xurl CLI adds Agent Skills support

// 1h agoPRODUCT UPDATE

xurl CLI adds Agent Skills support

Mike Rosinsky announced the integration of the Agent Skills open standard into xurl, a curl-like CLI tool designed for making authenticated requests to the X API. By implementing the SKILL.md specification, xurl allows AI agents to dynamically discover and execute operations while enforcing strict security guidelines to prevent API credential exposure.

// ANALYSIS

Integrating Agent Skills into command-line tools like xurl bridges the gap between static CLI utilities and autonomous agents, transforming local tools into discoverable APIs for LLMs. However, granting agents direct access to execute social media actions makes security boundaries around credential storage a paramount concern.

–The standard formatting of SKILL.md allows xurl to be instantly utilized by any compliant agent runner (e.g., Claude Code, Cursor, or Gemini CLI) without manual prompt engineering.
–Rigid security instructions in the skill file—such as banning verbosity flags and blocking the reading of local config files—are crucial to prevent prompt injections from leaking API credentials.
–Progressive disclosure enables the host agent to keep its context window clean, loading the extensive command reference only when X-related tasks are explicitly triggered.

// TAGS

xurlx-apitwitter-apiagent-skillsdevtoolopen-sourcecli

DISCOVERED

1h ago

2026-06-14

PUBLISHED

1h ago

2026-06-14

RELEVANCE

7/ 10

AUTHOR

mike_rosinsky

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

NEWS41m ago

Prominent developers challenge the metric of lines of code written as AI tools like Anthropic's Mythos models surge code output.

Morgan Linton highlights a recent debate surrounding developer productivity metrics in the AI era. While Anthropic published a chart boasting of the massive increase in the lines of code written by their engineers utilizing their Mythos-class AI models, critics and prominent developers like ThePrimeagen point out that elite software engineers often measure success by how much code they delete and simplify, suggesting that counting lines written is a counterproductive and outdated metric for software quality and efficiency.

NEWS52m ago

NexEcosystem reveals that the viral Rio 3.5 model is actually a direct merge of their open-source Nex N2 Pro model.

The municipal IT company of Rio de Janeiro, IplanRIO, released the Rio 3.5 model as a high-performance, homegrown open-weights model. However, NexEcosystem and independent AI researchers discovered that the model is actually a linear weight merge comprising roughly 60% Nex N2 Pro and 40% Qwen 3.5. When stripped of its system prompts, Rio 3.5 even identifies itself as Nex N2 Pro, sparking community debate over "AI washing" versus the collaborative spirit of open-source model merging.

NEWS58m ago

Pietro Schirano automates Codex goal generation

AI builder Pietro Schirano has automated his prompt engineering by having OpenAI's Codex write its own goals and spawn sub-agents. Instead of manually specifying tasks, Schirano instructs the coding agent to formulate its own primary objectives and generate goals for each spawned sub-agent.