Borrowing it
Nothing to install: this file belongs to EXboys/skilllite. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/EXboys/skilllite/main/.skills/writing-helper/SKILL.mdgit clone --depth 1 https://github.com/EXboys/skillliteWrote 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/exboys/skilllite/writing-helper)<a href="https://agentmods.dev/skills/exboys/skilllite/writing-helper"><img src="https://agentmods.dev/badge/skills/exboys/skilllite/writing-helper/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/exboys/skilllite/writing-helper"><img src="https://agentmods.dev/badge/skills/exboys/skilllite/writing-helper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.01230 |
| Opus 5.5 | $0.00010 | $0.00492 |
| Sonnet 5.5 | $0.00005 | $0.00246 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
writing-helper 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 2mo 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.
What it actually says
写作助手
⚠️ 强制约束（必须遵守）
当用户要求写文章、写内容、要求"去AI味"、"降低AI感"时，必须严格遵守以下规则：
绝对禁止的表达（出现即扣分）
❌ 禁止使用的开头：
- "在当今..."、"随着...的发展"、"在这个...的时代"
- "让我们一起..."、"众所周知..."
- "作为一个..."、"作为..."
❌ 禁止使用的结构词：
- "首先...其次...再次...最后..."
- "第一...第二...第三..."
- "一方面...另一方面..."
❌ 禁止使用的过渡词：
- "值得注意的是"、"需要指出的是"、"不可否认的是"
- "综上所述"、"总而言之"、"由此可见"
- "换句话说"、"也就是说"
❌ 禁止使用的互联网黑话：
- "赋能"、"抓手"、"闭环"、"打通"、"沉淀"
- "颗粒度"、"对齐"、"拉通"、"落地"
- "底层逻辑"、"顶层设计"、"方法论"
❌ 禁止使用的空洞形容：
- "非常重要"、"至关重要"、"不可或缺"
- "深刻影响"、"深远意义"、"重大突破"
- "令人振奋"、"令人期待"、"令人瞩目"
必须使用的写作技巧
✅ 开头必须：用具体场景、故事、问题、或反常识观点
✅ 句式必须：长短交错，有节奏感，像说话一样
✅ 语气必须：有个人色彩，用"我"、"你"拉近距离
✅ 内容必须：有具体细节、数据、案例，不说空话
✅ 结尾必须：自然收尾，可以留问题，不要强行升华
写作风格指南
语言风格
像聊天，不像报告：
- 用"说实话"、"其实"、"我觉得"这类口语
- 适当用反问："你有没有想过...？"
- 可以有语气词："嗯"、"啊"、"吧"
- 允许不完美的表达，更真实
有态度，不中立：
- 敢于表达明确观点
- 可以有偏好和倾向
- 不必面面俱到
- 有锋芒比圆滑更吸引人
结构风格
不要工整的总分总：
- 从一个小切口进入
- 段落长短不一
- 过渡自然，不用连接词硬接
- 结尾可以戛然而止
情感风格
有温度，不冷冰冰：
- 写自己的真实感受
- 用细节打动人
- 适当暴露脆弱或困惑
- 让读者感到"这是个真人在说话"
示例对比
❌ AI味重的写法：
在当今数字化时代，人工智能技术正在深刻改变我们的生活。首先，AI在医疗领域发挥着重要作用；其次，在教育领域也有广泛应用；最后，在交通领域同样不可或缺。综上所述，AI技术的发展对人类社会具有深远意义。
✅ 去AI味的写法：
上周我妈给我发微信，问我"那个能聊天的机器人怎么用"。我教了她半小时，她现在每天用它查菜谱、问养生知识，比我这个儿子还贴心。
说实话，看着一个60多岁的老太太跟AI聊得火热，我挺感慨的。这玩意儿真的在悄悄改变一些东西，不是什么"颠覆性变革"，就是一点一点渗透进日常。
我不知道AI最后会发展成什么样。但至少现在，它让我妈少打了几个电话问我"这个菜怎么做"。这算好事吧？
不同场景要点
公众号/自媒体
- 标题有悬念但不标题党
- 开头3秒抓住人
- 短句多、分段多
- 结尾抛问题引讨论
工作邮件
- 先结论后过程
- 数据说话，少形容词
- 简洁直接
- 专业但有温度
产品文案
- 说人话
- 聚焦痛点和场景
- 用对比突出差异
- 行动号召要自然
自检清单
写完后检查：
- 开头是不是"在当今..."这类套话？→ 改掉
- 有没有"首先其次最后"？→ 删掉
- 有没有具体的故事、细节？→ 没有就加
- 读起来像人说的话吗？→ 大声读一遍
- 结尾是不是强行升华？→ 改自然点
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 137 lines · 25 tokens per session scan A 191f6a8ba64a
writing-helper is a skill published in the GitHub repository EXboys/skilllite (152 stars, last pushed 4d ago), licensed MIT. It adds 25 tokens to every session and 1,230 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
writing-helper compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| writing-helperEXboys/skilllite | Skill | 152 | 4d ago | MIT | A | 25 | Claude Code, Codex |
| analyzing-malware-behavior-with-cuckoo-sandboxMikaru0Mystic/sectinel | Skill | 12 | 4mo ago | Apache-2.0 | A | 78 | Claude Code |
| ops-demoSnowflake-Labs/cocoplus | Skill | 727 | 2d ago | MIT | A | 46 | Claude Code |
| diarySnowflake-Labs/cocoplus | Skill | 727 | 2d ago | MIT | A | 12 | Claude Code, Codex |
| pulse-configureSnowflake-Labs/cocoplus | Skill | 727 | 2d ago | MIT | A | 12 | Claude Code, Codex |
| stall-resetSnowflake-Labs/cocoplus | Skill | 727 | 2d ago | MIT | A | 14 | Claude Code, Codex |
| code-reviewmagnus919/agent-skills | Skill | 166 | 2d ago | MIT | A | 196 | Claude Code, Codex |