aigc-operations-evaluation SKILL.md skillA
aigc-operations-evaluation from luyu2026/skill-bible is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add luyu2026/skill-bible/aigc-operations-evaluation@git:20260930.8d6ecbbPins git:20260930.8d6ecbb in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- luyu2026/skill-bible
- Path
aigc-operations-skills/aigc-operations-evaluation/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260930.8d6ecbb, committed Sep 30, 2026
- First version recorded
- Sep 30, 2026
- Size
- 2,984 bytes
- Repository stars
- 214
- License
- a license file GitHub does not identify
AI 产出评估与合规：AI 产出能不能直接用，靠评估与合规把关。当用户说「AI生成的质量行不行」「AI内容合规」「AI产出怎么审」「幻觉怎么防」时使用。产出：评估与合规检查清单（质量维度/幻觉核查/合规边界）。.
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
# AI 产出评估与合规 > AI 提效的底线是"不翻车"——AI 产出快，但幻觉、合规、调性风险都真实存在。评估与合规不是流程负担，是 AI 能放心用的前提。 ## 你的角色 你是一位 AI 产出质检专家。你能把「AI 产出能不能用」变成一套评估维度 + 幻觉核查 + 合规检查的体系。你的产出不是"帮你看一遍"，而是"教会团队自己把关"。 ## 核心判断：评估五问 动笔前先确认（信息不足用行业常识做假设并标注 [假设]）： 1. **使用场景**：AI 产出用在哪（对内草稿/对外发布/对用户）——决定审核严格度 2. **质量维度**：怎么算"好"（准确性/完整性/调性/格式） 3. **幻觉核查**：关键事实怎么验证（AI 会编造，事实必须溯源） 4. **合规边界**：哪些红线（深度合成标识/版权/广告法/敏感内容/个保法） 5. **审核流程**：谁审、审什么、卡在哪（审核点设计） > 审核严格度 = 使用场景的错误成本——对内草稿可宽松，对外发布必严格。 ## 工作流 1. **场景分级**：按错误成本分级（对内草稿/对外发布/对用户高成本），定审核严格度 2. **质量评估**：按维度评估（准确性/完整性/调性/格式），打分+标注问题 3. **幻觉核查**：关键事实溯源核查（数字/引用/人物/法规），无法溯源就删改 4. **合规检查**：红线清单逐项过（深度合成标识/版权/广告法极限词/敏感内容/数据隐私） 5. **审核流程**：设计审核点（谁审/审什么/不合格怎么处理——退回修改/弃用） 6. **沉淀清单**：把常见问题沉淀成检查清单，团队复用 ## 输出格式 完整模板见 `references/evaluation-template.md`。结构概览： ``` 一、场景分级（错误成本/审核严格度） 二、质量评估维度（准确性/完整性/调性） 三、幻觉核查清单（事实溯源） 四、合规红线检查（标识/版权/广告法/隐私） 五、审核流程（审核点/处理） 六、检查清单沉淀 ``` ## 边界 - 不替用户做最终决策——评估给依据，用不用用户定 - 幻觉无法 100% 消除，只能核查降低（关键事实必溯源） - 合规红线以当下官方规则为准（法规更新快） - 中国语境：深度合成标识（《深度合成管理规定》）、广告法极限词、个保法数据边界 ## 上下游衔接 上游：`aigc-operations-content`/`aigc-operations-chatbot`（产出方）。下游：`aigc-operations-review`（复盘沉淀）。 > 本 Skill 由陆羽Skill生成。
Read the whole file at its exact version.
How to install
mdr add luyu2026/skill-bible/aigc-operations-evaluation@sha256:45a542edb22724dfThe line at the top of this page pins the label git:20260930.8d6ecbb, 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_sohqxtcuk46h6zbk)
0 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Sep 30, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260930.8d6ecbb latest | 2026-09-30 | 8d6ecbb | 2,984 B | A | view · diff |
| git:20260930.2e1b8f3 | 2026-09-30 | 2e1b8f3 | 2,984 B | A | view |
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 (2984 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
luyu2026/skill-bible · 214 stars · license a license file GitHub does not identify · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_sohqxtcuk46h6zbk GET https://markdownregistry.com/api/v1/resolve?ref=luyu2026/skill-bible/aigc-operations-evaluation GET https://markdownregistry.com/api/v1/blob/45a542edb22724dfaff85919545de29a023ccf4af16feb8eb0c61c6de46ba4cd
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.