
Use when you have a PRD and need to design the technical approach — components, data flow, dependencies, and tech decisions — before breaking work into tasks.
Rewrite AI-generated text to remove LLM tells and make it read like a human wrote it. Use when the user mentions 'humanize', 'sounds like AI', 'too robotic', 'make it natural', 'AI slop', 'rewrite naturally', or when reviewing text that exhibits LLM writing patterns.
Meta-skill for writing compact skill definitions. Reduces skill file size without losing instructions. Use when creating or refactoring SKILL.md files, or when another skill asks for compact/terse/shorter rule definitions.
Use when you have a defined goal and need to explore different approaches before committing to a direction. Use when there are multiple valid solutions, when trade-offs need evaluation, or when the best approach is not obvious.
Use when starting analysis on a codebase, before any planning or design work, or when you need to understand an existing project's structure, patterns, and constraints.
Use when you have a PRD and architecture document and need to slice work into ordered, interlinked development tasks with acceptance criteria and verification steps.
Rebase current feature branch onto master (or configured base) with automated conflict resolution. Handles pre-checks, conflict classification, and post-rebase verification. Use when the user asks to rebase, update a branch, sync with master, or resolve rebase conflicts.
Idea to implementation-ready plan: requirements, design, tasks, optional compile to issue files. Research on demand for repo context. Phase rules live in ./references/.
Use when you have a raw idea or feature request and want to go from idea to implementation-ready task list through a structured 3-phase pipeline — requirements, design, tasks. Uses research on demand to gather codebase context whenever needed.
Strip LLM tells from text so it reads human. Triggers: humanize, sounds like AI, too robotic, natural rewrite, AI slop, or obvious LLM patterns. Reference: https://en.wikipedia.org/wiki/WP:Signs_of_AI_writing
Concise technical communication that stays readable and honest. Cuts fluff about fifty to seventy percent while keeping natural flow, uncertainty markers, and human tone. Levels lite (default), mid, tight. Short SKILL body; rules below are complete.
Guide frontend development toward websites that feel premium and trustworthy, grounded in cognitive science research (processing fluency, prototypicality). Two modes: active guidance during build, and audit (problems + suggestions). Use when building UI, reviewing frontend code, or when the user mentions premium, trust, design quality, audit, review, or frontend polish.
Guardrails for coding: surface assumptions before acting, write minimal solutions, make surgical edits, tie every task to verifiable criteria. Use when writing, reviewing, or refactoring code. Biases caution over speed; relax for trivial edits.
Use when starting work on any project to produce or update living documentation (TechStack.md, ProjectStructure.md) that bootstraps context for any AI agent session. Run before any feature work, or periodically to keep docs current.
Concise technical communication that stays readable and honest. Cuts fluff ~50-70% while keeping natural sentence flow, uncertainty markers, and human tone. Supports intensity levels: lite (default), mid, tight. Use when user says "techtalk mode", "use techtalk", "be concise", "less fluff", "talk shorter", or invokes /techtalk. Also auto-triggers when brevity is requested without sacrificing clarity, or when compact/precise/terse output is explicitly asked for in context.
Use when you have a chosen direction and need to formalize requirements into a Product Requirements Document. Use when user stories, acceptance criteria, and scope boundaries need to be written down before architecture or implementation.
Use when you have a raw idea or request and need to define a clear goal with success criteria before exploring solutions. Use when requirements are vague, when "what does done look like" is unclear, or when assumptions need surfacing.
Use when you have a raw idea or request and want to run the full analytics pipeline automatically — from research through to an interlinked task list. Best for straightforward problems where the full pipeline can flow with minimal back-and-forth.
Code review skill for Vue 3, TypeScript, and Rust projects. Discovers what to review (uncommitted, committed, or GitHub PR), applies structured review process with severity-labeled feedback, language-agnostic quality rules, and language-specific references. Use when: reviewing code, code review, MR review, quality check, reviewing changes.
FE feature analysis from raw idea (or YouTrack ticket) through to a split-aware developer briefs. Produces context-map.md, requirements.md, task-brief-{side}.md. Generic — project knowledge is auto-discovered.
Shrink SKILL.md files without dropping rules: remove duplication, trim exposition, merge examples into definitions. Use when authoring/refactoring skills or when asked for compact/terse rules.