Explore Then Exploit: Matt Pocock's Writing Skills (452K)
Matt Pocock’s writing-shape and writing-fragments split writing into explore and exploit. We read both SKILL.md files: the grounding ledger, 452K installs.
Microsoft’s entra-agent-id skill gives each agent instance its own Entra identity via Blueprint, BlueprintPrincipal, and the two-step fmi_path token exchange.
GitHub Skill Forge turns any repo into an AI skill from one URL — no cloning, no manual work. Your AI reads open-source projects via natural conversation.
Mem0 is an open-source memory layer for AI agents that remembers user preferences, facts, and context across sessions using embeddings and retrieval.
The n8n Workflow Architect skill makes AI agents n8n experts — build, validate, and deploy production workflows through conversation with MCP integration.
A skill by Matt Pocock that turns unstructured AI conversation into structured PRDs and publishes them straight to your issue tracker.
Matt Pocock’s writing-shape and writing-fragments split writing into explore and exploit. We read both SKILL.md files: the grounding ledger, 452K installs.
We ran RigorPilot’s minimal-run-and-audit scripts on a real repo: the metric it calls best, the shell-mode gate, and a pipe that fakes success.
Inside the twitter-automation skill — nine belt CLI apps for posting, liking, DMs, and follows — and why six mirror counters on skills.sh all exploded at once.
Practical guide to Matt Pocock’s research skill: delegate reading to a background agent, trace claims to primary sources, and collect one cited Markdown file.
Straight answers on Matt Pocock’s wizard skill: what generated bash wizards do, how stages and secrets work, when to commit one, what 392K installs mean.
RigorPilot’s repo-intake-and-plan (450K installs, #70) scanned micrograd, makemore, and nanoGPT for me: 2, 3, and 16 commands — plus one it invented.
RigorPilot’s ai-research-reproduction (310.8K installs) runs DL repos as 9 README-first steps: smallest target, audited patches, repro_outputs/ evidence.
5 AI skills that actually find bugs, compared from their source: diagnosing-bugs loop, TDD seams, code-review axes, prototype flow, and the regression trap.
12 AI agent frameworks, ranked with GitHub data from August 15, 2026: stars, maintenance signals, and the right pick for Python, TypeScript, or enterprise.
Learn how to scrape websites for AI with Firecrawl — get an API key, install the SDK, and run your first scrape, search, and crawl in under ten minutes.
I let an AI note-taking agent run my notes for a month — what it captured, what it lost, and the hybrid workflow I kept after the experiment ended.
Set up Lark Knowledge AI in six steps — structure Wiki knowledge spaces, enable AI search and summaries, and connect the lark-wiki skill to your coding agent.
Compare Agent Browser, Browser Use, and Playwright MCP for AI agent browser automation — control model, setup friction, and which fits your workflow.
I ran my research for a full week using AI search agents instead of Google — what they nailed, where they hallucinated, and whether the switch is worth it.
Learn how to automate complex workflows with AI agents using n8n — from MCP setup to building production-ready automation pipelines in 6 steps.
A step-by-step guide to building your first AI automation workflow — from choosing the right task to scheduling a pipeline that runs while you rest.
A2A vs MCP — two protocols for AI agent communication, but they solve different problems. Here’s when to use each, and when you need both.
Answers to the most common questions about web scraping with AI agent skills — from choosing the right tool to handling JavaScript-heavy sites and extracting structured data.