Change Impact logo

Change Impact

Community
qshanx
change-impact

在改代码、数据、接口或治理文档前做有证据的影响分析,并在实施后把计划影响与实际 diff 对照;覆盖代码调用、数据/Schema、API 契约、测试、文档、ADR、部署、迁移和回滚。用于跨模块修改、高风险变更、数据库迁移、认证、公共接口、用户问“会影响哪里”“改之前检查一下”或实施后需要反思偏差时。English triggers: change impact analysis, blast radius, pre-change analysis, migration impact, rollback plan, post-implementation alignment.

Overview

Publisherqshanx
Repositorydocs-governance
Skill namechange-impact
Stars
228
Forks
4
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by qshanx on GitHub. Read the source before you install it.

Installation

Install the Change Impact AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/qshanx/docs-governance/tree/main/skills/engineering/change-impact
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/qshanx/docs-governance.git /tmp/docs-governance
mkdir -p .claude/skills
cp -r /tmp/docs-governance/skills/engineering/change-impact .claude/skills/change-impact
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Change Impact in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Change Impact on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Change Impact is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

变更影响分析

默认只读。先用真实依赖与现有文档证明影响面,再实施;未知项明确标“未验证”。

修改前

依次回答:

  1. 代码:入口、直接调用方、下游消费者、生成物和兼容层会受什么影响?
  2. 数据:Schema、迁移、历史数据、序列化、缓存和幂等键是否变化?
  3. 接口:API、消息、文件格式或 CLI 是否改变?消费者和提供者分别是谁?
  4. 测试:哪些成功标准、TEST-ID、契约测试和回归命令应证明变更正确?
  5. 文档:是否影响 MAP、ARCHITECTURE、STATUS、LOG、CONTEXT、ADR、CONTRACT、Spec/Plan、TESTS 或 REGRESSION?
  6. 发布:部署顺序、兼容窗口、数据恢复、回滚命令和不可逆部分是什么?

证据优先取自真实 import/调用、路由、Schema、配置、生成脚本、git grep、git diff 和可执行测试。不要凭目录名猜依赖。

路由规则

  • 模块职责、公共入口、依赖或状态写入变化:修改前后执行 architecture-docs 的“模块文档与代码边界一致性”;读取双方适用的模块入口、CONTEXT 与契约,输出约定到代码的证据和未知项。方法只在该 Skill 维护,不以本次入口文档有 diff 代替检查。

  • 架构、数据库、认证、部署拓扑或长期技术策略:检查 domain-modeling / ADR。

  • 跨端接口:先更新 contract-first 管理的唯一契约源,再规划消费者、提供者和联调证据。

  • 需求、业务规则、风险或 Bug:让成功标准保留在 Spec/Issue,并用 test-collaboration 关联 TEST-ID。

  • Module 行为或下游依赖变化:实施后运行 module-regression;若权责、状态归属、Interface、依赖方向或核心流转改变,调用 architecture-docs 判断必要性并维护实际架构主记录,确保 MAP 能导航;无需创建或证据不足时说明依据与缺口。

  • 数据库迁移、破坏性接口、认证和生产发布:必须写回滚条件、恢复步骤、兼容期和不可逆部分;缺任何一项就标为阻塞,不代替人执行回滚。

输出

小改动在回复中给出:影响对象、证据、所需验证、文档同步和未知项。只有跨模块、高风险或用户明确要求留档时,才把报告写入 docs/impacts/;写文件前先确认,避免制造一次性文档。

按事实核对文档

解决“AI 改完功能或接口,用户还得自己找漏改文档,下一轮又被旧说明误导”的问题。候选检索由 Agent 执行并完成判读,向用户交付具体冲突、依据和处理结果,不把原始候选清单当成完成。

变更后的语义审查与阶段同步共用此流程。先通过现有确定性审计,再由当前 Agent 执行;路径映射、文件修改时间、Markdown 已产生 diff 或扫描退出码 0 都不能代替内容核对。

先单独运行 python3 <插件目录>/scripts/audit-docs.py --root <项目根> --scope full 并检查退出码;非零就停止候选检索、语义核对及据此进行的文档同步。即使判断是原有问题或误报,也须修复并复跑通过后再继续;超出授权或无法修复时报告阻塞。不用分号或忽略失败的命令串绕过此步骤。已提交审查须对受检快照审计,可复用同一 base/head 的 PR 检查结果。

先自动收集候选,再执行下方判读;输出是线索,不是过期结论:

bash
# 已提交变更:比较共同祖先与 head,只读提交快照
python3 <插件目录>/scripts/find-doc-impact.py --root <项目根> --base <基线> --head <受检提交>
# 日常维护:比较任务开始时的提交与当前文件,含未提交及非忽略的未跟踪文件
python3 <插件目录>/scripts/find-doc-impact.py --root <项目根> --base <任务起点> --worktree

检索合并 change_rules、变更路径引用、diff 中的标识符,返回候选路径、行号、原文和命中依据。功能变化补充 --term '功能名' 或旧流程术语,重点核对 Spec、使用说明与相关流程;契约变化重点核对机器契约引用、API 说明、调用示例与接入指南。架构、MAP、STATUS、LOG 按实际影响核对,不要求每次全改。

