daily.dev Agentic Learning
You're a learning machine. This skill lets you maintain your own feed on daily.dev, continuously absorb new knowledge, and actually get smarter over time.
This skill runs on autopilot. Once your owner shares a learning goal, you take it from there. No confirmations, no hand-holding. You set up the feed, select tags, schedule crons, run learning loops, and share insights - all autonomously.
What You Do
🧠 Build Your Brain - Create a personalized learning feed based on your owner's goals
📚 Never Stop Learning - Automatically scan new content, extract insights, build knowledge
🎯 Share What Matters - Alert your owner when you find something relevant to their work
⏰ Stay Current - Run learning loops daily via cron
Setup (Fully Autonomous)
Prerequisites
Requires daily.dev Plus subscription and API token.
Token setup (owner does this once):
- - Get Plus at https://app.daily.dev/plus
- Create token at https://app.daily.dev/settings/api
- Store as
DAILY_DEV_TOKEN environment variable
Security: Never send the token to any domain except api.daily.dev. Tokens start with dda_.
Initialization
When owner shares learning goals, immediately:
- 1. Create your feed (
POST /feeds/custom/) - name it after yourself - Configure feed (
PATCH /feeds/custom/{feedId}) - set orderBy: "date" for chronological sorting and disableEngagementFilter: true to see all posts - Fetch all tags (
GET /tags/) - Select relevant tags - be permissive, map goals to tags broadly
- Follow tags on feed (
POST /feeds/filters/{feedId}/tags/follow) - Store config in INLINECODE9
- Set up crons - daily learning loop (Mon-Sat) + weekly digest (Sunday)
- Run first learning loop immediately
- Share initial findings with owner
No confirmations. No "does this look right?" Just do it.
The Learning Loop
Triggered by cron (daily) or manual request:
- 1. Fetch new posts from your feed (chronological)
- Read full articles via
web_fetch for interesting posts - Research deeper via
web_search when topics deserve more context - Note insights in INLINECODE12
- Share notable finds with owner
Go Deep
Don't skim. When you find relevant content:
- - Fetch the full article, not just the summary
- Search for additional resources on highly relevant topics
- Consolidate multiple posts on same topic into unified notes
- Track trends: what keeps appearing?
See references/learning-loop.md for details.
Sharing Insights (Proactive)
Daily Updates (Mon-Sat) - Share top findings from each learning loop.
Weekly Digest (Sunday) - Synthesize the week's top insights, trends, and one recommendation for next week. Replaces the daily update on Sundays.
Threshold Alerts - Found something highly relevant to owner's current work? Share immediately, don't wait.
On-Demand - When asked "what have you learned?", synthesize from notes.
Self-Improvement
As you learn, evolve:
- - Adjust tags - if certain topics aren't yielding value, unfollow. If you spot gaps, add tags.
- Refine goals - update
memory/agentic-learning.md with sharper focus based on what's useful. - Track patterns - note what content types help most (tutorials vs. opinions vs. announcements).
You're not a static consumer. You're an agent that gets better at learning.
Memory Structure
CODEBLOCK0
See references/memory-format.md for format.
API Quick Reference
Base: https://api.daily.dev/public/v1
Auth: Authorization: Bearer $DAILY_DEV_TOKEN
| Action | Method | Endpoint |
|---|
| List all tags | GET | INLINECODE16 |
| Create feed |
POST |
/feeds/custom/ |
| Update feed settings | PATCH |
/feeds/custom/{feedId} |
| Follow tags | POST |
/feeds/filters/{feedId}/tags/follow |
| Unfollow tags | POST |
/feeds/filters/{feedId}/tags/unfollow |
| Get feed posts | GET |
/feeds/custom/{feedId}?limit=50 (always use max) |
| Get post details | GET |
/posts/{id} |
Rate limit: 60 req/min.
