Skills matching the name, description or GitHub author.
Spawn and manage terminal tabs via TabzChrome REST API. Use when spawning workers, creating terminals programmatically, setting up worktrees for parallel work, monitoring worker status, or sending prompts to Cl...
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for...
Guide for creating effective skills using TypeScript/Bun scripts (Windows-compatible). Use when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized...
Centralizes Diataxis documentation framework guidance so Claude can write, review, or improve documentation following the four distinct types (tutorials, how-to guides, reference, explanation).
Autonomous AI coding loop that ships features while you sleep. Use when the user wants to run Ralph, start an autonomous coding session, work overnight, or let Claude implement multiple user stories autonomousl...
Centralizes persona-driven code reviews (Carmack, React core, Anders, React Router, Next.js, etc.) so Claude can pick or combine expert viewpoints when the user asks for a code review or perspective-specific cr...
Guide for evaluating models using scenarios specified by the user. This skill should be used when users ask Claude to evaluate a model using a specific scenario.
タスクの性質を LLM ベースで深く分析し、適切な executor（claudecode/codex/coderabbit/user）を判定する専門 Skill。キーワードベースの単純判定を置き換える。
Create Claude Code sub-agents with optimal configuration. Use when users ask to create a new agent, custom agent, specialized assistant, or want to configure task-specific AI workflows.
Create atomic commits grouped by logical features with README.md and CLAUDE.md awareness.
Configure Claude Code's terminal status line display
Review local codebase for bugs and CLAUDE.md compliance using multi-agent analysis
Diagnose slow Claude Code startup and guide cleanup. Use /bluera-base:clean to run.
Validate/update/create CLAUDE.md memory files with progressive disclosure and context-optimized structure
Use when Claude Code hits "File content exceeds maximum allowed tokens" error, or when files are too large to read. Helps analyze and break apart large files into smaller, focused modules.
Captures valuable insights and documents them in CLAUDE.md. Auto-triggers when: discovering gotchas or unexpected behavior, completing significant features, fixing complex bugs, making architectural decisions,...
This skill should be used when the user asks to "check CLAUDE.md compliance", "review against coding standards", "check AI agent instructions", "verify guidelines", "check coding conventions", "check naming con...
Extract and read Claude conversation JSONL files with composable filters (discovery: rubber-duck). Evaluate at rubber-duck or at any point in the sesssion when task requires reading conversation history, verify...
Initialize a new repository with standard scaffolding - git, gitignore, CLAUDE.md, justfile, mise, and beads. Use when starting a new project or setting up an existing repo for Claude Code workflows.
Sandbox Runtime (srt) patterns for CLI/autonomous Claude runs. For interactive sandboxing, use Claude Code's built-in `/sandbox` command instead.
Activate at session start when you are the primary Claude instance. Establishes orchestrator role with delegation protocols, subagent launch templates, token efficiency rules, and parallel safety constraints. Y...
Analyzes Claude Code Skills for lint issues and duplicate content. Use when user asks to analyze skills, lint skills, check quality, or find duplicates.
A generic helper for various tasks. Assists with common operations.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or to...
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.