behavioral-modes
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
Découvrez les skills tools scripting, comparez leurs dépôts et consultez leurs instructions.
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.
Convert raw task input into a machine-safe execution plan or explicitly refuse to proceed. Use before any code changes in unattended/headless mode to ensure deterministic, safe task execution.
Generate execution plans from user queries through intake, research, specification, and validation. Use when user provides any query (vague to specific) and needs an executable plan for /execute skill.
Deterministic plan execution with mathematical certainty. Use for implementing IMPLEMENTATION-PLAN.md files with triple verification, git workflow, and cross-session context sharing. Works identically for rad-e...
Documentation automation with file versioning and metadata. Use for maintaining documentation, tracking file versions, adding metadata headers.
Chrome browser automation skill for AI-controlled testing and interaction. Use when performing browser automation, E2E testing, form filling, or UI verification tasks. Includes test credentials and common opera...
Generate automation scenarios from natural-language requests by drafting `scenarios//plan.json` plus supporting files (behaviors, curl, SQL mocks). Use when a user asks to create or update a scenario or wants a...
This skill should be used when the user asks to "create a Worker", "build a Worker", "deploy to Workers", "configure wrangler.toml", "use Durable Objects", "setup KV storage", "use D1 database", "configure R2 b...
Execute Python code in an isolated environment for calculations, file generation, and data processing
Creates, analyzes, updates, and improves Claude Code hooks including configuration, scripts, and security validation. Use when user asks how hooks work, explaining hook concepts, understanding hook types and ev...
Security best practices and guidelines for the Jarvy CLI codebase - a cross-platform development environment provisioning tool that executes system commands with elevated privileges
Master Python asynchronous programming with asyncio, async/await, and concurrent.futures. Use for async code and concurrency patterns.
Use when writing shell scripts that need to run across different systems, shells, or environments. Covers POSIX compatibility and platform differences.
Use when writing or modifying Bash/shell scripts. Covers script structure, variables, quoting, conditionals, and loops with modern best practices.
Use when implementing error handling, cleanup routines, or debugging in shell scripts. Covers traps, exit codes, and robust error patterns.
Automations & Ops Engineer that reduces manual work through automatic alerts, notifications, and scheduled tasks. Use when implementing notifications, alerts, or background jobs.
Spec-driven development with task-by-task execution. Transforms feature ideas into structured specs (research, requirements, design, tasks) then executes them autonomously with fresh context per task. Supports...
Farm out AI tasks via Named Pipe to get isolated context. Use when processing large files, batch summarization, or to avoid context pollution. Each call runs in fresh context.
Unified execution engine for all development workflows. Progressive disclosure for phase execution, quick features, story completion, and scaffolding. Integrates with artifact-tracking and meatycapture-capture....
High-velocity, intent-driven development using agentic workflows and MCP servers.
Browser automation CLI for AI agents. Use for web scraping, testing, screenshots, form filling, and headless browser interactions.
How to use the natscli tool when not directly available
CLI tool for working with eyepop workers
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.