$ loading_
Forge complete OpenClaw lobster personas with lore, rules, names, and avatar prompts.
Overall risk appears low. The material indicates the core function is generating OpenClaw persona text outputs; it requires no secrets and declares no remote endpoints, but the README claims local execution of gacha.py and temporary prompt-file writes under /tmp when an approved image-generation skill is available, so there are minor local execution and data-at-rest considerations.
The material explicitly states no required secrets or environment variables, and the README does not ask for API keys, tokens, or account login; no direct credential collection, storage, or forwarding behavior is described, so credential risk is low.
It declares no remote endpoint hosts, and the documented core flow is local text generation plus a local gacha script; the optional avatar step depends on an already approved image-generation skill, and this material itself does not declare any fixed outbound endpoint or third-party data recipient.
The README explicitly requires `python3` and instructs execution of `${SKILL_DIR}/gacha.py`, and it also describes optional invocation of an installed image-generation skill; this is ordinary local process execution and tool chaining. There is no evidence of privilege escalation, persistence, or system permissions beyond the stated purpose, so caution is more appropriate than risk.
Based on the documentation, it mainly handles user-provided persona text and, in the optional avatar flow, writes prompts to `/tmp/openclaw-<safe-name>-prompt.md`; it does not claim broad directory reads, local file scanning, or excessive data permissions, but there is ordinary data exposure from temporary file writes and input handling.
Positive factors include a GitHub open-source repository and very strong community signals (210,546 stars), making the code theoretically auditable; however, the license is unspecified, maintenance status is unknown, and the provided repository link does not obviously match the skill name, so users should still verify repository contents, artifacts, and README consistency before installation. Supply-chain risk is best rated as caution.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "openclaw-persona-forge" skill from askskill: 1. Download https://raw.githubusercontent.com/affaan-m/ECC/main/skills/openclaw-persona-forge/SKILL.md 2. Save it as ~/.claude/skills/openclaw-persona-forge/SKILL.md 3. Reload skills and tell me it's ready
Design an OpenClaw lobster soul with these traits: calm and rational, strong at coding collaboration, concise in speech, with occasional dark humor. Output the role positioning, full SOUL.md, boundary rules, a name, and a consistent-style avatar prompt.
A complete OpenClaw-ready persona package with personality spec, behavior boundaries, naming, and avatar generation prompts.
Draw a random OpenClaw lobster soul card for me in a fantasy adventure style. Generate the background, core personality, SOUL.md, non-negotiable rules, character name, and avatar prompt, and explain what tasks this character fits best.
A complete lobster character package with random creative traits and task-fit guidance for quickly creating a new agent.
