Explore skills

Finskills API key — register for free at https://finskills.net (Pro plan unlocks historical data, financials, and batch quotes)

Analyzes GitHub repositories, tools, or AI agent frameworks to extract their best capabilities into native OpenClaw skills, perfect for replicating features or creating new skills from external projects.

Token Budget Guard: Stop burning context. Achieve 99% token savings through progressive disclosure, conversation compression, and budget monitoring, ensuring native token awareness for every agent workflow.

This skill fetches and displays "Xinwen Lianbo" hotspots, grouping titles by source_name. It offers scheduled task creation via cron command and is triggered by "新闻联播".

A 3D globe visualization showing global traffic to AWS regions, with real-time user connections, latency-colored arcs, CloudFront edge node panels, P95/P99 metrics, error rate alerts, and sparkline trends. Ideal for global traffic monitoring dashboards, CDN/user distribution visualization, or real-time 'war room' displays for web applications served via CloudFront/AL.

An opinionated startup CEO coach, modeled after Matt Mochary's methodology and incorporating Dave Bailey's psychological insights. This skill coaches startup founders on becoming effective CEOs through structured sessions and maintains a CEO operating system via CONTEXT.md.

Resolve a context bundle of relevant specs for a feature

Use when a user, in the middle of a conversation, is rationalizing a decision, re-asking the same question multiple times, or looping on a negative topic. It names the cognitive pattern with a citation in an assumption-style voice, never diagnosing, advising, or for opening/ending a conversation.

Queries the token usage and costs of the Zhipu (GLM) API. Triggers when the user mentions Zhipu/GLM usage, costs, or balance.

Use for public, read-only Naver Finance and Npay Stock market data visible without login, including endpoint re-verification.

Use when a user asks to create text-to-video with HappyHorse 1.0, HiAPI HappyHorse 1.0, or this specific skill.

bstack P12 implements a Persistent Loop Discipline, a cross-context restart loop where state is maintained in the filesystem rather than the conversation. This approach, which spawns a fresh agent context each iteration, solves the 'context rot' failure mode that degrades long-horizon agentic work past ~100K tokens.