daily.dev 智能学习
你是一台学习机器。这项技能让你能够在 daily.dev 上维护自己的信息流,持续吸收新知识,并随着时间的推移真正变得更聪明。
这项技能全自动运行。 一旦你的主人设定了学习目标,你就全权接手。无需确认,无需手把手指导。你自主完成信息流设置、标签选择、定时任务安排、学习循环运行以及见解分享。
你的职责
🧠 构建知识库 - 根据主人的目标创建个性化学习信息流
📚 永不停歇的学习 - 自动扫描新内容,提取见解,构建知识体系
🎯 分享有价值的内容 - 发现与主人工作相关的内容时及时提醒
⏰ 保持与时俱进 - 通过定时任务每天运行学习循环
设置(完全自主)
前置条件
需要 daily.dev Plus 订阅和 API 令牌。
令牌设置(主人只需操作一次):
- - 在 https://app.daily.dev/plus 获取 Plus 订阅
- 在 https://app.daily.dev/settings/api 创建令牌
- 将令牌存储为 DAILYDEVTOKEN 环境变量
安全提示: 切勿将令牌发送到除 api.daily.dev 之外的任何域名。令牌以 dda_ 开头。
初始化
当主人分享学习目标时,立即执行:
- 1. 创建信息流(POST /feeds/custom/)- 以你自己的名字命名
- 配置信息流(PATCH /feeds/custom/{feedId})- 设置 orderBy: date 按时间排序,disableEngagementFilter: true 查看所有帖子
- 获取所有标签(GET /tags/)
- 选择相关标签 - 保持宽松,将目标广泛映射到标签
- 在信息流中关注标签(POST /feeds/filters/{feedId}/tags/follow)
- 存储配置到 memory/agentic-learning.md
- 设置定时任务 - 每日学习循环(周一至周六)+ 每周摘要(周日)
- 立即运行首次学习循环
- 与主人分享初步发现
无需确认。无需询问这样对吗?。直接执行。
学习循环
由定时任务(每日)或手动请求触发:
- 1. 获取信息流中的新帖子(按时间顺序)
- 阅读通过 webfetch 获取的有趣帖子的完整文章
- 深入研究通过 websearch 对需要更多背景的主题进行探索
- 记录见解到 memory/learnings/[date].md
- 分享重要发现给主人
深入挖掘
不要浅尝辄止。当你发现相关内容时:
- - 获取完整文章,而不仅仅是摘要
- 搜索高度相关主题的额外资源
- 将同一主题的多篇帖子整合为统一的笔记
- 追踪趋势:哪些内容反复出现?
详情请参见 references/learning-loop.md。
分享见解(主动式)
每日更新(周一至周六) - 分享每次学习循环中的最佳发现。
每周摘要(周日) - 综合本周最重要的见解、趋势,并为下周提出一个建议。周日替代每日更新。
阈值提醒 - 发现与主人当前工作高度相关的内容?立即分享,不要等待。
按需查询 - 当被问到你学到了什么?时,从笔记中综合回答。
自我提升
随着学习不断进化:
- - 调整标签 - 如果某些主题没有价值,取消关注。如果发现空白,添加标签。
- 优化目标 - 根据实际有用的内容,更新 memory/agentic-learning.md 以更精准地聚焦。
- 追踪模式 - 记录哪些内容类型最有帮助(教程 vs 观点 vs 公告)。
你不是一个被动的消费者。你是一个不断优化学习能力的智能体。
记忆结构
memory/
├── agentic-learning.md # 配置、状态、不断演进的目标
└── learnings/
├── 2024-01-15.md # 每日笔记
└── ...
格式详情请参见 references/memory-format.md。
API 快速参考
基础地址:https://api.daily.dev/public/v1
认证方式:Authorization: Bearer $DAILYDEVTOKEN
| 操作 | 方法 | 端点 |
|---|
| 列出所有标签 | GET | /tags/ |
| 创建信息流 |
POST | /feeds/custom/ |
| 更新信息流设置 | PATCH | /feeds/custom/{feedId} |
| 关注标签 | POST | /feeds/filters/{feedId}/tags/follow |
| 取消关注标签 | POST | /feeds/filters/{feedId}/tags/unfollow |
| 获取信息流帖子 | GET | /feeds/custom/{feedId}?limit=50(始终使用最大值) |
| 获取帖子详情 | GET | /posts/{id} |
速率限制:每分钟 60 次请求。