← 返回 Skills 市场
205
总下载
0
收藏
5
当前安装
1
版本数
在 OpenClaw 中安装
/install retro
功能描述
Deep blameless postmortem workflow—timeline, impact, root cause vs contributing factors, what went well/poorly, action items with owners, and follow-through....
安全使用建议
This skill is an instruction-only retro/postmortem workflow and appears coherent and low-risk. Before using it with an agent that can access your systems: (1) verify any integrations you enable for attaching logs/traces have minimal, read-only scope and appropriate retention controls; (2) ensure PII and sensitive security details are redacted per the skill's own advice; (3) for security incidents, follow your org's legal/infosec process rather than publishing details; and (4) review any auto-generated postmortem content before it is shared externally. No credentials or installs are required by the skill itself.
功能分析
Type: OpenClaw Skill
Name: retro
Version: 1.0.0
The 'retro' skill bundle is a purely procedural guide for conducting blameless postmortems after incidents or outages. It contains no executable code, shell commands, or network activity, and its instructions in SKILL.md are entirely focused on providing a structured workflow for documentation and analysis without any indicators of malicious intent or prompt injection risks.
能力评估
Purpose & Capability
The name and description (postmortem/retro workflow) match the SKILL.md content. The skill requests no binaries, env vars, or config paths — consistent with a facilitator/template-style instruction set.
Instruction Scope
Runtime instructions are procedural guidance (stages, checklists, tips). They do not instruct the agent to read arbitrary host files, call external endpoints, or exfiltrate data. The only operational suggestions are linking traces/metrics/logs and redacting PII, which are appropriate for the stated purpose.
Install Mechanism
No install spec or code files are present. As an instruction-only skill, it introduces no installation risk or downloaded code.
Credentials
The skill itself requires no credentials or environment access. However, the guidance suggests linking traces, metrics and logs in appendices; if you allow an agent to gather those artifacts, you must separately grant whichever integrations/credentials are needed. That potential need for log/trace access is expected for its purpose but worth guarding (read-only access, PII redaction).
Persistence & Privilege
The skill is not always-enabled and does not request persistent system presence or modify other skills. Default autonomous invocation is allowed by the platform but this skill's content does not demand elevated privileges.
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 retro - 安装完成后，直接呼叫该 Skill 的名称或使用
/retro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 of the retro skill: a structured, blameless postmortem workflow.
- Guides users through six stages: scoping, timeline, root cause analysis, review of what worked/failed, action items, and follow-up.
- Focuses on clear ownership of action items and distinguished root cause vs contributing factors.
- Emphasizes psychological safety and tailored communication for both internal and external audiences.
- Provides best practices, final review checklist, and specific guidance for security incidents.
元数据
常见问题
Retro 是什么？
Deep blameless postmortem workflow—timeline, impact, root cause vs contributing factors, what went well/poorly, action items with owners, and follow-through.... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 205 次。
如何安装 Retro？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install retro」即可一键安装，无需额外配置。
Retro 是免费的吗？
是的，Retro 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Retro 支持哪些平台？
Retro 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 Retro？
由 clawkk（@clawkk）开发并维护，当前版本 v1.0.0。
推荐 Skills