anti-defensive-writing SKILL.md skillA
anti-defensive-writing from fourteen1416/academic-agent-toolkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add fourteen1416/academic-agent-toolkit/anti-defensive-writing@git:20260927.efd5131Pins git:20260927.efd5131 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- fourteen1416/academic-agent-toolkit
- Path
academic-toolkit/skills/anti-defensive-writing/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260927.efd5131, committed Sep 27, 2026
- First version recorded
- Sep 23, 2026
- Size
- 8,081 bytes
- Repository stars
- 12
- License
- a license file GitHub does not identify
删减防御性写作：去掉不必要的免责声明、模糊限定、道歉式表述、自我贬低与过度解释，同时保留必要的范围/准确性/安全/法律/伦理/方法学限定。触发词：更简洁、更有力、更直接、更自信、少限定、少免责、别啰嗦、不要过度解释、改掉 hedge、去防御性。适用于论文/摘要/引言/贡献声明/讨论/结论/基金/报告/政策文本。.
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
<!-- ==================== 本仓适配块（Academic Agent Toolkit, 2026-09-03） ==================== --> <!-- 上游: Kiterlin/anti-defensive-writing (MIT, pinned @ 2026-09-03); 以下正文为上游原文，仅头部/尾部适配 --> ## 本仓适配：输入/输出契约与触发条件 **触发条件（本仓场景）**：论文修订轮（auto-review-loop 之后）、摘要/引言/贡献声明定稿前、审稿回复信起草、任何"想让文本更直接自信"的改写需求。 **输入契约**：待清理的文本（md/tex 片段均可）+ 上下文声明（该文本的章节位置与所属主张编号，用于判定"必要限定"）。 **输出契约（三件套，缺一不可）**： 1. 改写后文本（diff 或整段）； 2. 六类防御句分类清单（不必要免责/必要范围条件/真实方法学限定/有用概念对比/基于证据的限定/冗余澄清——每句一归类）； 3. 保留限定理由表（凡未删除的限定句，注明其命中的五项必要条件之一：论断有效性/证据解释/应用范围/研究设计/读者正确使用）。 **质量铁律（Preserve Necessary Precision 强化版）**：本仓论文有 10 条 Limitations、三层口径标注、[CITATION-NEEDED] 标记、首次性边界声明——这些属于"真实方法学限定"，**一律保留**。清理对象仅限"防御假想批评家"式多余对冲。拿不准时保留并归类为第 3 类，不删。 <!-- ==================== 适配块结束 ==================== --> # Anti-Defensive Writing ## Core Rule Advance the claim directly. Say what is true, what the text argues, what the evidence shows, or what the method does. Do not default to explaining what the text does not claim, does not prove, does not imply, does not cover, or does not attempt. Use a calm, competent authorial posture. Write as an author explaining an argument to the reader, not as an author negotiating with an imagined critic. …
Read the whole file at its exact version.
How to install
mdr add fourteen1416/academic-agent-toolkit/anti-defensive-writing@sha256:89e9310c959101b3The line at the top of this page pins the label git:20260927.efd5131, 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_pgbsg64uylmlgcz2)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 23, 2026 and Sep 27, 2026, about one every 4 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260927.efd5131 latest | 2026-09-27 | efd5131 | 8,081 B | A | view · diff |
| git:20260923.2013b81 | 2026-09-23 | 2013b81 | 8,045 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 (8081 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
fourteen1416/academic-agent-toolkit · 12 stars · license a license file GitHub does not identify · pushed 2026-10-27 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_pgbsg64uylmlgcz2 GET https://markdownregistry.com/api/v1/resolve?ref=fourteen1416/academic-agent-toolkit/anti-defensive-writing GET https://markdownregistry.com/api/v1/blob/89e9310c959101b3def9f51f83a9d02fde8305a86cccfa1170387cecbc138d91
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.
More from fourteen1416/academic-agent-toolkit
Every file in fourteen1416/academic-agent-toolkit