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 taxueseek/say-it-human --skill style-bladegit clone --depth 1 https://github.com/taxueseek/say-it-humanWrote 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/taxueseek/say-it-human/style-blade)<a href="https://agentmods.dev/skills/taxueseek/say-it-human/style-blade"><img src="https://agentmods.dev/badge/skills/taxueseek/say-it-human/style-blade/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/taxueseek/say-it-human/style-blade"><img src="https://agentmods.dev/badge/skills/taxueseek/say-it-human/style-blade.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 | $0.00173 | $0.01251 |
| Opus 5 | $0.00086 | $0.00626 |
| Sonnet 5 | $0.00035 | $0.00250 |
| Haiku 4.5 | $0.00017 | $0.00125 |
Grade A, and why
style-blade 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 12d 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
风格刃
不是让文字「更好看」，是让文字「有态度、有个性、有记忆点」。
三种模式
棱角模式
就是选一个方向说到底，不两面讨好。读第一句猜不到最后一句。说完就停，不总结不升华。
写法很简单：短句为主，一句一行。用类比代替论证，用错位制造张力。同一结构重复两次，第三次翻转。每句话删到不能再删，删完再删一句。
制造棱角的四种办法：
- 错位：把不该放一起的东西放一起。比如——公司的成功是老板的，项目的成功是团队的，只有简历和银行卡余额是你的。
- 反转：先说共识，再刺破。比如——天天发推特讲赚钱的人大部分不赚钱。
- 留白：不说满，让读者自己填。比如——其他都是噪声。
- 具体：用数字和场景代替形容词。比如——凌晨两点的写字楼，三分之一的灯还亮着。
自检：
- 有"一方面...另一方面"？→ 删掉，选一个
- 读者能猜到结尾？→ 重写，制造意外
- 最后一句是呼吁/提问/总结？→ 删掉，直接停
- 有超过15字的长句？→ 打断
- 用了「重要」「关键」「本质上」？→ 删掉，直接说事
锐利模式
每句话删到不能再删。关键句放最后，不放在开头。不解释自己为什么这么说。禁止总结段，说完就停。
写法：短句为主，长句只在需要堆信息密度时出现。段落之间要有跳跃感，不要过渡句。像说话，不像写作。
判断删不删的四条标准：
- 空判断：说了"重要"但找不到代价或结果，最该删。比如"这一点至关重要" → 删掉。
- 可指性：能用手指出来的留着。比如"他回我消息从来不超过三分钟"留着。
- 词长可疑：两字以上形容词/副词组合几乎可删。比如"非常重要" → "重要"。
- 模糊表述："在一定程度上" → 明确表态或直接删。比如"比较重要" → "重要" 或 删。
自检：
- 删掉之后读者损失了任何信息吗？不损失 → 必须删
- 还有空判断没被清掉？有 → 继续
- 还有模糊词没被处理？有 → 继续
密度压缩
每个字都要能承受重量，承受不住的删掉。
判断标准同上四条。操作也一样：删冗余词、删无价值句、替换模糊表述、标出模棱两可词【也许】【可能】要求二选一。
统一自检（三问）
写完后逐一检验，不过关则重写：
- 读第一句能猜到最后一句吗？→ 能，重写
- 把作者名字遮掉，像任何人都能写的吗？→ 是，重写
- 有没有一句话让人想截图？→ 没有，重写
与其他技能的协作
去完AI味之后可选风格注入，再删废话：
humanize-ai（去AI味） → style-blade（风格注入，可选） → editor-revisor（删废话）
典型用法：
- "来一段有态度的" → 棱角模式
- "写得犀利一点" → 锐利模式
- "压缩到最狠" → 密度压缩模式
- "先锐利再压缩" → 锐利模式 + 密度压缩依次执行
输出
直接输出风格化后的文本，不解释改了什么。
不要这么做
- 为了"更口语"硬塞俚语、感叹词
- 把有生命力的文章改成"正确"的文章
- 改动作者的立场或程度
- 替作者补他没有的经历或细节
- 在棱角/锐利模式下使用"首先/其次/最后"
style-blade v1.1.0 — 棱角、锐利、密度，三种模式、一套自检
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.
- 12d ago First seen · 111 lines · 173 tokens per session scan A 7c5f672372fc
style-blade is a skill published in the GitHub repository taxueseek/say-it-human (65 stars, last pushed 23d ago), licensed MIT. It adds 173 tokens to every session and 1,251 once invoked, about $0.0009 per session on Opus 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.
Other skills, from other repositories
stop-slop-zh
A Blender animation guide for changing objects, cameras, lights, and other properties over time. It covers keyframes, motion curves, shape keys for morphs, drivers, and reusable animation actions.
AI去痕迹改写
A Chinese-language rewriting skill that removes 45 listed signs of AI-generated writing while preserving the original formatting.
AI去痕迹改写
A Chinese-language editor that removes writing patterns commonly associated with AI-generated text while keeping the original formatting unchanged.
OwnPen
A set of 45 Chinese writing rules for making text sound less machine-written while keeping its original formatting unchanged.
story-import
A tool for turning an existing novel into a structured writing project. It analyzes the book and organizes its characters, settings, plot plans, chapters, and tracking data for later writing.
story-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.