Skill UI

A comprehensive guide detailing the selection criteria for core modern system components, including databases (SQL/NoSQL), caching, message queues, and API protocols. It helps architects choose the optimal technology for specific use cases, scalability needs, and architectural patterns.

This skill guides coding agents through a comprehensive memory loop using AccInt's MCP server. It allows agents to retrieve prior outcomes, resolve complex reasoning frames, and formally close commitments with verifiable evidence (e.g., passing tests, successful merges). Essential for managing non-trivial, multi-step development workflows and ensuring work builds on genuine results.

This skill implements a rigorous, Fable-inspired workflow discipline for coding tasks. It enforces a strict process requiring the agent to inspect the codebase first, track multiple goals and findings, ground all conclusions in verifiable evidence, and perform thorough testing before declaring completion. It is ideal for complex, structured development, debugging, or adapting external prompt instructions into a disciplined, verifiable agent process.

A protocol for token-efficient, accurate, and structured web research. It guides the model to fetch minimum data when accessing URLs, GitHub repositories, or performing web searches, preventing token waste.

This skill provides deep security review for GitHub Actions workflow files. It focuses on the unique Actions threat model—identifying vulnerabilities like script injection via ${{ }} interpolation, privilege escalation from triggers (e.g., pull_request_target), and ensuring least-privilege permissions for CI/CD pipelines. Use it to audit, secure, or harden existing workflows, preventing attacks from untrusted inputs and supply chain risks.

This skill manages and maintains your personal context portfolio, a structured set of markdown files detailing your identity, professional roles, team information, and system configurations. It guides users through first-time setup interviews, detects missing or incomplete information (e.g., TODO placeholders), and facilitates targeted updates when your professional context changes.

This skill operates on two layers: the THINK layer enforces rigorous coding discipline (simplicity, surgical changes, goal-driven execution), and the SPEAK layer compresses prose output (caveman/classical modes) for maximum token efficiency. Use it when brevity is explicitly requested or when disciplined, high-precision code generation is required.