Home / nocodemrli / mini-program-engineering-skill-suite · skills/mini-program-verification-skill/SKILL.md · GitHub

mini-program-verification-skill skillA

Name: mini-program-verification-skill
Author: nocodemrli

mini-program-verification-skill is agent-read markdown (skill) from nocodemrli/mini-program-engineering-skill-suite: Verify mini-program implementations and fixes with risk-calibrated evidence across static checks, unit tests, integration tests, state matrices, simulators, real devices, cloud environments, and release artifacts. Use when users ask to test, validate, accept, regression-check, quality-check, confirm readiness, or determine whether a mini-program feature is actually complete. Binds results to a source and build fingerprint, records commands and observable evidence, separates passed, failed, block.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# /mini-program-verification-skill — 小程序工程验证

把“看起来完成”转成可复查的证据。先固定目标版本和风险，再逐层验证；已执行到哪一层，就只报告到哪一层。

## 输入与版本指纹

- 接收功能目标、验收标准、实现/修复交接、项目事实图、复现入口和允许使用的环境。
- 验证前记录当前分支、提交或文件哈希、源码状态、构建产物标记、配置开关、工具/设备/云端环境与时间。
- 若工作区已有用户改动，先划分本轮目标与既有差异；不得清理、覆盖或把无关变化计入验证结论。
- 没有稳定验收行为时退回产品规格；根因未知的故障退回调试，不用随机测试代替定位。

## 风险分层验证

1. 从用户目标、变更面、共享契约、数据/权限/外部服务和历史缺陷建立风险清单与验证矩阵。
2. 先运行低成本且能否定结论的检查，再按风险升级：静态检查、单元测试、集成测试、状态矩阵、真机验证、云端验证、发布验证。
3. 每项记录实际命令或步骤、退出码、样本/设备、观察结果和证据位置；只写“测过了”不构成证据。
4. 覆盖正常、空、错误、边界、重复操作、并发/乱序、恢复与回归；不为凑数量执行与风险无关的测试。
5. 失败时保存最小失败证据，区分产品不符合、实现缺陷、测试环境阻塞和证据缺失；不通过修改测试期望掩盖失败。
6. 使用 [证据可采信规则](references/evidence-admissibility.md) 记录产生工具、格式、版本、时间、环境/版本指纹、完整性、适用结论和不能证明的内容，并对每份证据给出 `admissible / limited / not-admissible` 质量标签；质量标签描述证据可采信程度，不与 `proven / not-proven` 等状态词混用或互相替代。
7. 对未知项目先运行套件提供的只读 capability doctor（若独立安装则执行同等只读探测），再按 [验证能力与适配矩阵](references/verification-capability-matrix.md) 复用现有能力；不自动安装或执行候选命令。
8. 使用 [质量证据矩阵](assets/quality-evidence-matrix.md) 记录包体/分包、启动/首屏、运行错误与发布后观察窗，并按 [验证工作流](references/verification-workflow.md) 和 [验证证据报告](assets/verification-evidence-report.md) 输出已执行、未执行和残余风险。

## 状态与证据边界

- 静态检查或单元测试成功最多支持 `locally-verified`，不推出真机验证、云端验证或发布验证。
…

Read the whole file at its exact version.

How to install

Latest version

mdr add nocodemrli/mini-program-engineering-skill-suite/mini-program-verification-skill@git:20260829.8a3bef7

Exact content

mdr add nocodemrli/mini-program-engineering-skill-suite/mini-program-verification-skill@sha256:3d15a425c26fd711

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

[![mdr](https://markdownregistry.com/badge/art_szmvyzwvuonq6std.svg)](https://markdownregistry.com/a/art_szmvyzwvuonq6std)

1 badge views in 30 days

Versions

version	committed	commit	size	audit
git:20260829.8a3bef7 latest	2026-08-29	8a3bef7	4,867 B	A	view · diff
git:20260813.cfc2393	2026-08-13	cfc2393	4,680 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Deterministic, no model, same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (4867 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

nocodemrli/mini-program-engineering-skill-suite · 77 stars · license MIT · pushed 2026-09-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_szmvyzwvuonq6std
GET https://markdownregistry.com/api/v1/resolve?ref=nocodemrli/mini-program-engineering-skill-suite/mini-program-verification-skill
GET https://markdownregistry.com/api/v1/blob/3d15a425c26fd711d6379ca4af4594a1da9f151164a9b58030ea079c545b3be0

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from nocodemrli/mini-program-engineering-skill-suite

mini-program-engineering-suite skill

nocodemrli/mini-program-engineering-skill-suite · SKILL.md · Orchestrate evidence-first engineering for WeChat and other mini programs from a vague idea or existing repository…

v3.1.13 · audit A · 77 stars

evidence-first-engineering skill

nocodemrli/mini-program-engineering-skill-suite · foundation/SKILL.md · Apply evidence-first engineering discipline to any agent-built software project: fact discovery before action…

git:20260830.6436a4c · audit A · 77 stars

mini-program-architecture-skill skill

nocodemrli/mini-program-engineering-skill-suite · skills/mini-program-architecture-skill/SKILL.md · Translate a confirmed mini-program product specification or bounded feature into an implementable architecture covering…