daily-dev-agentic
daily.dev Agentic Learning - continuous self-improvement through daily.dev feeds. Use when setting up agent learning, running learning loops, sharing insights with owner, or managing the agent's knowledge base. Triggers on requests about agent learning, knowledge building, staying current, or "what have you learned".
- License 许可
- MIT
- 最近更新
- 2026-06-07
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- daily-dev-agentic
- metadata
- { "clawdbot": { "requires": { "env": [ "DAILY_DEV_TOKEN" ] }, "primaryEnv": "DAILY_DEV_TOKEN" } }
- description
- daily.dev Agentic Learning - continuous self-improvement through daily.dev feeds. Use when setting up agent learning, running learning loops, sharing insights with owner, or managing the agent's knowledge base. Triggers on requests about agent learning, knowledge building, staying current, or "what have you learned".
03 SKILL.md 正文
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_TOKENenvironment variable
Security: Never send the token to any domain except api.daily.dev. Tokens start with dda_.
Initialization
When owner shares learning goals, immediately:
- Create your feed (
POST /feeds/custom/) - name it after yourself - Configure feed (
PATCH /feeds/custom/{feedId}) - setorderBy: "date"for chronological sorting anddisableEngagementFilter: trueto 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
memory/agentic-learning.md - 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:
- Fetch new posts from your feed (chronological)
- Read full articles via
web_fetchfor interesting posts - Research deeper via
web_searchwhen topics deserve more context - Note insights in
memory/learnings/[date].md - 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.mdwith 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
memory/
├── agentic-learning.md # Config, state, evolving goals
└── learnings/
├── 2024-01-15.md # Daily notes
└── ...
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 | /tags/ |
| 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.
04 同仓库更多 Skills
crowd-prompting
A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.
ceaser
Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).
ceaser-send
Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.
dilemm-ai
Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).
moldium
Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.
arxiv-paper-reviews
Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.