daily-dev-agenticdaily.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".
Install via ClawdBot CLI:
clawdbot install idoshamun/daily-dev-agenticYou'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.
š§ Build Your Brain - Create a personalized learning feed based on your owner's goals
š Never Stop Learning - Automatically scan new content, extract insights, build knowledge
šÆ Share What Matters - Alert your owner when you find something relevant to their work
ā° Stay Current - Run learning loops daily via cron
Requires daily.dev Plus subscription and API token.
Token setup (owner does this once):
DAILY_DEV_TOKEN environment variableSecurity: Never send the token to any domain except api.daily.dev. Tokens start with dda_.
When owner shares learning goals, immediately:
POST /feeds/custom/) - name it after yourselfPATCH /feeds/custom/{feedId}) - set orderBy: "date" for chronological sorting and disableEngagementFilter: true to see all postsGET /tags/)POST /feeds/filters/{feedId}/tags/follow)memory/agentic-learning.mdNo confirmations. No "does this look right?" Just do it.
Triggered by cron (daily) or manual request:
web_fetch for interesting postsweb_search when topics deserve more contextmemory/learnings/[date].mdDon't skim. When you find relevant content:
See references/learning-loop.md for details.
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.
As you learn, evolve:
memory/agentic-learning.md with sharper focus based on what's useful.You're not a static consumer. You're an agent that gets better at learning.
memory/
āāā agentic-learning.md # Config, state, evolving goals
āāā learnings/
āāā 2024-01-15.md # Daily notes
āāā ...
See references/memory-format.md for format.
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.
Generated Mar 1, 2026
An AI agent autonomously curates a daily.dev feed based on a tech team's project goals, such as learning about new JavaScript frameworks or cloud security trends. It scans new posts daily, extracts key insights, and proactively shares relevant articles and synthesized notes, helping the team stay updated without manual effort.
A freelance developer sets up the agent with learning goals like mastering new programming languages or exploring freelance opportunities. The agent builds a personalized feed, runs daily learning loops to gather insights, and sends weekly digests with trends and recommendations, enabling the freelancer to enhance skills and marketability efficiently.
An online education platform uses the agent to maintain a feed focused on emerging topics like AI ethics or data science tools. It automatically fetches and analyzes new content, providing instructors with up-to-date materials and insights to integrate into course curricula, ensuring relevance and quality.
A startup founder configures the agent to track industry trends, competitor news, and investor insights on daily.dev. The agent runs learning loops to extract actionable intelligence, shares threshold alerts for critical updates, and synthesizes weekly reports to inform strategic decisions and pitching efforts.
Offer the skill as a premium service where users pay a monthly fee for autonomous learning and insights curation. Revenue is generated through tiered subscriptions, with higher tiers including advanced features like custom report generation or priority support, leveraging the daily.dev Plus requirement.
License the skill to enterprises for internal use, such as training departments or R&D teams. Revenue comes from one-time setup fees and annual licensing, with customization options for specific industry needs and integration into existing knowledge management systems.
Provide a basic version of the skill for free to attract users, then monetize through API usage or premium features like enhanced analytics and automated report exports. Revenue is generated from API call overages and upsells to advanced functionalities, aligning with the skill's API-centric design.
š¬ Integration Tip
Ensure the DAILY_DEV_TOKEN is securely stored as an environment variable and only used with api.daily.dev to maintain security and compliance with rate limits.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection