Loading...
Loading...
Found 147 Skills
Shelf framework guardrails, patterns, and best practices for AI-assisted development. Use when working with Shelf (Dart HTTP server) projects, or when the user mentions Shelf. Provides middleware patterns, request handling, pipeline composition, and server guidelines.
Core context and guardrails for OpenWork native app
Use this skill when building production LLM applications, implementing guardrails, evaluating model outputs, or deciding between prompting and fine-tuning. Triggers on LLM app architecture, AI guardrails, output evaluation, model selection, embedding pipelines, vector databases, fine-tuning, function calling, tool use, and any task requiring production AI application design.
CrewAI agent design and configuration. Use when creating, configuring, or debugging crewAI agents — choosing role/goal/backstory, selecting LLMs, assigning tools, tuning max_iter/max_rpm/max_execution_time, enabling planning/code execution/delegation, setting up knowledge sources, using guardrails, or configuring agents in YAML vs code.
Safety guardrails that warn before destructive commands. Use to protect beginners from accidentally running dangerous operations like rm -rf, DROP TABLE, git push --force, or git reset --hard. Provides beginner-friendly explanations of WHY a command is dangerous and suggests safer alternatives. Activate when the user mentions safety, careful mode, guardrails, protection, or when working with beginners on tasks involving file deletion, database changes, or git operations.
Use when any Maestro command is invoked — provides foundational workflow design principles across prompt engineering, context management, tool orchestration, agent architecture, feedback loops, knowledge systems, and guardrails.
Secure command execution sandbox with approval workflows, dangerous command detection, allowlisting, and audit logging. Runs commands in restricted environments with safety guardrails.
Umbrella skill for agent work discipline across development, analysis, and documentation: inspect the repo before restructuring, keep durable truth in repo artifacts instead of chat memory, co-evolve specs/design/steering/user docs with code, apply sound coding patterns, verify work honestly, avoid shortcuts, work efficiently with subagents without hallucinating, and keep moving through the next concrete work item when the human is away. References cover coding patterns, AI-authored code review, and artifact co-evolution. Trigger when the user asks for workflow discipline, coding patterns, doc/artifact maintenance, code review of AI-authored code, project hygiene, execution guardrails, repo normalization, or when a task risks drifting across architecture, storage, specs, continuity, or tooling boundaries.
Behavioral guardrails for Cavekit agents. Four principles — think before coding, simplicity first, surgical changes, goal-driven execution — that prevent over-engineering, silent assumptions, scope creep, and unfocused work. Every task-builder, reviewer, planner, and inspector must internalize these before writing a single line. Trigger phrases: "guardrails", "karpathy", "scope creep", "over-engineering", "stop adding features", "surgical fix".
Operate NEAR JSON-RPC reads through UXC with a public provider default, provider-override guidance, and read-only guardrails.
Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance.
Vendor-neutral skill to generate a staged feature-flag rollout plan (phases, metrics, guardrails, rollback criteria) from feature context and risk inputs.