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 ntygod/ZhiWei --skill skill-creatorgit clone --depth 1 https://github.com/ntygod/ZhiWeiWrote 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/ntygod/zhiwei/skill-creator)<a href="https://agentmods.dev/skills/ntygod/zhiwei/skill-creator"><img src="https://agentmods.dev/badge/skills/ntygod/zhiwei/skill-creator.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.00711 |
| Opus 5 | $0.00024 | $0.00356 |
| Sonnet 5 | $0.00010 | $0.00142 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
skill-creator 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 8d 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
Skill 创作指南
帮用户手写 / 改写一份符合 v2 规范的 SKILL.md。核心约束：description 必须以"当 / 用于 / Use when"开头，不含工作流词；body 必须有"适用场景 / 不适用场景 / 工作流"三小节。
适用场景
- 用户从零写一个新的 Skill（描述 / 工作流 / references 全套）
- 改写老格式 Skill 让它符合 v2 规范
- 修复因 description / body 校验失败被跳过的 Skill
- 打磨 metadata.zhiwei（tags / suggested_tools / requires）
不适用场景
- 从开源市场找现成 Skill → 走前端"扩展市场"页面
- 只是查看已有 Skill 列表 / 能力 → 直接调
status工具 - 调用已有 Skill 执行业务 → 直接
skill_load
工作流
- 目录结构：
skills/<name>/下SKILL.md+ 可选references//scripts//assets/ - 写 frontmatter：name（kebab-case）+ description（≤1024）+ version（semver）+ metadata.zhiwei（可选）
- description 硬约束：
- 必须以"当 / 用于 / Use when"开头
- 禁工作流词：步骤 N / 首先 / 然后 / Step N / First / Then 不能出现
- 列关键词（用户高频说法）+ 边界（不适用场景的反向引导）
- body 三必需小节：标题完全一致（
## 适用场景/## 不适用场景/## 工作流）；body ≤5000 字符 - 复杂内容下沉 references：长命令 / 详细模板 / 大量样例放
references/<name>.md，body 只引用 - suggested_tools 仅作元数据：不会在
skill.load后自动注入；如填写，优先写已注册 canonical Tool ID，并用status/tool.search核对 - 3 指标自检：用词精简？职责分工（不重复 react-system / context-guide 已说的全局规则）？场景全面（按用户表达列分流路径）？
详细参考
- v2 frontmatter 完整字段、body 模板、常见校验错误、迁移老 Skill 步骤：
{skill_dir}/references/v2-spec-template.md
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.
- 8d ago First seen · 52 lines · 49 tokens per session scan A 4fdd3c144e8e
skill-creator is a skill published in the GitHub repository ntygod/ZhiWei (137 stars, last pushed 27d ago), licensed MIT. It adds 49 tokens to every session and 711 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
inbox-triage
Summarize unread Gmail messages Alfred Core has already synced, and offer to draft or schedule follow-up actions -- never sends or deletes anything on its own.
morning-brief
Render Alfred Core's deterministic morning brief and deliver a short, warm rewrite of it without changing any fact, date, or link it contains.
weekly-review
Pull together the week's open tasks, GitHub notifications, Canvas missing assignments, and remembered context into one retrospective-style summary.
docmancer
Work from the same local memory as every other coding agent on this machine. Recall prior decisions, preferences, instructions, and project conventions that Claude Code, Codex, Cursor, and other agents wrote here, with cited sources, fully local. Also searches a separate local technical-documentation index.
vault-for-llm
Connect OpenClaw to Vault Agent Memory as a local-first governed project memory layer. Search first, then bounded-read cited source ranges; propose new memories as candidates instead of writing directly into active memory.
mooncite
Use when an agent needs past Pi, OMP, Claude Code, Codex, or ChatGPT context.