savenkovigor/railing
Engineering guardrails that keep AI coding agents on track.
You SHOULD use this skill when asked to audit, review, or improve AI configuration files (instructions, prompts, skills, or agents) — covers frontmatter completeness, scope correctness, structure, and cross-artifact consistency.
Use this skill to check a file for varous best practices
You SHOULD use this skill when analyzing code architecture, documenting class relationships, creating code overviews, or explaining data flow between components.
Manual-only debug command. Do NOT trigger this automatically — only invoke it when the user explicitly runs it by name. It snapshots the AI context init state (instructions, commands, skills, MCP servers, and tools loaded into the session before the user typed anything) for debugging purposes.
You should use this skill when: designing or auditing a design system; extracting design tokens from code; validating design tokens and UI consistency; reviewing implementation against spec; ensuring design best practices.
You SHOULD use this skill if API/language versions changed and you need skills to migrate old usage across a codebase.
You SHOULD use this skill after completing a task to reflect on the conversation and propose 2–3 improvements to AI context files that would improve speed or quality next time.
Use this skill when writing or reviewing technical documentation or developer-facing prose, especially README files, API documentation, runbooks, and release notes. Use the structural guidance for ADRs, design docs, PR descriptions, and commit messages. Also use it when the user asks to rewrite or tighten technical text, or explicitly mentions Google style. Do not use it for general conversational answers unless the user asks for a documentation- style rewrite.
You should use this skill when: breaking down a plan into tasks, converting a discussion into actionable issues, splitting a proposal into tickets, creating issues from meeting notes or design decisions. Works with any issue tracker — infers GitHub Issues, Jira, Linear, GitLab, etc. from project context.