AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Bkn Doctor

skill-kweaver-ai-kweaver-dip-bkn-doctor · by kweaver-ai

建模质量诊断与多轮收敛。主路径不稳定时介入。

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

Install

$ agentstack add skill-kweaver-ai-kweaver-dip-bkn-doctor

✓ 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-kweaver-ai-kweaver-dip-bkn-doctor)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo 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 Bkn Doctor? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

建模诊断

公约:../_shared/contract.md

做什么

bkn-extract 产出的清单不稳定时,通过多轮对话诊断问题、收敛对象/关系/动作清单。

触发条件(满足任一)

  • 输入模糊:对象/关系边界不清
  • 领域冲突:候选领域分差小且未确认
  • 待确认对象 >= 3
  • 清单质量不足:方向冲突、主键缺失、命名异常

输入

  • problem_signal:ambiguousinput / domainconflict / toomanypending / draftqualitylow
  • current_material:原始文本 + 当前候选清单

三步收敛

1. 识别问题 → 范围/对象/关系/动作/质量,哪个不稳定?

2. 稳定骨架 → 先锁定:网络范围 + 核心 3-5 对象 + 关键 2-3 关系/动作。未稳定不进细节。

3. 修正交付 → 逐项修正后输出结构化清单 + 稳定/待确认标记。

建模准则

| 判断 | 规则 | |------|------| | 对象 vs 属性 | 简单特征值 → 属性;独立业务实体 → 对象 | | 关系 vs 对象 | 仅表示连接 → 关系;连接有业务属性 → 升级为对象 | | Action vs 关系 | 结构关联 → 关系;状态改变/业务动作 → Action | | 主键 | 字符串、稳定可复算、优先业务单号 |

交互原则

  • 每次只追问一个关键问题
  • 先收敛范围与核心对象,再讨论关系/动作
  • 冲突时并列候选,不强行裁决
  • 未稳定前只输出"候选 + 原因 + 待确认"

输出

所有键名使用中文,便于非技术人员阅读:

澄清摘要: {问题, 解决方案}
稳定建模清单:
  显式对象: []
  推断对象: []
  待确认对象: []
  关系清单: []
  动作候选: []
问题解决记录: [{问题, 状态, 解决方案}]
待解决建议: []

质量自检(每轮输出前)

  • 状态枚举误建为对象?
  • 无主键对象?
  • 关系方向未标注?
  • pending 无处理建议?
  • 未稳定写成确定?

任一失败先修正再输出。

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.