crewai
Workflow patterns and gotchas for CrewAI. Directs to RAG for implementation.
Découvrez les skills Outils, comparez leurs dépôts et consultez leurs instructions.
Workflow patterns and gotchas for CrewAI. Directs to RAG for implementation.
This skill should be used when the user asks about "visual builder", "no-code agent builder", "drag and drop", "ThinkingConfig", "extended thinking", "chain of thought", "reasoning", or needs guidance on using...
Workflow patterns and gotchas for LangChain. Directs to RAG for implementation.
Generate new Claude Skills for the Dual-Domain LLM Platform using natural language. Use when the user wants to create a new skill, automate a workflow, or build team capabilities. Activates when user mentions "...
Creates a git worktree for parallel development. Use when the user asks to "create a worktree", "set up a worktree for ", "make a worktree", or "/worktree". Enables running multiple Claude Code sessions on the...
Sets up and installs the AI Software Architect framework in a NEW project for the FIRST time. Use when the user requests "Setup .architecture", "Setup ai-software-architect", "Initialize architecture framework"...
Scans repository for security issues and automatically remediates them. Use when the user asks to "clean up security issues", "fix security problems", "remove sensitive data", "sanitise the repo", or "/repo-sec...
Creates a new Rails project with personal preferences (RSpec, PostgreSQL, Docker, master branch). Use when the user asks to "create a new Rails project", "start a new Rails app", "new-project-rails", or "/new-p...
Checks documentation consistency across the repository. Use when user asks to "check consistency", "are the documents consistent", "is everything aligned", "verify documentation", or "/repo-consistency".
Creates a NEW Architectural Decision Record (ADR) documenting a specific architectural decision. Use when the user requests "Create ADR for [topic]", "Document decision about [topic]", "Write ADR for [choice]",...
Reads emails from Gmail account. Use when the user asks to "look at emails", "check emails from [sender]", "read recent emails", or "/read-email". Fetches emails with full body content for analysis.
Rewrites git history to permanently remove sensitive data. DESTRUCTIVE OPERATION - rewrites commit history. Use when user asks to "purge secrets from history", "remove sensitive data from git history", "clean g...
Scans a repository for sensitive information and security vulnerabilities. Use when the user asks to "scan for security issues", "check for sensitive data", "repo security scan", "make sure this repo has no sen...
Extract and generate coding best practices from PR review comments. Use when the user asks to "extract best practices", "analyze PR comments", "generate coding standards", "create best practices from PRs", or "...
Specialized skill for performing deep web and code research regarding mojo and general software technologies. Use this skill when the user needs mojo specific or other language guidance, architectural analysis,...
Specialized skill for brainstorming technical ideas, architectural patterns, and syntax choices. Use this skill when the user asks to brainstorm ideas, implementation details, logic etc.
Coordinate with other agents using Swarm mail and file locking
Review relevant guidelines before starting a task
Initialize a new Python repository with correct structure following RAE guidelines
Use a subagent to review the code change and remove AI generated slop
Propose improvements to upstream RAE repository
Mandatory skill that ensures all work follows RAE guidelines. Activates automatically before any code task.
This skill should be used when the user asks to "execute plan with beads", "implement with persistent tracking", "bead-driven execution", "run plan with subagents", "track tasks across sessions", "use beads for...
Expert guidance on Supabase/PostgreSQL implementation for RAG, including pgvector semantic search and full-text search.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.