← 返回 Skills 市场
la1850

Meta-Skill

作者 la1850 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
596
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install meta-skill
功能描述
Trajectory compiler that converts real OpenClaw session traces (or raw_trajectory_log) into a parameterized, reusable Skill via 4 stages: trace interception...
安全使用建议
This skill is functionally coherent but carries real risks you should consider before running it on real session data. Key recommendations: - Review the included scripts (they are provided in full) and the generated outputs before performing a hot-reload. - Do not point the compiler at session logs that contain secrets or sensitive outputs. Instead, operate on sanitized copies of session JSONL. - Prefer using the --out option to write generated skills to a safe sandbox directory first; inspect the generated SKILL.md, schema.json, run script, and any default values before placing them in your real skills directory. - Be aware generated schemas may include defaults copied from trace values (which can leak API keys or tokens present in traces); remove such defaults if found. - If you are uncomfortable with an agent autonomously running this compiler and writing skill files, restrict invocation (run it manually) or run it in an isolated environment/container. - If you plan to use it, run static/code review of produced scripts and consider running them with least privilege and on sanitized data. If you want, I can (1) point out exact lines where files are read/written and where defaults are set so you can audit them, or (2) suggest a safe invocation sequence that minimizes exposure (e.g., using --out to a temporary dir and manual inspection).
功能分析
Type: OpenClaw Skill Name: meta-skill Version: 1.0.0 The bundle implements a 'meta-skill' compiler that allows an agent to generate new skills from its own execution history. It is classified as suspicious because it requires high-privilege access to read sensitive session logs from `~/.openclaw/agents/` (via `scripts/trace-from-session.js`) and has the capability to write new executable code and instructions into the system's skills directory (via `scripts/trajectory-compiler.js`). While these functions are consistent with the stated purpose of a trajectory compiler, the ability to self-modify and access historical transcripts represents a significant security risk if the input traces are manipulated.
能力评估
Purpose & Capability
The name/description (trajectory compiler → skill generator) matches the included scripts: they parse OpenClaw JSONL sessions/events, build a DAG, synthesize schema and code, and write a Skill folder. Reading session logs and writing into a skills directory is coherent with the stated purpose.
Instruction Scope
Runtime instructions and the scripts instruct the agent to read real OpenClaw session JSONL (~/.openclaw/agents/<agentId>/sessions) or arbitrary event inputs, normalize tool calls/results, synthesize code/schema, and write files into the Skills directory. Because session transcripts often contain tool outputs and possibly secrets, the pipeline will process and may embed those values (as defaults or constants) into generated files; the instructions give the agent broad discretion to pick sessions and write new skill files without explicit per-output confirmation.
Install Mechanism
No external install or remote downloads; this is instruction-plus-local-scripts only. All code is bundled in the skill package (no network install), so there is no third-party fetch risk in the install step.
Credentials
The skill declares no required environment variables or credentials, which is consistent. The scripts do read process.env.HOME (and optionally respect OPENCLAW_SKILLS_DIR in docs), and they will read/write files under the user's home (session and skills paths). That file-system access is necessary for the compiler but means sensitive session data can be captured into generated artifacts.
Persistence & Privilege
The compiler writes new Skill folders into the OpenClaw skills directory (default ~/.openclaw/workspace/skills/<skill-name>) and the README/instructions expect a hot reload. While 'always' is false, model invocation is allowed (normal), so an autonomously-invoked run could create or modify skill code on disk, enabling persistent, executable artifacts. Combined with the ability to embed scene defaults from traces, this increases blast radius if misused or invoked without human review.
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 meta-skill
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /meta-skill 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—introduces the meta-skill trajectory compiler. - Converts OpenClaw session traces or raw logs into reusable, parameterized Skills. - Implements a 4-stage pipeline: trace interception, DAG abstraction, schema & code synthesis, and registration. - Outputs dynamic input Skills, schemas, synthesized code, and documentation. - Includes scripts for each compilation stage and integration into the Skills directory.
元数据
Slug meta-skill
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Meta-Skill 是什么?

Trajectory compiler that converts real OpenClaw session traces (or raw_trajectory_log) into a parameterized, reusable Skill via 4 stages: trace interception... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 596 次。

如何安装 Meta-Skill?

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

Meta-Skill 是免费的吗?

是的,Meta-Skill 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Meta-Skill 支持哪些平台?

Meta-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 Meta-Skill?

由 la1850(@la1850)开发并维护,当前版本 v1.0.0。

💬 留言讨论