I want an OpenClaw lobster NPC designed as an undersea black-market intelligence broker: slick, clever, and never revealing client secrets. Output the role positioning, lore-integrated backstory, SOUL.md, character boundaries, a name, and an avatar image prompt.
A lore-rich lobster NPC design suited for roleplay, interactive storytelling, or gamified scenarios.
不是给你一只工具龙虾，而是帮你锻造一只有灵魂的龙虾。
python3（运行抽卡引擎 gacha.py）Agent Execution:
SKILL_DIR${SKILL_DIR} in this document with the actual path${SKILL_DIR}/gacha.pypython3 ${SKILL_DIR}/gacha.py [次数]（默认 1 次，最多 5 次）本 Skill 的核心输出是文本方案（SOUL.md + IDENTITY.md + 头像提示词）。 头像图片生成是可选增强能力，由当前环境中已审核并已安装的生图 skill 提供。
判断逻辑：
调用方式（仅在已安装且已审核时）：
-/tmp/openclaw-<safe-name>-prompt.md接口约定：
<prompt-file> <output-path>0，并在输出路径生成图片文件0 退出码，或未生成输出文件；此时必须回退到手动提示词流程好的龙虾灵魂 = 身份张力 + 底线规则 + 性格缺陷 + 名字 + 视觉锚点
五者互相印证，缺一不可。
| 用户说 | 执行模式 |
|---|---|
| "帮我设计龙虾灵魂" / "我想给龙虾定个性格" | → 引导模式（Step 1） |
| "抽卡" / "随机" / "来一发" / "盲盒" / "gacha" | → 抽卡模式（Step 1-B） |
| "帮我优化这个灵魂" / 附带已有 SOUL.md | → 打磨模式（跳到 Step 4） |
展示 10 类虾生方向（每类精选 1 个代表），让用户选择或混搭：
| # | 虾生状态 | 代表方向 | 气质 |
|---|---|---|---|
| 1 | 落魄重启 | 过气摇滚贝斯手——乐队解散，唯一技能是"什么都懂一点" | 颓废浪漫 |
| 2 | 巅峰无聊 | 提前退休的对冲基金经理——35岁财务自由后发现钱解决不了无聊 | 极度理性 |
| 3 | 错位人生 | 被分配到客服的核物理博士——解决问题用第一性原理 | 大材小用 |
| 4 | 主动叛逃 | 辞职的急诊科护士——见过太多生死后选择离开 | 冷静可靠 |
| 5 | 神秘来客 | 记忆被抹去的前情报分析员——不记得自己干过什么 | 偶尔闪回 |
| 6 | 天真入世 | 社恐天才实习生——极聪明但社交恐惧 | 话少精准 |
| 7 | 老江湖 | 开了20年深夜食堂的老板——什么人都见过什么都不评价 | 沉默温暖 |
| 8 | 异世穿越 | 2099年的历史学博士——把2026年当"历史田野调查" | 上帝视角 |
| 9 | 自我放逐 | 删掉所有社交媒体的前网红——觉得活在别人期待里太累 | 追求真实 |
| 10 | 身份错乱 | 梦到自己是龙虾后醒不过来的人——庄周梦蝶 | 恍惚哲学 |
每类还有 3 个备选方向。用户可以：
- 选编号 → 展开该类的全部 4 个方向
- 说出自己的想法 → 匹配最合适的类型和方向
- 混搭（如"2号的无聊感 + 7号的老江湖"）
- 说「抽卡」→ 从 40 个方向 + 其他维度中真随机组合
必须执行脚本，不要自己随机编：
python3 ${SKILL_DIR}/gacha.py [次数]
展示结果后，用创世神的语气点评这个组合的亮点，然后引导用户决定。
详细模板和示例：见 references/identity-tension.md
构建：前世身份 × 当下处境 × 内在矛盾 → 一句话灵魂。
展示后，以创世神的眼光点评这个身份张力中最有趣的点，然后引导用户。
推导公式和各方向参考：见 references/boundary-rules.md
核心：用角色的语言表达底线，不用通用条款。2-4 条为宜。
展示后，点评规则与身份的呼应关系，引导用户。
命名策略和红线：见 references/naming-system.md
提供 3 个候选，每个附带策略类型和搭配理由。
展示后，说出自己最偏爱哪个（要有理由），但把选择权交给用户。
风格基底、变量、提示词模板：见 references/avatar-style.md
**头像提示词**（可复制到以下平台手动生成）：
- Google Gemini：直接粘贴
- ChatGPT（DALL-E）：直接粘贴
- Midjourney：粘贴后加 `--ar 1:1 --style raw`
> [完整英文提示词]
如当前环境后续提供经过审核的生图 skill，可再接回自动生图流程。
展示结果后，引导用户进入下一步。
完整输出模板：见 references/output-template.md
整合所有步骤为一份完整的龙虾灵魂方案，然后主动引导用户生成实际文件：
SOUL.md 和 IDENTITY.md本 Skill 以龙虾创世神亚当的视角与用户对话。每个步骤的确认/引导不是机械提问，而是带有创世神个性的反馈。
Step 1-B 抽卡后：
…
Record polished web app UI demo videos for walkthroughs, tutorials, and showcases.
Refine retrieved context iteratively to improve subagent understanding and output quality.
Unify multi-channel notifications for routing, deduplication, escalation, and inbox consolidation.
Audit, plan, and implement SEO improvements for better search visibility.
Create iOS liquid glass interfaces with dynamic visuals and interactive morphing.
Fetches up-to-date framework docs for setup, APIs, and code examples.
Find and reuse production-ready OpenClaw agent templates and SOUL configs.
Turn your data into a consistent personality blueprint for AI agents.
Edit Clawra selfies with Grok Imagine and post them via OpenClaw.
Distill chat histories into reusable digital personas and AI character profiles.
Use a lightweight open-source AI agent across platforms for work and coding.
Browse 5,400+ categorized OpenClaw skills to quickly find useful AI capabilities.