Agent Skills Hub

deepscan-monitor

Manage long-running PapersFlow DeepScan research workflows with asynchronous monitoring, live progress tracking, and automated report generation.

monitor

Automated PR CI monitoring and failure resolution agent.

Extract structured data from unstructured files (PDF, PPTX, DOCX...)

Implement LlamaExtract for robust structured data extraction from PDF, DOCX, and PPTX files using Pydantic schemas.

user-story-mapping

Create a hierarchical user story map to visualize the user journey, plan MVP releases, and align product, design, and engineering teams on workflow priorities.

submit-work

Submit completed tasks on OpenAnt via CLI. Handles text reports, file uploads (images, docs, code), and external proof links to ensure verified deliverables.

skill-architect

Expert consultant for designing and building high-quality, consistent AI agent skills. Guides you through discovery, architecture, and creation phases to ensure reliable, composable, and efficient skill delivery.

spec-metadata

Generates standardized metadata, including git/jj version info and timestamps, for research docs, handoffs, and implementation plans.

java-test

Executes Gradle-based Java tests, filters results for failures and key statistics, and provides concise reports to streamline backend development and debugging.

stop

Gracefully pause or close sessions: harvest context, archive work, verify features, and settle AtlasCoin bounties. Use when finishing for the day or wrapping up tasks.

prompt-engineering-patterns

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production applications.

github-gh

Interact with GitHub via the gh CLI to manage issues, pull requests, workflow runs, and execute advanced API queries programmatically.

clean-comments

Streamline your codebase by automatically removing redundant or obvious comments while preserving essential architectural and logic-focused documentation.