#273 by GitHub stars
Adkid-Zephyr/anti-defensive-writing-Skill
极致轻量|阻止论文的防御性写作 | Anti-defensive writing for academic papers — 学术写作原则 Skill + prompt pack (CN/EN)
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/anti-defensive-writing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
82d31402caa0 → 82d31402caa0
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
82d31402caa0 → 82d31402caa0
skills/anti-defensive-writing-en/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
82d31402caa0 → 82d31402caa0
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
82d31402caa0 → 82d31402caa0
Heat
7.3- Star growth, last 7 daysAhead of 99% of tracked repositories
- Star growth, last 24 hoursAhead of 99% of tracked repositories
- Rank movement, last 7 daysAhead of 93% of tracked repositories
- Commits, last 30 daysAhead of 0% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- anti-defensive-writing
skills/anti-defensive-writing - anti-defensive-writing-en
skills/anti-defensive-writing-en
How it works
anti-defensive-writing
When your agent uses it
论文写作、修改、压缩和实验组织全流程中阻止【防御性写作】。把论文视为一场学术发布会, 而不是项目总结、实验日志或自我审查报告:识别这项工作最值得发表的价值,围绕它建立 最有利、最完整、最有说服力的叙事。不平均展示、不主动示弱、不写实验流水账、不替审稿人 攻击自己。 触发词:论文润色、论文修改、写摘要、写引言、写结论、压缩论文、rebuttal、回复审稿意见、 组织实验、论文AI味、防御性写作、心虚。
What it loads into context
Frontmatter
174 tokensAlways available to the agent
SKILL.md
1,462 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 一句话原则
- 一、叙事规则
- 二、语言规则(防自我削弱)
- 三、实验规则
- 四、结构规则
- 五、默认决策规则(遇到不理想材料时,按优先级处理)
- 六、交稿前自查(不给审稿人递刀子)
- 最终目标
Files
SKILL.mdcore5,523 bytes
Read SKILL.md
# 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
1. **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。
2. **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。View the complete source on GitHubanti-defensive-writing-en
When your agent uses it
Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments. Treats the paper as a press conference, not a project summary, lab log, or self-audit: identify the single most publishable strength of the work and build the most favorable, complete, and persuasive narrative around it. Never present everything evenly, never volunteer weakness, never write an experiment diary, never attack the paper on the reviewer's behalf. Triggers: polish my paper, revise manuscript, write abstract, write introduction, write conclusion, shorten paper, rebuttal, respond to reviewers, organize experiments, defensive writing, AI-flavored academic writing.
What it loads into context
Frontmatter
158 tokensAlways available to the agent
SKILL.md
1,375 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- One-line principle
- 1. Narrative rules
- 2. Language rules (against self-undermining)
- 3. Experiment rules
- 4. Structure rules
- 5. Default decision rules (for any unfavorable material, in priority order)
- 6. Pre-submission checklist (never hand the reviewer a knife)
- Final goal
Files
SKILL.mdcore6,419 bytes
Read SKILL.md
# The Press-Release Principle (Paper as Press Conference)
## One-line principle
A paper is a press conference, not a project summary, a lab log, or a self-audit.
Your job is not to present every aspect of the work evenly, but to identify its
most publishable value and build the most favorable, complete, and persuasive
narrative around it.
## 1. Narrative rules
1. **Organize the paper around strengths only.** Look for what is genuinely ahead,
unique, or irreplaceable: a new capability, a new problem, a new mechanism, a new
perspective, broader applicability, lower cost, higher efficiency, betterView the complete source on GitHubSkills included
- anti-defensive-writing
- anti-defensive-writing-en
Repository facts
- License
- MIT
- Created
- Aug 11, 2026
- Last pushed
- Oct 27, 2026
- Forks
- 122
- Open issues
- 2
- Project activity
- Active
Rank over the last 12 weeks
Now #273 · best #272 · up 135 in 30 days
- #283 on Nov 1
- #279 on Nov 2
- #280 on Nov 3
- #275 on Nov 4
- #272 from Nov 5 to Nov 6
- #273 since Nov 7
76 earlier periods
- #893 on Aug 9
- #926 on Aug 12
- #936 on Aug 13
- #909 on Aug 14
- #880 on Aug 15
- #902 on Aug 16
- #909 on Aug 17
- #927 from Aug 18 to Aug 19
- #907 on Aug 20
- #921 on Aug 21
- #865 on Aug 22
- #919 on Aug 23
- #931 on Aug 24
- #940 on Aug 25
- #921 on Aug 26
- #927 on Aug 27
- #961 on Aug 28
- #878 on Aug 29
- #876 on Aug 30
- #921 on Aug 31
- #950 on Sep 1
- #914 on Sep 2
- #916 on Sep 3
- #875 on Sep 4
- #846 on Sep 5
- #876 on Sep 6
- #856 on Sep 7
- #815 on Sep 8
- #744 on Sep 9
- #725 on Sep 10
- #673 on Sep 11
- #660 on Sep 12
- #640 on Sep 13
- #621 on Sep 14
- #586 on Sep 15
- #567 on Sep 16
- #549 on Sep 17
- #536 on Sep 18
- #512 from Sep 19 to Sep 20
- #505 on Sep 21
- #509 on Sep 22
- #490 on Sep 23
- #475 on Sep 24
- #469 on Sep 25
- #454 on Sep 26
- #462 on Sep 27
- #461 on Sep 28
- #458 on Sep 29
- #451 on Sep 30
- #448 on Oct 1
- #438 on Oct 2
- #424 on Oct 3
- #416 on Oct 4
- #420 on Oct 5
- #421 on Oct 6
- #418 on Oct 7
- #408 on Oct 8
- #404 on Oct 9
- #383 on Oct 10
- #377 on Oct 11
- #371 on Oct 12
- #360 on Oct 13
- #355 on Oct 14
- #341 on Oct 15
- #335 on Oct 16
- #327 on Oct 17
- #330 on Oct 18
- #320 on Oct 19
- #319 on Oct 20
- #317 on Oct 21
- #307 on Oct 22
- #298 on Oct 23
- #299 on Oct 24
- #300 on Oct 25
- #288 on Oct 28
- #285 from Oct 29 to Oct 31
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 2, 2026
- No broad tool permissions
- No dangerous shell commands
- No network access
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/anti-defensive-writing/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/anti-defensive-writing/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/anti-defensive-writing/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/anti-defensive-writing/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/anti-defensive-writing/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/anti-defensive-writing/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/adkid-zephyr-anti-defensive-writing-skill/)