lov-harness-issue SKILL.md skillA
lov-harness-issue from lovstudio/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add lovstudio/skills/lov-harness-issue@git:20260925.4b67fd1Pins git:20260925.4b67fd1 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- lovstudio/skills
- Path
skills/harness-issue/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260925.4b67fd1, committed Sep 25, 2026
- Size
- 4,914 bytes
- Repository stars
- 72
- License
- MIT
从用户角度深度、全面思考接下来的产品需求。Use when the user reports a product issue, bug, vague improvement request, confusing workflow, UX friction, or partial feature idea and Codex should harness the issue into underlying user goals, adjacent requirements, acceptance criteria, and a bounded execution plan before coding.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 需求解题师 · Product Problem Solver 把用户提交的局部问题转化为可执行的产品需求判断。重点不是扩大改动范围，而是站在真实用户视角，把“用户想完成什么、为什么当前体验不符合预期、接下来最该补齐什么”想清楚。 ## Core Rule 先理解用户目标，再决定实现范围。不要只消除报错或按字面修一个点；也不要借机重做整个产品。每次都把需求分层，明确哪些属于本次必须完成、哪些可以顺手补齐、哪些只作为后续建议。 ## Workflow 1. **Restate the user goal** - 将用户的问题改写成用户正在尝试完成的任务。 - 区分表层症状、真实目标、产品预期。 - 如果缺少关键信息，优先从代码、界面、文案、测试和现有产品结构中推断；只有无法安全推断时才询问用户。 2. **Map the current product path** - 找到用户进入该问题的路径：入口、操作步骤、数据状态、成功出口。 - 检查相邻状态：loading、empty、error、success、permission、offline、mobile、long content、invalid input。 - 对前端产品，实际运行页面或用浏览器/截图验证关键路径；不要只读代码猜测体验。 3. **Infer hidden requirements** - 从用户视角列出当前问题背后的隐含需求。 - 覆盖功能、交互、视觉层级、文案反馈、数据一致性、权限、性能感知、可恢复性。 - 标注每个需求的证据来源：用户原话、现有代码、产品惯例、验证结果或合理推断。 4. **Set the execution boundary** - **Must fix now**: 不完成就无法满足用户当前目标。 - **Should include now**: 与当前改动同路径、低风险、能明显补齐体验。 - **Follow-up**: 有价值但会扩大范围、需要产品决策或需要额外数据。 - **Out of scope**: 明确不做，避免无限扩展。 5. **Implement or plan** - 如果用户要求执行，直接实施 `Must fix now`，并在风险合理时包含 `Should include now`。 - 如果用户只要求分析，输出需求拆解和优先级，不改文件。 - 修改代码时保持范围紧凑，遵循项目既有模式；不要把需求推演变成无关重构。 6. **Verify from the user path** - 用用户路径验证，而不只是运行最低层测试。 - 对 UI/UX 问题，验证桌面和移动端的布局、状态反馈和主要交互。 …
Read the whole file at its exact version.
How to install
mdr add lovstudio/skills/lov-harness-issue@sha256:75da03099c4f2aeaThe line at the top of this page pins the label git:20260925.4b67fd1, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_m3icbbf5ee547wvq)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 25, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4914 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
lovstudio/skills · 72 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_m3icbbf5ee547wvq GET https://markdownregistry.com/api/v1/resolve?ref=lovstudio/skills/lov-harness-issue GET https://markdownregistry.com/api/v1/blob/75da03099c4f2aeadb528897af346ab637691ebfcf64c5a6e082c7a86033b8ff
Your AI assistant 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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.