Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/huangrichao2020/pretty-skillsnpx agentmods add skills/huangrichao2020/pretty-skills/pretty-skills-creatorWrote 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/huangrichao2020/pretty-skills/pretty-skills-creator)<a href="https://agentmods.dev/skills/huangrichao2020/pretty-skills/pretty-skills-creator"><img src="https://agentmods.dev/badge/skills/huangrichao2020/pretty-skills/pretty-skills-creator/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/huangrichao2020/pretty-skills/pretty-skills-creator"><img src="https://agentmods.dev/badge/skills/huangrichao2020/pretty-skills/pretty-skills-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 66 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 66 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 129 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00122 | $0.01478 |
| Opus 5 | $0.00061 | $0.00739 |
| Sonnet 5 | $0.00024 | $0.00296 |
| Haiku 4.5 | $0.00012 | $0.00148 |
Grade A, and why
pretty-skills-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 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.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pretty-skills-creator
创 — 让创建新 skill 像"填一个表"一样简单。
一句话
pretty-skills-creator = 创建 skill 的 5 步流水线。
ps create <name> --title "..." --description "..." --triggers a b c
→ 校验输入（name / title / description / triggers）
→ 生成 4 件套：xxx讲解.pdf.placeholder.md + manifest.yaml + SKILL.md + CHANGELOG.md
→ 装到本地 store（ps create 自动软链 5 agent）
→ 你填细节 + 准备图 → 跑 build_case_pdf.py → ps contribute → 提 PR
v3.20 改造
| 改动 | 原因 |
|---|---|
| ❌ 删 web.html | GitHub 不能预览 + PPT 时代已废 |
| ❌ 删 4 风格 HTML 模板 | 替代方案 = xxx讲解.pdf（GitHub 原生预览） |
| ❌ 删 --style 参数 | PPT 风格 picker 没了，PDF 是统一的 PIL 合并 |
| ✅ 加 xxx讲解.pdf.placeholder.md | 占位说明，告诉用户怎么跑 build_case_pdf.py |
必备参数
| 参数 | 校验 | 说明 |
|---|---|---|
--title |
≥ 5 字 | Skill 标题（中文 / 英文都行） |
--description |
≥ 100 字 | 一句话定位 + 详细说明（多行用 | 或 \n） |
--triggers |
≥ 3 个 | 触发词（用户自然语言） |
可选参数
| 参数 | 默认 | 说明 |
|---|---|---|
--contributor |
@anonymous |
你的标识 |
--tags |
（无） | 标签列表 |
--related |
（无） | 关联资源描述 |
--out-dir |
（必填） | 输出目录 |
--dry-run |
false |
只看输出，不写文件 |
--created |
2026-07-10 |
创建日期 YYYY-MM-DD |
完整流程
Step 1 · 写参数
ps create my-new-skill \
--title "我的新 skill 标题" \
--description "$(cat <<EOF
这是一个非常厉害的新 skill，解决了 XXX 问题。
它的核心思路是 YYY，用法是 ZZZ。
适用场景：AAA / BBB / CCC。
EOF
)" \
--triggers 触发词1 触发词2 触发词3 触发词4 \
--contributor "huangrichao2020" \
--tags "tag1" "tag2" \
--related "knowhub 路径 / 关联 skill" \
--out-dir "$HOME/.pretty-skills/store"
Step 2 · 校验
脚本会自动校验：
- ✅ name 合法（kebab-case，2-64 字符）
- ✅ title ≥ 5 字
- ✅ description ≥ 100 字
- ✅ triggers ≥ 3 个
Step 3 · 生成 4 件套
~/.pretty-skills/store/my-new-skill/
├── xxx讲解.pdf.placeholder.md # 怎么跑 build_case_pdf.py 的说明
├── manifest.yaml # 符合 pretty-skills manifest schema
├── SKILL.md # agent 加载入口
└── CHANGELOG.md # 变更记录
Step 4 · 准备图 + 跑 build_case_pdf.py
cd ~/.pretty-skills/store/my-new-skill
# 1. 准备 AI 出图（每页 1 张）
# 用 matrix / DALL-E / 即梦 任意工具
mkdir images
# 把 PNG 放到 images/slide-01.png / slide-02.png / ...
# 2. 跑 PIL 合并 → xxx讲解.pdf
python3 ../../tools/build_case_pdf.py "my-new-skill"
# 工具路径：pretty-skill/tools/build_case_pdf.py · v3.20 极简版（5 行核心）
What ships with it
5 files 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 · 145 lines · 122 tokens per session scan A 01771ea04098
pretty-skills-creator is a skill published in the GitHub repository huangrichao2020/pretty-skills (54 stars, last pushed today), licensed MIT. It adds 122 tokens to every session and 1,478 once invoked, about $0.0006 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
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
story-long-write
A Chinese-language coaching workflow for creating a long online novel from the initial idea through the outline and chapter text. It starts by defining the intended emotion, then uses research and story-planning stages to guide writing.
story-import
A Chinese-language workflow for turning an existing novel into a structured writing project that can be continued later.
story-long-analyze
A structured process for deeply analysing a long online novel, starting with its opening three chapters and continuing chapter by chapter.
story-review
A review process for finding problems in a novel’s structure, characters, wording, and world rules. It can use several reviewers or one reviewer when others are unavailable.
story-short-write
A tool for writing complete short online novels, from the initial idea through the finished manuscript. It focuses on a single main emotional effect and usually uses first-person narration.