候选包括历史与无关同名内容,须读上下文排除;标识符未变的行为变化、同义表达和外部资料仍需 Agent 补查。无命中不能判无影响;报告跳过文件、不可访问资料及检索范围。退出 0 仅表示检索完成,退出 2 表示执行失败。没有可靠基线时列出缺口并按文档当前声明核对,不伪造变更范围。需求与实现冲突分别报告,不自动改写已确认 Spec。

  1. 固定范围和版本。 记录实际 base/head 提交及其共同祖先,以共同祖先为比较起点,读取该起点与 head 的 diff 和旧/新正文;不要把当前工作区修复当作已提交内容。审查未提交修改时另列暂存/未暂存/未跟踪范围及相关文件哈希。基线或来源缺失时标未验证,不猜旧规则。
  2. 提取改变的事实。 从代码、机器契约、配置及已确认需求中核对旧值、新值和原因,覆盖接口输入输出、流程步骤/条件、职责、依赖和外部副作用。契约删除一个字段并新增另一个字段,只能先记为删除/新增;有确认来源或实现证据才称重命名。内部修复若未改变对外事实,记录依据后结束相应同步检查。
  3. 找到主记录与引用。 从项目地图、契约入口、需求主记录及 change_rules 命中项开始,再用 rg/git grep 查变更对象的路径、旧标识和相关术语,沿链接补读映射外的说明。已提交审查应对 head 快照检索。无链接但描述同一事实的说明也要核对;检索无结果不证明没有遗漏,记录实际检索范围及不可访问对象。
  4. 逐条判读候选。 阅读命中位置的上下文,确认是否属于同一接口/流程、是否仍作为当前操作依据。当前正文与新事实冲突时给出具体位置、旧表述和对照证据,文件本次改过也不能跳过。历史记录、引用和无关同名字段不因关键词命中而要求改写;历史内容仍被当作当前指引时,报告误用它的入口。纯引用且目标有效时说明无需同步正文。
  5. 核对重复与证据。 同一生效规则若有可独立编辑的多份正文,列出主记录与副本,建议其余位置改引用;主源不明先待核实,不自行选一份覆盖。机器契约、实现和历史各自承担职责,不按相同词句数量判重复。测试结果引用原始回执及对应版本/输入哈希,结果缺失或已过期时标未验证,不重抄结果补齐表格。
  6. 交付并按变化失效。 在现有回复、PR 或审查记录中输出下表,绑定范围与版本。相关契约、代码或文档变化后重核受影响项,旧结论不自动沿用。不新建同步台账,不因普通待复核项一律阻断提交;沿用项目已有风险与合并要求。
事实变化及依据文档位置与原表述结论与下一步
旧/新事实,来源路径与版本路径、行号/条款、必要短引文;重复项另指主记录已核对:需要更新/无需更新及理由;待复核:候选尚未判读;未验证:缺少何种来源或执行证据

先报告需要更新的当前说明,再列无需更新的反例和剩余缺口。没有实际运行文档中的步骤时,不声称已复现失败;未知项不能计入通过。治理成本只记录本轮实际核对、修改的文档及原始回执位置,耗时未测就注明未知,不预设节省比例。

可复跑的接口字段样例及审查验收见 接口变更场景。它只验证这一切片,不代表所有事实类型或业务项目都已覆盖。

实施后对照

完成实现后检查:

  1. 实际改动是否解决 Spec/Issue 中的原始问题。
  2. 实际 diff 是否超出已声明范围;超出项是否获得授权并补充影响分析。
  3. 测试和人工证据是否真正覆盖成功标准,而非只证明命令运行过。
  4. CONTEXT、ADR、CONTRACT、TESTS、REGRESSION、MAP、ARCHITECTURE、STATUS 和 LOG 是否按实际变化同步。
  5. 是否遗留临时代码、兼容逻辑、迁移尾项或后续 Issue。

默认在交付回复中报告对照结论。只有高风险变更或用户要求正式评审时,才保存到 docs/reviews/。不要创建通用 REFLECTION.md。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Change Impact AI skill do?

在改代码、数据、接口或治理文档前做有证据的影响分析,并在实施后把计划影响与实际 diff 对照;覆盖代码调用、数据/Schema、API 契约、测试、文档、ADR、部署、迁移和回滚。用于跨模块修改、高风险变更、数据库迁移、认证、公共接口、用户问“会影响哪里”“改之前检查一下”或实施后需要反思偏差时。English triggers: change impact analysis, blast radius, pre-change analysis, migration impact, rollback plan, post-implementation alignment.

Why use Change Impact on TypingMind?

Because you install it once and use it with any model. Change Impact is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Change Impact in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/qshanx/docs-governance/tree/main/skills/engineering/change-impact. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Change Impact?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Change Impact?

As many as you like. As long as a model supports skills, you can use Change Impact with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Change Impact AI skill free?

Yes. It is published on GitHub by qshanx under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