smyrick/smyrick-skills
Shane Myrick's reusable workflows for research, planning, code review, and writing.
Create source-grounded codebase architecture documentation with optional self-contained HTML diagrams.
Help Shane review a PR or local diff with a compact brief, consequential code and product decisions, a light architecture review, and guided discussion calibrated to his background.
Shape coding requests, ongoing implementations, and long AI conversations into coherent, verifiable chunks with fresh-task-ready handoffs and scannable PR documentation.
Rewrite prose to remove generic AI-writing patterns while preserving facts, meaning, and the writer's voice.
Create and maintain scoped PRODUCT_TERMS.md glossaries that connect product language, domain rules, and code references.
Run a source-grounded mock interview with stage-specific practice, evidence-based feedback, and optional session notes.
Research a non-code decision and produce a concrete recommendation and action plan. Select direct research, focused read-only leaf scouts, or an internal durable research subworkflow based on the evidence needed.
Research a code change and produce a decision-complete implementation plan. Select direct inspection, focused read-only leaf scouts, or an internal durable research subworkflow without modifying code.
Coordinate authorization-gated durable research for another skill or user request. Use when planning or decision work needs multiple focused passes, persistent findings, recovery, or a reusable evidence handoff.
Apply a concise coworker-style response mode that preserves technical depth, caveats, and required safety communication.
Create a product requirements document through bounded discovery, codebase context when available, and explicit product decisions.