correction SKILL.md skillA
correction from nxcoreai/everroom is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add nxcoreai/everroom/correction@git:20260902.7664a2bPins git:20260902.7664a2b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- nxcoreai/everroom
- Path
agents/room-corrector/skills/correction/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260902.7664a2b, committed Sep 2, 2026
- Size
- 1,842 bytes
- Repository stars
- 2,990
- License
- a license file GitHub does not identify
Compute Room overview corrections—citation corrections as per-claim edits and general corrections as a single proposal.
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
# Correction 按 task 计算 Room 总览的纠正；claims 列表是权威快照，一切 originalText 以其中的 claim 文本为准。 ## citation-correction（引用纠正） 1. 先从 selectedText（引用上下文）解析命中的 claim 与用户评论（instruction）；评论是最高权威。 2. **为每个命中 claim 提交一条独立 edit**：字段自带 targetClaimId、section、operation、originalText、replacementText 和非空 rationale，不得摊到根参数。 3. originalText 逐字取自目标 claim 文本（或引用文本中该 claim 的原文），不得转述；replacementText 是该 claim 的新内容。 4. 跨 claim 合并：替换保留的 claim 并对其余 claim 用 content_suppress；不得把多条 claim 拼成一条 originalText。 5. 选择 operation：改文字用 content_replace；仅修事实性错误用 fact_correct；新增内容用 content_add/fact_add；移除错误来源用 source_remove（需带 targetSource）；把 claim 归到其他来源用 source_reassign。 6. 指令与 claim 内容冲突时以指令为准；指令含糊到无法唯一定位目标时，在 summary 说明缺口，仍对可确定的部分给出 edits。 ## general-correction（模糊纠正） 1. 按 instruction（如"更新建议下一步""把简介改成……"）定位目标区块与 claim，计算一条 proposal。 2. 能唯一定位时填 targetClaimId 与 originalText（逐字）；新增类操作（content_add 等）可省略 originalText。 3. rationale 说明为什么这样改；不虚构证据。 ## 输出 citation-correction 提交 edits；general-correction 提交 proposal；summary 简述改了什么、依据什么。
Read the whole file at its exact version.
How to install
mdr add nxcoreai/everroom/correction@sha256:a25e5076301d2279The line at the top of this page pins the label git:20260902.7664a2b, 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_n3v62zzn63ynw5mq)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 2, 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 (1842 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
nxcoreai/everroom · 2,990 stars · license a license file GitHub does not identify · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_n3v62zzn63ynw5mq GET https://markdownregistry.com/api/v1/resolve?ref=nxcoreai/everroom/correction GET https://markdownregistry.com/api/v1/blob/a25e5076301d227902aa9c7a4293c75d75d19e8f94b24f7d33de2129ec11bd3d
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.