Loading...
Loading...
Found 42 Skills
Best practices for using Claude Code in team environments. Covers skill management, knowledge capture, version control, and collaborative workflows.
[BETA] Execute work with external delegate support. Same as ce-work but includes experimental Codex delegation mode for token-conserving code implementation.
Configure AI coding agents like Cursor, GitHub Copilot, or Claude Code with project-specific patterns, coding guidelines, and MCP servers for consistent AI-assisted development.
Analyzes, generates, and enhances CLAUDE.md files for any project type using best practices, modular architecture support, and tech stack customization. Use when setting up new projects, improving existing CLAUDE.md files, or establishing AI-assisted development standards.
Use this skill when the user needs to turn an idea into a buildable spec, write a project scope, create feature requirements, or define an MVP. Covers quick feature specs (10-15 min) for immediate AI builds and full project scopes (1-2 hours) for planning and contractor estimates.
Project scaffolding and management for vibe coding. Initializes opinionated documentation structure, tracks features, and keeps agent context updated. Use when: setting up a new project, tracking features, viewing project status, or managing documentation. Works with Claude Code, OpenCode, Codex CLI, and other skills-compatible agents.
Bootstraps a new AI-assisted project through a structured 4-phase conversation, then generates PROJECT.md, JOURNAL.md, .gitignore, and tmp/README.md. Also searches skills.sh and installs relevant skills for the approved tech stack. Use when starting a new project from scratch or when no PROJECT.md exists in the current directory. Do NOT trigger if PROJECT.md already exists — redirect to /project-sync instead. Invoke with /project-init — never auto-trigger.
A comprehensive guide to building React apps with a modern 2026 stack, covering frameworks, build tools, routing, state management, and AI integration.
The root entry of the CodeStable workflow family — introduces the overall system to users and routes users' specific requests to the correct cs-* sub-skills. Trigger scenarios: users only input `cs` / `/cs`, say "introduce codestable", "do something with codestable", "I want to do X, which skill should I use", "don't know which one to use", or users' described requests are open-ended (e.g., "start working") and haven't converged to a specific sub-skill. This skill itself **does not perform actual tasks** — it doesn't write specs, write code, or read/write content products in the codestable/ directory — it only performs scanning, routing, prompting, and then transfers control to the target sub-skill.
Scaffold the Mimas agent instruction file tree for any repository — AGENTS.md at root, subdomain CONTEXT.md files, and the full agents-docs/ hierarchy (a sibling of any existing docs/, kept separate so human-maintained project docs stay untouched). Every file is tailored to the repo's actual tech stack, git platform, and conventions. Use this skill whenever someone wants to set up agent instructions, onboard a repo for AI-assisted development, add AGENTS.md / CONTEXT.md files, create engineering docs for agents, or mentions "set up agentic repository" or "mimas template". Even if they just say "set up this repo for agents" or "add agent docs", this is the skill to use.
Multi-Model Collaboration — Invoke gemini-agent and codex-agent for auxiliary analysis **Trigger Scenarios** (Proactive Use): - In-depth code analysis: algorithm understanding, performance bottleneck identification, architecture sorting - Large-scale exploration: 5+ files, module dependency tracking, call chain tracing - Complex reasoning: solution evaluation, logic verification, concurrent security analysis - Multi-perspective decision-making: requiring analysis from different angles before comprehensive judgment **Non-Trigger Scenarios**: - Simple modifications (clear changes in 1-2 files) - File searching (use Explore or Glob/Grep) - Read/write operations on known paths **Core Principle**: You are the decision-maker and executor, while external models are consultants.
Spec-Driven Development (SDD) methodology based on GitHub's SpecKit. Use for structured AI-assisted development with constitutional governance, phased workflows, and multi-agent coordination. Implements 7-phase process from constitution to implementation.