Skill UI

A self-hosted, semantic memory service designed for AI agents. It allows agents to save worklogs, decisions, and notes, and recall this knowledge across sessions based on meaning rather than exact keywords. Using pgvector and structured workspaces, it maintains persistent, context-aware knowledge bases, making it ideal for collaborative AI projects.

SocialClaw is a powerful, agent-first skill designed for comprehensive social media automation. It allows users to schedule and publish content across 13 major platforms (including X, LinkedIn, Instagram, TikTok, and more) using a single workspace API key. Streamline your marketing campaigns by managing content creation, media uploads, scheduling validation, and performance analytics from one central workflow.

This skill orchestrates a complete, reproducible pipeline for bulk RNA-seq differential expression analysis. It guides users from raw FASTQ reads through QC, trimming, alignment (STAR/Salmon), quantification, generating a gene-level counts matrix, and concluding with differential expression analysis (DESeq2) and pathway enrichment. It ensures statistical soundness and reproducibility by connecting dedicated tools and enforcing proper experimental design.

This skill runs the Bumblebee scanner on macOS/Linux to perform read-only inventory and exposure checks. It detects compromised packages, developer tools, and host configurations against known security advisories. It is primarily used for supply-chain incident response and vulnerability assessment, providing developers with a clear picture of local system exposure.

A comprehensive toolkit for structuring prospective clinical study designs. It assists in selecting and classifying primary/secondary endpoints, estimating sample size and power for various designs (means, proportions, survival), and scoring overall study plan feasibility (GO/NO-GO). All outputs are estimates routed to specified human experts (clinicians, biostatisticians, regulatory owners), never presented as final facts or regulatory submissions.

A structured playbook for improving the time and space complexity (Big-O) of existing, slow code. This skill guides developers through systematic refactoring, focusing on identifying bottlenecks like nested loops or N+1 queries. It emphasizes applying transformations one at a time, maintaining test coverage, and measuring performance gains to ensure correct and efficient code.

A comprehensive guide for securing container images and runtime environments. Covers best practices from Dockerfile authoring (minimal base images, multi-stage builds, non-root users) through advanced runtime enforcement (seccomp, AppArmor) and Kubernetes security controls. Essential for production hardening and maintaining supply chain integrity.

This guide establishes the Conventional Branch specification for naming Git branches. It defines standardized prefixes (e.g., feature/, bugfix/, hotfix/) and enforces strict rules (lowercase, kebab-case, no underscores) to ensure consistency across development teams. Use it to validate, create, or understand the correct naming structure for any new branch, improving project traceability and collaboration.

This tool indexes local files or directories into a persistent FTS5 knowledge base. This allows subsequent search operations to efficiently retrieve highly relevant, focused snippets from the project source without needing to re-read the raw files every time. It is crucial for managing and searching large, complex codebases or detailed project documentation.

This tool accesses a persistent FTS5 knowledge base containing previously indexed project documentation, local content, and session memory. Instead of feeding entire raw sources into the conversation context, it allows users to perform targeted, efficient searches using specific queries and source scoping. This is ideal for quickly retrieving technical details, project specifications, or historical context without lengthy re-reading.

This skill guides users who feel stuck or overwhelmed by providing a structured, branching approach to complex problems. Instead of giving vague advice, it asks clarifying questions (3-5 options) at each level, progressively narrowing the infinite problem space until concrete, actionable steps are identified. Ideal for career changes, starting businesses, or making major life decisions.

This skill converts complex, narrative technical documents, research excerpts, or natural language problem descriptions into a highly structured Mathematical Problem Specification (MPS). It systematically extracts variables, constraints, objectives, and uncertainty parameters. By adhering to a strict Zero-Inference Protocol, it ensures all extracted elements are strictly grounded in the source text, making it invaluable for formalizing real-world optimization, data science, and engineering problems.