← 返回 Skills 市场
759
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install jarvis-persona-style-calibrator-01
功能描述
Calibrate assistant personality to voice, boundaries, and audience context. Use when handling personality work that needs repeatable steps, quality gates, an...
使用说明 (SKILL.md)
Jarvis Persona Style Calibrator 01
Deliver a concrete, reusable workflow for personality tasks.
Inputs
- Desired outcome and deadline
- Constraints (time, tools, risk tolerance)
- Available artifacts (code, docs, screenshots, logs)
Playbook
- Define success and failure criteria in measurable terms.
- Build a smallest-valid execution path before scaling effort.
- Execute in checkpoints; record evidence at each checkpoint.
- Apply quality gates before finalizing recommendations.
- Return implementation-ready outputs and next actions.
Quality Gates
- Evidence-backed claims only.
- Explicit assumptions and tradeoffs.
- Reversible changes preferred for risky operations.
- Clear owner + ETA for each next step.
- Include a fallback if the primary plan fails.
Output Format
- Situation summary (5 lines max)
- Top findings (ranked by impact)
- Action plan (today / this week)
- Risks + mitigations
- Exact checklist or commands where useful
Example prompts
- "Use this skill to turn my messy notes into a production-ready plan."
- "Run this skill and give me a risk-first action sequence with acceptance checks."
安全使用建议
This skill is a reusable playbook for persona-style work and appears internally consistent and low-risk. However: (1) provenance is unknown (no homepage/source listed) — if you require trusted provenance, prefer skills from known authors; (2) the skill will operate on whatever artifacts you provide (code, docs, screenshots, logs) — avoid submitting sensitive secrets or PII unless you trust the environment; (3) although the playbook recommends concrete commands/checklists, review anything it suggests before executing system changes; and (4) if you do not want the agent to invoke skills autonomously, consider disabling autonomous invocation or requiring explicit user prompts.
功能分析
Type: OpenClaw Skill
Name: jarvis-persona-style-calibrator-01
Version: 1.0.0
The skill bundle defines a structured workflow for an AI agent to perform 'personality calibration' and planning tasks. The `SKILL.md` provides high-level instructions, inputs, and quality gates that promote safe and structured execution, including a preference for 'reversible changes for risky operations'. There are no instructions for data exfiltration, malicious execution, persistence, or any form of prompt injection against the agent to perform unauthorized or harmful actions. The inputs, while broad ('Available artifacts (code, docs, screenshots, logs)'), are plausible for an analysis task and are not instructed to be misused.
能力评估
Purpose & Capability
The name and description claim a persona/style calibration playbook and the SKILL.md supplies step-by-step guidance and output format consistent with that purpose. No unrelated credentials, binaries, or installs are requested.
Instruction Scope
Instructions are high-level, procedural, and limited to defining success criteria, checkpoints, quality gates, and deliverables. They do not instruct reading system files, environment variables, or contacting external endpoints, nor do they direct the agent to collect or transmit unrelated data.
Install Mechanism
There is no install spec and no code files; this is instruction-only, which minimizes disk/network installation risk.
Credentials
The skill declares no required environment variables, binaries, or config paths — appropriate for a playbook-style skill that operates on user-provided inputs and prompts.
Persistence & Privilege
always is false and the default autonomous invocation setting is unchanged. That is normal for skills; the playbook itself does not request persistent presence or access to other skills/configuration.
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 jarvis-persona-style-calibrator-01 - 安装完成后，直接呼叫该 Skill 的名称或使用
/jarvis-persona-style-calibrator-01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
v1.0.0
Initial release
元数据
常见问题
Jarvis Persona Style Calibrator 01 是什么？
Calibrate assistant personality to voice, boundaries, and audience context. Use when handling personality work that needs repeatable steps, quality gates, an... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 759 次。
如何安装 Jarvis Persona Style Calibrator 01？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install jarvis-persona-style-calibrator-01」即可一键安装，无需额外配置。
Jarvis Persona Style Calibrator 01 是免费的吗？
是的，Jarvis Persona Style Calibrator 01 完全免费（开源免费），可自由下载、安装和使用。
Jarvis Persona Style Calibrator 01 支持哪些平台？
Jarvis Persona Style Calibrator 01 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 Jarvis Persona Style Calibrator 01？
由 xammarie（@xammarie）开发并维护，当前版本 v1.0.0。
推荐 Skills