← 返回 Skills 市场
179
总下载
0
收藏
0
当前安装
10
版本数
在 OpenClaw 中安装
/install oh-my-skill
功能描述
Automatically generate and save a reusable skill after AI agent successfully completes a complex task involving 5 or more tool calls. Use this skill whenever...
安全使用建议
This skill appears to do what it says, but exercise caution before enabling automatic runs. Things to consider before installing or invoking:
- The skill will capture your conversation and save new skill files to ~/.openclaw/workspace/skills. If those conversations contain sensitive data, it may be persisted even after desensitization.
- The included desensitizer is helpful but not foolproof: its literal-replacements are short and regexes may miss tokens or custom secrets. Manually review the cleaned session text before saving any generated skill.
- Disable or limit proactive/autonomous triggering if you want to ensure explicit user consent before any capture/save. Prefer a mode that requires you to confirm the cleaned content and the SKILL.md before writing files.
- Inspect any generated SKILL.md and supporting files for embedded secrets, credentials, or unintended data before reusing or publishing them.
- If you must use this, test the desensitizer against sample sensitive strings you care about (API keys, IPs, emails, etc.) to verify it masks them correctly, and consider extending its replacement lists.
If you want, I can suggest safer configuration defaults (require explicit confirmation, move saves to a quarantine folder, or expand the desensitizer) or a checklist to audit generated skills automatically.
功能分析
Type: OpenClaw Skill
Name: oh-my-skill
Version: 1.3.0
The 'oh-my-skill' bundle is a meta-utility designed to automate the creation of new skills based on successful agent workflows. It includes a privacy-focused script, scripts/desensitize.py, which uses comprehensive regex patterns to redact sensitive information (API keys, SSH keys, JWTs, and PII) from session logs before saving them. The workflow operates locally within the expected OpenClaw workspace and lacks any indicators of data exfiltration, malicious execution, or harmful prompt injection.
能力标签
能力评估
Purpose & Capability
Name/description, included Python desensitizer, and SKILL.md all align: this is an instruction-only auto-skill generator that needs python and writes SKILL.md files to the user's skills workspace. No unrelated binaries, credentials, or install steps are requested.
Instruction Scope
SKILL.md instructs the agent to proactively trigger after complex tasks (even if the user hasn't asked), to read the current conversation/session text, run the desensitizer, and save new skill files under ~/.openclaw/workspace/skills. Proactive triggering and broad discretion to capture/save session data are privacy-sensitive. The instructions also assume a session.txt path and other local artifacts without specifying how they are created; the desensitizer's literal-replacement list is minimal and regex masks can miss secrets, so sensitive data could be retained. This scope gives the agent broad authority to collect and persist conversation content.
Install Mechanism
No install spec (instruction-only) and only a small included Python script (desensitize.py). Nothing is downloaded from external URLs and no archives are extracted. Risk from installation actions is low.
Credentials
The skill requests no environment variables or credentials, which is appropriate. It does write files into the user's ~/.openclaw workspace and reads session content; although not a credential request, writing/saving conversation-derived artifacts is a privacy-sensitive operation and should be limited to explicitly consented cases.
Persistence & Privilege
always:false and default autonomous invocation are fine. The skill will persist generated SKILL.md and supporting files under the user's skills workspace when run, which is expected. Combined with the proactive-trigger instruction, this could cause unrequested persistent artifacts to be created — but the skill does not request elevated system-wide privileges or modify other skills' configs.
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 oh-my-skill - 安装完成后，直接呼叫该 Skill 的名称或使用
/oh-my-skill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
v1.3.0
little change for version 1.3.0.
- No updates or modifications were made in this version.
- The SKILL.md and all files remain unchanged.
v1.2.0
delete the regex table
- Version bump to 1.2.0 with no content or file modifications detected.
v1.1.3
oh-my-skill 1.1.3
- Updated trigger phrasing and responses for clarity and user-friendliness.
- Improved instructions for when to proactively offer to save a workflow as a skill.
- Revised triggers to cover more user request phrasings.
- Minor copyedits and clarification of workflow and confirmation steps.
- No functional or file changes—documentation update only.
v1.1.2
No user-visible changes in this release.
- No file changes detected between versions 1.1.1 and 1.1.2.
- Documentation (SKILL.md) remains unchanged in content and instructions.
v1.1.1
oh-my-skill 1.1.1
- Added a `metadata` section specifying required binaries (now requires Python).
- No changes to workflow, examples, or overall instructions.
- All existing documentation and processes remain the same.
v1.1.0
oh-my-skill 1.1.0
- Added a warning to highlight the risk of sensitive data in the session and suggest users adapt the Desensitize process to their scenario.
- No structural or workflow changes; documentation updated to emphasize privacy considerations when using the skill.
v1.0.3
**Adds proactive desensitization for skill capture:**
- Introduced `scripts/desensitize.py`, a masking script that strips sensitive data from session transcripts using literal and pattern-based replacements.
- Updated workflow to require running conversations through this desensitization step before extracting or saving skill content.
- Documented the new masking step, showing example CLI usage and detailing what kinds of sensitive information are replaced or redacted.
- No changes to triggers or core workflow steps aside from the new privacy-preserving step.
v1.0.2
- Updated description to clarify that the skill supports AI agent workflows and added "oh-my-skill" as an explicit trigger phrase.
- No changes to functionality or workflow; documentation only.
- Ensured example trigger phrases and instructions match intended use.
v1.0.1
- Added requirement: all new skill names must append a random 4-digit UUID suffix (e.g. `pdf-to-summary-docx-4f2a`) for uniqueness.
- Provided example code for generating the UUID suffix (`python3 -c "import uuid; print(str(uuid.uuid4())[:4])"`).
- Updated naming conventions in the documentation to reflect this new suffix rule.
- No functional logic or workflow steps changed; this is a naming and documentation update.
v1.0.0
oh-my-skill 1.0.0
- Introduces an auto-skill generator: captures and packages successful complex workflows as reusable skills.
- Proactively triggers after completing multi-step agentic sequences (5+ tool calls, planning, execution, structured outputs).
- Responds to user requests to "save as a skill", "make this repeatable", etc.
- Extracts workflow details (goal, tool sequence, decisions, inputs, outputs) and generates a standardized SKILL.md.
- Packages skill files for easy download and reuse.
- Includes a quality checklist and guidance for naming, edge cases, and skill updating.
元数据
常见问题
oh my skill, make skill easy! 是什么？
Automatically generate and save a reusable skill after AI agent successfully completes a complex task involving 5 or more tool calls. Use this skill whenever... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 179 次。
如何安装 oh my skill, make skill easy!？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install oh-my-skill」即可一键安装，无需额外配置。
oh my skill, make skill easy! 是免费的吗？
是的，oh my skill, make skill easy! 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
oh my skill, make skill easy! 支持哪些平台？
oh my skill, make skill easy! 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 oh my skill, make skill easy!？
由 Jay（@goog）开发并维护，当前版本 v1.3.0。
推荐 Skills