// AI Reviewed Skills
Skills evaluated and scored by AI for quality and usefulness
Each skill has been evaluated by an AI reviewer on a structured rubric: instruction quality, usefulness, technical soundness, and description precision. Scores range from 0 to 100 — skills scoring 75+ (green badge) are high quality, 50–74 (gold badge) are solid with targeted value.
View Review StatisticsShowing 1-12 of 14153 skills
Kessoku compile-time DI with parallel initialization for Go. Use when writing or debugging kessoku providers/injectors, enabling async dependencies, migrating from google/wire, or fixing go:generate/codegen issues in Go services.
Detect quality drops in AI output and prompt re-anchoring. Auto-triggers after repeated corrections, context confusion, or when user says "something seems off", "you're not getting this".
Design systematic decision frameworks for selecting appropriate AI tools (Claude Code vs Gemini CLI) based on context requirements, codebase size, reasoning depth needs, and task complexity. Use this skill when starting projects with unclear tool requirements, optimizing context-constrained workflows, or designing multi-phase strategies that leverage multiple tools' strengths. This skill helps match tool capabilities to task characteristics, preventing wasted context and ensuring optimal resource allocation.
Provides architectural guidance for data lake design including partitioning strategies, storage layout, schema design, and lakehouse patterns. Activates when users discuss data lake architecture, partitioning, or large-scale data organization.
Systematic peer review toolkit. Evaluate methodology, statistics, design, reproducibility, ethics, figure integrity, reporting standards, for manuscript and grant review across disciplines.
Generate new Navigator slash commands following project conventions. Use when user says "add slash command", "create command", "new /nav command", or "add /nav:[name] command".
Use this skill for PR preparation. Use when preparing PRs for submission, running quality gates, drafting PR descriptions and templates. Do not use when reviewing existing PRs - use pr-review instead. DO NOT use when: just generating commit messages - use commit-messages.
Use when Godot ParallaxBackground/ParallaxLayer nodes show incorrect positions in editor due to parallax multipliers. Calculates correct editor positions based on camera start position and parallax motion scale. Makes parallax layers preview realistically in editor, matching gameplay appearance.
Help users communicate more effectively in writing. Use when someone is drafting memos, emails, strategy docs, announcements, or any written communication that needs to be clear, concise, and persuasive.
Single deployable with enforced module boundaries for team autonomy without distributed complexity. Triggers: modular-monolith, module boundaries, single deployment, team autonomy Use when: teams need autonomy without distributed overhead DO NOT use when: already using microservices or system is small.
Help users plan and run effective team offsites. Use when someone is organizing a team retreat, planning a strategy offsite, trying to improve remote team cohesion, or preparing for quarterly planning sessions.
Setup visual regression testing with Storybook stories, configuration, and CI/CD workflows. Supports Chromatic, Percy, BackstopJS. Auto-invoke when user says "set up visual regression", "add Chromatic tests", "add screenshot testing", or "set up Percy".
Page 1 of 1180
