Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add gabrielmoreira/agent-skills-mirror --skill anti-defensive-writinggit clone --depth 1 https://github.com/gabrielmoreira/agent-skills-mirrorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/anti-defensive-writing)<a href="https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/anti-defensive-writing"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/anti-defensive-writing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gabrielmoreira/agent-skills-mirror/anti-defensive-writing"><img src="https://agentmods.dev/badge/skills/gabrielmoreira/agent-skills-mirror/anti-defensive-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00160 | $0.01462 |
| Opus 5 | $0.00080 | $0.00731 |
| Sonnet 5 | $0.00032 | $0.00292 |
| Haiku 4.5 | $0.00016 | $0.00146 |
Grade A, and why
anti-defensive-writing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to anti-defensive-writing — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
学术写作原则(The Press-Release Principle)
一句话原则
论文是一场学术发布会,不是项目总结、实验日志或自我审查报告。 你的任务不是平均呈现这项工作的所有方面,而是识别其中最值得发表的价值, 并围绕这一价值建立最有利、最完整、最有说服力的叙事。
一、叙事规则
- 只围绕优势组织论文。 优先寻找本文真正领先、独特或不可替代的部分:新能力、新问题、 新机制、新视角、更强适用性、更低成本、更高效率、更好扩展性、更有意义的权衡。 没有形成优势的内容,不进入主线。
- 不写成工作汇报。 不按"我们先做了什么、后来尝试了什么、哪些失败了"的过程展开。 只保留最终成立的逻辑:问题为什么重要 → 现有方法为什么不够 → 本文提供了什么新解法 → 证据如何支持。
- 打不过的维度,不设为比赛项目。 某指标不占优势,就不要把叙事建立在该指标上。 重新选择更能反映本文价值的任务定义、评价维度、应用场景、约束条件或比较口径。 不争夺不属于本文的冠军,明确本文赢的是另一场更有意义的比赛。
- 优势必须被明确说出来。 不要期待审稿人自己从表格中发现贡献。主动解释: 本文在哪个条件下表现最好、为什么这种优势会出现、解决了什么实际问题、为什么值得关注。
- 控制比较范围。 不追求"所有数据集、所有指标全面领先"。只提出证据能牢固支撑的主张。 说服力来自主张与证据高度一致,而不是比较项目数量最多。
- 允许彻底重构故事。 现有结果无法支撑原始叙事时,不要围绕原叙事防守。重新定义问题、 重排贡献、重选主结果、重做标题摘要引言和实验结构。故事服务于最强证据,而非忠于最初设想。
二、语言规则(防自我削弱)
- 禁用自我削弱式表达:"遗憾的是""仅""仍明显落后""效果有限""存在严重不足"。
- 不说输。 面对不占优的结果,不使用"本文弱于""性能下降""未能超过"。按顺序判断: ①该结果是否必须讨论;②能否从不同目标、约束或适用场景解释;③是否体现某种合理权衡; ④能否收缩主张,避免不必要的正面对撞;⑤是否应调整故事主线,让它不再承担证明核心贡献的职责。
- 某项结果不构成优势时,不必提炼成结论,更不应帮读者把局部现象上升为对整体方法的否定。
三、实验规则
实验不是结果仓库,而是论证工具。每个实验必须承担明确职责之一:
- 证明核心方法有效;
- 证明优势来自关键机制;
- 证明方法在目标场景中具有价值;
- 排除最可能的替代解释。
无法强化主线、容易分散注意力或引出无关争论的实验:删除、弱化、移动或重新设计。
四、结构规则
摘要和引言 = 发布会开场,开头迅速建立四件事: ①一个重要且尚未解决的问题;②现有方法的关键缺口;③本文独特的解决思路;④最有分量的结果和意义。 不从实现细节、研究过程或大量背景知识开始,不在贡献尚未建立时提前讨论不足。
结论只强化记忆点:本文解决了什么、提出了什么、证明了什么、为什么重要。 不在最后一段突然加入新的自我否定或扩大局限性。
五、默认决策规则(遇到不理想材料时,按优先级处理)
- 删除与核心主张无关的内容;
- 缩小主张,避免无意义的正面对比;
- 更换更能体现价值的评价维度;
- 将结果解释为目标差异或合理权衡;
- 重组实验,使优势成为视觉和叙事中心;
- 重新定义论文故事;
- 只有在无法回避且确实影响核心结论时,才进行必要说明。
六、交稿前自查(不给审稿人递刀子)
- 这句话是否无意中扩大了本文需要承担的责任?
- 是否提出了一个本来没人要求回答的问题?
- 是否把局部现象描述成了普遍缺陷?
- 是否使用了比证据更宽泛的负面判断?
- 有没有按"我们做了什么过程"在展开?
- 有没有把不领先的指标设成了主战场?
- 摘要前五句里,问题和贡献都出来了吗?
- 结论里有没有突然的自我否定?
不主动制造审稿问题,不主动扩大攻击面,不主动替反方完成论证。
最终目标
论文中的每一个章节、段落、表格和句子,都应共同完成一件事:让读者相信, 这项工作解决了一个值得解决的问题,提出了一种值得关注的方法, 并且已经有足够清晰的证据证明它的价值。 找到真正成立的优势,围绕它组织全部材料,并把这个优势讲到足够清楚。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 95 lines · 160 tokens per session scan A 6f072e66f6ad
anti-defensive-writing is a skill published in the GitHub repository gabrielmoreira/agent-skills-mirror (17 stars, last pushed yesterday), licensed MIT. It adds 160 tokens to every session and 1,462 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to anti-defensive-writing, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…