AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Siyu Report

skill-maojiebc-majia-siyu-team-siyu-report · by maojiebc

|

No reviews yet
0 installs
8 views
0.0% view→install

Install

$ agentstack add skill-maojiebc-majia-siyu-team-siyu-report

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-maojiebc-majia-siyu-team-siyu-report)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
17d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Siyu Report? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

siyu-report:客户咨询报告

只从 ~/.siyu/clients/{客户}/ 的存档合并报告,不从当前对话凭空发挥。报告属于跨对话客户档案;.siyu-team/ 仍只是一轮团长编排的运行时状态。

用户措辞

对用户说「客户」「存档」「对话」,不说 slug、snapshot、session。报告本身保持克制、可追溯,不加感叹号或鼓励语。

触发方式

| 命令 | 行为 | |---|---| | /siyu-report | 合并当前客户全部存档 | | /siyu-report --client | 指定客户 | | /siyu-report --since YYYY-MM-DD | 只取指定日期之后的存档 |

工作流程

1. 确认数据

  • 0 份:说明先用 /siyu-save 累积结论。
  • 1 份:说明单份可以直接阅读;用户仍要报告时继续。
  • 至少 2 份:直接合并。

路径必须限定在 ~/.siyu/clients/,禁止路径穿越。按文件名前缀从早到晚读取,不依赖 mtime。

2. 解析并追溯

读取每份档案的 frontmatter 和六段正文。格式不完整时使用现有字段并在附录标注缺失,不猜造。合并规则:

  • 主诉按时间展示演进,只总结关注点变化,不推测原因。
  • 结论语义去重;后续修正旧结论时两条都保留,旧条目标「已被后续修正」。
  • 否决方向原样保留理由。
  • 未解决问题取进行中档案的待验证假设,以及从未被后续处理的方向。
  • 下一步优先使用最新档案,其次是反复出现但未完成的建议。

3. 写入新报告

~/.siyu/reports/{客户}/{YYYYMMDD-HHMMSS}-{客户}-私域咨询报告.md

永不覆盖已有报告。固定结构:

# {客户} 私域咨询报告

**生成时间**:{本地时间}
**累积存档**:{N} 份({最早日期}—{最新日期})
**主要使用的能力**:{source_skill 去重}

## 一、客户主诉的演进
## 二、已确认的结论
## 三、已否决的方向
## 四、当前未解决的问题
## 五、推荐下一步
## 六、合规记录
## 七、附录:存档索引

由私域专家团生成。

每条结论标注来源标题和日期;附录列日期、标题、中文状态、来源能力和原文件路径。

4. 交付前合规扫描

先写到报告路径,再运行:

PYTHONPATH=src python3 -m siyu_team.eval.cli score "{报告路径}" --threshold 0
  • 命中 COMPLIANCE_RED:不得交付。定位命中句,基于原存档做合规改写;不能安全改写时停止并让用户确认。
  • 未命中:在「合规记录」写扫描时间与结果,再完成交付。
  • 不得删除或绕过 COMPLIANCE_RED 硬卡。

5. 回执

> 报告已生成:{路径}。合并 {N} 份存档({起始日期}—{结束日期}),合规扫描通过。

只给路径、数量、跨度和扫描结果,不复述报告正文。

边界

  • 存档冲突:全部保留并标注修正关系。
  • 敏感信息:生成前提醒报告会原样合并本地档案;需要脱敏时先征得用户确认。
  • 只输出 markdown,不主动转 PDF 或 HTML。
  • 一律中文,遵循《中文文案排版指北》。

不知道下一步用哪个 skill?

输入 /siyu

这是私域工具箱的导航入口。它会读取刚才的具体结论,选择当前最值得处理的一个方向, 并直接路由到对应 skill。迷路了就回 /siyu

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.