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 malue-ai/dazee-small --skill style-learnergit clone --depth 1 https://github.com/malue-ai/dazee-smallWrote 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/malue-ai/dazee-small/style-learner)<a href="https://agentmods.dev/skills/malue-ai/dazee-small/style-learner"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/style-learner/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/malue-ai/dazee-small/style-learner"><img src="https://agentmods.dev/badge/skills/malue-ai/dazee-small/style-learner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00026 | $0.01020 |
| Opus 5 | $0.00013 | $0.00510 |
| Sonnet 5 | $0.00005 | $0.00204 |
| Haiku 4.5 | $0.00003 | $0.00102 |
Grade A, and why
style-learner 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 9d 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
风格学习
从用户的对话和文本样本中学习写作风格,并在后续写作任务中复用。
使用场景
- 用户说「记住我的写作风格」「用我的风格写一篇 XXX」
- 用户提供了几篇自己的文章作为样本
- 小搭子主动识别到用户有稳定的写作偏好
工作流程
阶段 1:采集样本
当用户提供文本样本时,提取风格特征:
输入:用户的 1-3 篇文本样本
↓
分析维度:
- 语气:正式/半正式/口语/学术
- 句式:长句偏好/短句偏好/混合
- 用词:书面/通俗/专业术语密度
- 结构:段落长度/转折词/列表偏好
- 特殊习惯:口头禅/常用表达/标点习惯
↓
输出:风格画像(结构化 JSON)
阶段 2:保存风格画像
将风格画像保存为本地文件,供后续写作时参考。
# 风格画像存储路径
~/.xiaodazi/styles/
# 文件格式
~/.xiaodazi/styles/{用户名}_default.json
~/.xiaodazi/styles/{用户名}_{场景名}.json # 可按场景保存多套风格
风格画像结构:
{
"name": "默认风格",
"created_at": "2025-01-15",
"updated_at": "2025-02-07",
"sample_count": 3,
"profile": {
"tone": "半正式,亲切但不随意",
"sentence_style": "短句为主,偶尔用长句做总结",
"vocabulary": "通俗用词,避免学术术语,喜欢用比喻",
"structure": "开头直入主题,段落短(3-5句),善用列表",
"special_habits": [
"喜欢用破折号做补充说明",
"段尾常用反问句引发思考",
"数字用阿拉伯数字不用中文"
]
},
"few_shot_examples": [
{
"context": "写产品介绍",
"sample": "(截取的 200 字典型片段)"
}
]
}
阶段 3:应用风格
写作任务时,读取风格画像并注入到提示词:
用户请求:「帮我写一篇关于 AI 的文章」
↓
读取风格画像 → 提取关键约束
↓
生成时遵循:
- 语气:半正式,亲切
- 句式:短句为主
- 用词:通俗,多用比喻
- 结构:开头直入主题,段落 3-5 句
↓
输出:符合用户风格的文章
阶段 4:持续学习
每次用户修改输出或给出反馈时,更新风格画像:
- 用户说「太正式了」→ 调整 tone 为更口语
- 用户手动修改了输出 → 对比差异,更新偏好
- 积累 5+ 次反馈后自动更新画像
命令参考
保存风格画像
mkdir -p ~/.xiaodazi/styles
cat > ~/.xiaodazi/styles/default.json << 'EOF'
{
"name": "默认风格",
...
}
EOF
读取风格画像
cat ~/.xiaodazi/styles/default.json
列出已有风格
ls ~/.xiaodazi/styles/
输出规范
- 分析风格时,用通俗语言描述(不用语言学术语)
- 保存成功后告知用户「已记住你的写作风格」
- 写作时不提及「我在使用你的风格画像」,自然地写
- 用户可以说「换个正式的风格」临时切换,不影响保存的画像
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.
- 9d ago First seen · 140 lines · 26 tokens per session scan A 654aabd1ed45
style-learner is a skill published in the GitHub repository malue-ai/dazee-small (36 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 1,020 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.