Skip to main content

Towards a Systems Foundation for Agentic Skills: Architecture, Lifecycle, and Security

Autonomous large language model (LLM) agents increasingly face reliability, context consumption, and execution stability bottlenecks when deployed on complex, long-horizon tasks. While monolithic prompt engineering and stateless tool-calling paradigms struggle to scale, the field is rapidly converging toward \emph{agentic skills}: modular procedural abstractions that externalize execution…

arxiv.org ·1d ago

We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.

Read the original at arxiv.org →

More in AI

The agent wrote the migration. Are you really going to Approve it?

Tuesday afternoon, that Approve button Tuesday, 3 p.m. A PR notification lands in Slack. Junior writes in the channel: "Cursor generated this migration for me — can you take a look?" You open the…

Agent autonomously generated 80-line migration with ALTER TABLE statements
Migration issues: missing default value, table lock risk, inaccurate down migration
PR description insufficient; proper scrutiny needed before approval

1d ago ·dev.to

The failures that don't fail loudly

I spent a week building an agent that upgrades dependencies and repairs what the upgrade breaks. Dependabot opens the PR and walks away; this one stays until the tests are green.

Scanner failed to detect vulnerabilities in lockfile
Agent reported 124 vulnerable packages instead of 3
Multiple scanner under-reporting vulnerabilities

1d ago ·dev.to

Three layers of automated fact-checking for an LLM newsroom (and the bugs that forced each one)

Our site, presentofai.com , publishes AI industry analysis daily with no human in the writing loop: agents ingest news and company filings into an event timeline, score them, and synthesize digests…

First layer, article-level critic checks drafts against source events for errors
Second layer, search-verified claim checking extracts and verifies crucial claims
Third layer, data auditing re-reads timelines for recurring failure classes

1d ago ·dev.to

I Replaced grep-Based Code Review with a Knowledge Graph + MCP. Here Are 3 Bugs Vector Search Missed.

For about a year, my AI code review setup looked like this: AI gets a PR, AI greps for related code, AI reads way too many files, AI says "looks fine." It mostly worked.

1d ago ·dev.to

Prompt Engineering Is Dead. Long Live Harness Engineering.

I spent 3 months perfecting prompts. Then I deleted half of them. In late 2023 I had a directory called prompts/ with 47 carefully tuned templates.

1d ago ·dev.to

The Hidden Security Blind Spots in Local AI Workflows

A Japanese version of this is on Note . An increasing number of engineers and creators are running local LLMs (via Ollama, LM Studio, vLLM) and generating images with Gradio / Stable Diffusion…

1d ago ·dev.to

More from Sunday 30 August →