← 返回 Skills 市场
81
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install qcstory
功能描述
华与华 QCstory 周改善教练。 输入改善课题，AI 教练逐步引导完成松浦九条全流程： 明确课题 → 把握现状 → 设定目标 → 找出真因 → 制定对策 → 实施对策 → 基准化 → 反思 → 下一课题。 每步有标准点评，不合格引导修改，最终输出完整改善报告。
安全使用建议
This skill is instruction-only and appears internally consistent. Before installing: 1) Note the source/homepage is unknown—consider provenance risk if you require vendor accountability. 2) The coach will ask for quantitative metrics and problem descriptions—avoid entering sensitive PII, secrets, or proprietary documents into the conversation. 3) Because it runs as an AI conversational flow, it will use your agent/model to process inputs; ensure you are comfortable with that model's data handling. 4) If you want stricter control, keep the skill user-invocable (not always-enabled) so it only runs when you explicitly start it.
功能分析
Type: OpenClaw Skill
Name: qcstory
Version: 1.0.0
The skill bundle defines an AI agent as a 'QCstory Improvement Coach' through `SKILL.md` and `qcstory.md`. These files contain detailed instructions for conversational flow, persona, and content generation to guide users through a 9-step improvement process. There are no instructions for the agent to perform any actions beyond generating text, such as executing shell commands, accessing sensitive files, or making network requests. The 'forbidden behaviors' specified are guardrails to ensure adherence to the coaching methodology, not malicious prompts or vulnerabilities.
能力评估
Purpose & Capability
Name and description match the SKILL.md and qcstory.md content: both specify a step-by-step QCstory (松浦九条) coach. The skill requests no binaries, env vars, or config paths — appropriate for a purely conversational guide.
Instruction Scope
Instructions are narrowly scoped to interactive, stepwise guidance (one step at a time), data collection from the user, and producing a formatted improvement report. There are no instructions to read local files, access system state, or send data to external endpoints beyond normal model usage.
Install Mechanism
No install spec and no code files that would be written to disk or executed. Being instruction-only minimizes installation risk.
Credentials
No environment variables, credentials, or config paths are requested. The skill's needs are proportional to its described conversational coaching function.
Persistence & Privilege
always is false and the skill does not request persistent system privileges or modify other skills. Autonomous invocation is allowed by default on the platform, which is expected for a conversational skill.
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 qcstory - 安装完成后，直接呼叫该 Skill 的名称或使用
/qcstory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 qcstory-coach: AI-based weekly QCstory improvement coach
- Guides users step-by-step through the full 松浦九条 (QCstory nine steps) process, from topic clarification to follow-up.
- At each step, provides explanation, example, and prompts for user input; reviews responses for completeness.
- Enforces standards: rejects vague statements, abstract measures, and missing quantitative data or targets.
- Produces a complete formatted improvement report after all steps are completed.
- Specifically tailored for 华与华 QCstory teams; Chinese interaction and process support.
- Clearly outlines both best practices and common anti-patterns for effective improvement activities.
元数据
常见问题
qcstory 是什么？
华与华 QCstory 周改善教练。 输入改善课题，AI 教练逐步引导完成松浦九条全流程： 明确课题 → 把握现状 → 设定目标 → 找出真因 → 制定对策 → 实施对策 → 基准化 → 反思 → 下一课题。 每步有标准点评，不合格引导修改，最终输出完整改善报告。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 81 次。
如何安装 qcstory？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install qcstory」即可一键安装，无需额外配置。
qcstory 是免费的吗？
是的，qcstory 完全免费（开源免费），可自由下载、安装和使用。
qcstory 支持哪些平台？
qcstory 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 qcstory？
由 CoCokkxy（@cocokkxy）开发并维护，当前版本 v1.0.0。
推荐 Skills