inno-prepare-resources
Automates research resource preparation by loading instances, searching GitHub for codebases, building dataset descriptions, and downloading arXiv papers.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
505 skills found
Automates research resource preparation by loading instances, searching GitHub for codebases, building dataset descriptions, and downloading arXiv papers.
Writes, executes, and refines SQL queries, from basic selects to complex multi-table joins, aggregations, and subqueries for data retrieval and reporting.
Generate hierarchical, token-efficient AGENTS.md files for AI coding agents to provide repository-wide context and project-specific guidelines.
Fetches Confluence PRDs and transforms them into structured local Markdown for the spec-kit specify workflow, bridging PO handoffs into technical SDD implementation.
Expert guidance for Claude Messages API: structured outputs, prompt caching, tool use, and migration from deprecated Claude 3.x models to 4.5. Prevents common API errors.
Token-efficient codebase analysis skill for call graphs, semantic search, impact analysis, and data flow. Saves ~95% tokens vs. raw reads.
Robot perception system design, configuration, and optimization for cameras, LiDAR, and sensor fusion pipelines. Includes camera calibration, 3D reconstruction, and production deployment best practices.
Structured 6-phase workflow for planning and implementing features, skills, and architectural changes with automated tool discovery and safety verification.
Implement production-grade Kubernetes security using NetworkPolicy, RBAC, Pod Security Standards, and OPA Gatekeeper policies.
Capture and formalize software development ideas into structured design documents within the Hashbrown repository, including research and conceptual sketches.
Remotely control tmux sessions for interactive CLIs by sending automated keystrokes and scraping pane output.
A comprehensive automation skill for Cosense (formerly Scrapbox) enabling page reading, searching, creating, and safe editing via API.