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 mengrru/Spherse --skill spherse-create-skillgit clone --depth 1 https://github.com/mengrru/SpherseWrote 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/mengrru/spherse/spherse-create-skill)<a href="https://agentmods.dev/skills/mengrru/spherse/spherse-create-skill"><img src="https://agentmods.dev/badge/skills/mengrru/spherse/spherse-create-skill/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/mengrru/spherse/spherse-create-skill"><img src="https://agentmods.dev/badge/skills/mengrru/spherse/spherse-create-skill.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 | $0.00042 | $0.01538 |
| Opus 5 | $0.00021 | $0.00769 |
| Sonnet 5 | $0.00008 | $0.00308 |
| Haiku 4.5 | $0.00004 | $0.00154 |
Grade A, and why
spherse-create-skill 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
创建自定义 Skill
Skill 是一段可被 agent 通过 load_skill 工具按需加载的指令(instructions)。你可以创建自己的 skill,将常用的写作规范、领域知识、工作流程封装成可复用的指令包。
Skill 的两个层级
Skill 按作用范围分为两个层级:
| 层级 | 目录路径 | 作用范围 |
|---|---|---|
| Project-level | .spherse/skills/{skill-name}/ |
项目内所有 agent 共享 |
| Agent-level | .spherse/agents/{agent-slug}/skills/{skill-name}/ |
仅该 agent 私有 |
如何选择
- Project-level:适用于所有 agent 都应遵循的通用规范(如世界观术语表、项目写作风格、文件命名约定)。
- Agent-level:适用于某个 agent 专属的工作方式(如某个角色扮演 agent 的对话风格、某个助手 agent 的特定输出格式)。Agent-level skill 放在该 agent 自己的目录下,不污染其它 agent 的 skill 列表。
- 项目根目录的
.agents/skills/{skill-name}/也会作为 project-level 兼容目录被载入。已有项目可以直接复用该目录;新建 Skill 时仍优先写入.spherse/skills,因为 Skill Panel、安装与市场更新只管理这个主目录。
优先级
同名 skill 的优先级为 agent-level > .spherse/skills > .agents/skills > builtin。
如何获取 agent slug
创建 agent-level skill 时,需要知道目标 agent 的 slug(即 agent 目录名,形如 writer-a1b2c3):
- 当前 agent 自身:在你的 system prompt 的
<session-context>块中,agent-slug: {slug}即为当前 agent 的目录名。用它构造路径.spherse/agents/{slug}/skills/{skill-name}/SKILL.md。 - 其它 agent:询问用户目标 agent 的 slug,或查看
.spherse/agents/目录下的子目录名。
标准目录结构
{skill-name}/
├── SKILL.md # 必需:YAML frontmatter + Markdown 指令正文
├── references/ # 可选:参考文档(如规范、模板说明)
│ └── style-guide.md
└── scripts/ # 可选:辅助模板或代码片段
└── outline.md
SKILL.md(必需):skill 的唯一入口,包含 frontmatter 和指令正文。- companion files(可选):
SKILL.md之外的任意文件会被自动枚举为该 skill 的附加文件。agent 加载 skill 时会获得文件清单,可用read_file按需读取。建议用references/、scripts/等语义化子目录组织。
SKILL.md 格式
SKILL.md 由两部分组成:
1. YAML Frontmatter
文件开头使用 --- 分隔的 YAML 块,必须包含两个字段:
| 字段 | 类型 | 说明 |
|---|---|---|
name |
string | skill 名称,必须与目录名完全一致,不可含 /、\、:,不可以 . 开头 |
description |
string | 一句话描述 skill 的用途,agent 据此判断是否需要加载该 skill |
2. Markdown 指令正文
frontmatter 之后的 Markdown 内容即为 skill 的指令正文。这部分会在 agent 调用 load_skill 时被注入到上下文中,应写清:skill 的目标、具体规则、示例、注意事项。
完整示例
---
name: fiction-style
description: 项目统一的小说写作风格规范,包括人称、时态、对话格式与章节结构约定
---
# 小说写作风格规范
## 人称与视角
- 全文使用第三人称限制视角
- 每章聚焦单一 POV 角色
## 对话格式
对话使用中文引号,人物语言与动作描写分行:
> 林晓转身看向窗外。
> 「这件事,我需要再想想。」
## 注意事项
- 避免大段心理独白,通过动作和环境暗示情绪
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.
- 10d ago First seen · 133 lines · 42 tokens per session scan A bbff7c7030f3
spherse-create-skill is a skill published in the GitHub repository mengrru/Spherse (71 stars, last pushed 4d ago), licensed MIT. It adds 42 tokens to every session and 1,538 once invoked, about $0.0002 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
llmlint
A Chinese-prose rule library with two entry points. Before writing, emit the rules as writing constraints to load into a system prompt or style guide. After writing, lint the draft with static rule hits, neural AIGC heatmaps, contextual review, approved repair, and local learning notes. Use when drafting or rewriting…
profile-system-guide
Guide users and agents through Neuro Book harness, TSX profiles, ProfileTurnPlan, skills, user-assets overlays, settings forms, profile home resources, profile compile checks, templates, system restore, and safe profile editing.
novel-technique-character-card-workshop
A workshop for turning rough character ideas into detailed, usable character profiles. It supports structured question cycles, personality layers, visual themes, and checks against reducing a character to a few labels.
novel-writer-execution
An internal execution guide for a writer profile after it receives a brief. It describes the detailed workflow, decision points, and common mistakes.
RP模式
A set of instructions for running a role-playing session under the NeuroBook RP protocol. RP means role-play, where characters and events are simulated according to defined rules.
skill-creator-zh
A skill for creating and maintaining skills in the Neuro Book repository. Skills are reusable instruction packages that guide an agent through a particular kind of work.