM JIT Optimize Trigger 是什么？
Trigger `skvm jit-optimize` with post-task evidence so it generates a reviewable optimization proposal for a skill. Use after finishing a task that was drive... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 86 次。
如何安装 SkVM JIT Optimize Trigger？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install skvm-jit」即可一键安装，无需额外配置。
SkVM JIT Optimize Trigger 是免费的吗？
是的，SkVM JIT Optimize Trigger 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
SkVM JIT Optimize Trigger 支持哪些平台？
SkVM JIT Optimize Trigger 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 SkVM JIT Optimize Trigger？
由 Le Chen（@lec77）开发并维护，当前版本 v0.1.0。
推荐 Skills