Repair Prevention Assessment logo

Repair Prevention Assessment

Organization
devcodex-labs
repair-prevention-assessment

修复防复发完成门禁 Owner — 任何 fix、self-fix 或 dev 中的 repair 切片在 accepted 前使用;形成可机器验证的 RepairPreventionAssessmentV1,分离当前关闭证据与长期前瞻有效性,避免 active 工作流依赖未部署的 gray 能力。

Overview

Publisherdevcodex-labs
Repositorydevcodex
Skill namerepair-prevention-assessment
Stars
433
Forks
44
Bundled files
2
LicenseAGPL-3.0
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.

  • 2 bundled files

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

  • Open source

    Published by devcodex-labs on GitHub. Read the source before you install it.

Installation

Install the Repair Prevention Assessment 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/devcodex-labs/devcodex/tree/main/content/skills/repair-prevention-assessment
  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/devcodex-labs/devcodex.git /tmp/devcodex
mkdir -p .claude/skills
cp -r /tmp/devcodex/content/skills/repair-prevention-assessment .claude/skills/repair-prevention-assessment
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Repair Prevention Assessment 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 Repair Prevention Assessment 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 Repair Prevention Assessment 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.

Repair Prevention Assessment

职责

本 Skill 是所有 repair task 的稳定、默认部署完成门禁,唯一拥有 RepairPreventionAssessmentGate 与 RepairPreventionAssessmentV1。它判断当前问题能否关闭,并要求为长期控制给出诚实的前瞻计划;不负责计算返工率、验证控制长期有效或自动晋级候选,这些试验性职责归 gray rework-prevention-engineering。

机器结构以 repair-prevention-assessment.schema.json 为准,确定性判定以 scripts/lib/repair-prevention-assessment.js 为准。其他 Skill、Prompt、报告与清单只能引用本 Owner,不复制字段定义。

RepairPreventionAssessmentGate

任何 repair——包括 fix、dev 中的修复切片、self-fix、审查 finding 修复与发布阻断修复——在 accepted 前必须形成有效 RepairPreventionAssessmentV1。当前修复重跑只允许进入 immediateClosureEvidence,不得写成长期 prevention 已有效。

双根因与证据

字段要求
defectRootCause缺陷、遗漏或错误判断本身为什么发生
controlFailure哪个需求、方案、实现、测试、复审或发布控制应拦截却未拦截
escapedFrom / detectedAt应发现阶段与真实发现阶段
regressionSeeds / negativeCases当前回归输入与能证明控制边界的负例
controlOwner / consumers控制真相源、执行消费者与验证消费者
immediateClosureEvidence当前 repair 的 fresh 关闭证据
prospectiveEvidencePlan后续可比较 WorkUnit、独立上下文、指标防作弊与回滚准备
rollbackOrSunset误报、成本或无效时的回退与退役条件

风险模式

  • 低/普通风险首次 repair 可使用 mode=light,但双根因、回归 seed、负例、当前关闭证据与 rollback/sunset 仍不可缺。
  • P0/P1、安全、控制面、公共契约、发布、多批次、角色交接、high/critical 或 repeat escape 必须 mode=full,追加 whyMissed / authorizationEvidence / independentReReviewPlan。
  • repeat escape 不得选择 no-new-control 或只恢复说明文案;必须使用 new-control-provisional,紧急高风险才允许 emergency-active。

preventionDecision

决策使用条件生命周期结论
existing-control-restored已有 active 控制因接线或执行偏差未生效保持既有控制;本次重跑不重新证明效果
new-control-provisional新增或实质修改 prompt/contract/checklist/probe/test/hook/tool新控制保持 gray/provisional,等待前瞻证据
no-new-control已有控制足够、一次性不可泛化、成本高于风险或无更早发现点必须使用标准 reason 与独立 evidence
emergency-activeP0、安全或高风险控制面必须先阻断active-expiring;必须有明确授权、补证与回退

prospectiveEvidencePlan.status=sufficient 只有在不少于 3 个可比 WorkUnit 或 2 个独立上下文、metricGaming=false 且 rollbackReady=true 时有效。当前事件唯一重跑必须保持 retrospective-only。

与 gray 返工工程的边界

  • 本 Skill 始终处理“当前 repair 能否 accepted”,属于 active correctness gate。
  • 只有用户或任务涉及返工率、一次通过率、重复逃逸簇、whyMissed 复发、PreventionHitRate 或长期效果判定时,才额外选择 gray rework-prevention-engineering。
  • active workflow 不得把 gray Skill 作为 mandatory dependency。gray 不可用时,本 Skill 仍须完整执行,不允许跳过 assessment。

验证与失败语义

最小验证:node scripts/test-repair-prevention-assessment.js,并由 V94、review checklist、report 与默认安装 replay 复证。以下任一情况阻断 accepted:

  • assessment 缺失、schema/identity 无效或风险模式不足;
  • immediate closure 与 prospective evidence 混写;
  • repeat escape 继续使用旧说明文字或无理由 no-new-control;
  • active consumer 强依赖默认不部署的 gray Skill;
  • mandatory Skill 未进入默认部署面;
  • rollback/sunset 或独立复审计划缺失。

反模式

  • 用“测试通过”同时证明当前修复与长期有效。
  • 为降低返工指标而隐藏 finding、缩小 WorkUnit 或把返工改名为计划迭代。
  • 把所有低风险 repair 扩大为完整事故报告。
  • 为避免生命周期拆分而无证据晋级 gray Skill。

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 Repair Prevention Assessment AI skill do?

修复防复发完成门禁 Owner — 任何 fix、self-fix 或 dev 中的 repair 切片在 accepted 前使用;形成可机器验证的 RepairPreventionAssessmentV1,分离当前关闭证据与长期前瞻有效性,避免 active 工作流依赖未部署的 gray 能力。

Why use Repair Prevention Assessment on TypingMind?

Because you install it once and use it with any model. Repair Prevention Assessment 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 Repair Prevention Assessment in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/devcodex-labs/devcodex/tree/main/content/skills/repair-prevention-assessment. 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 Repair Prevention Assessment?

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 Repair Prevention Assessment?

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

Is the Repair Prevention Assessment AI skill free?

Yes. It is published on GitHub by devcodex-labs under the AGPL-3.0 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 👇