808 skills · sorted by relevance
Author and run unattended autonomous workflows — "workflow", "unattended", "run on a schedule", "automate this overnight", "set up an autonomous", "dry-run". Mandatory budget guards, a separate verification gate, idempotency, and dry-run on by default.
The English summary is being prepared. Showing the original description.
Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% b
The English summary is being prepared. Showing the original description.
Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool APIs, implementing permission systems, or creating autonomous coding assistants.
The English summary is being prepared. Showing the original description.
Review safeguards for AI agents authorized to sign or send transactions. Cover malicious instructions hidden in external data, spending caps, pre-send simulation, automatic stop conditions, protected transaction routing, and private-key handling through layered security checks.
Design or review repeating agent workflows with machine-checkable goals, protected boundaries, independent verification, and retry limits. It helps identify endless retries, manipulated checks, and incorrect completion while keeping final judgment with a human.
Develop applications through separate planning, building, and evaluation agents. The workflow tests the running app, scores its design and functionality, and feeds specific issues back into repeated development cycles with configurable quality thresholds and iteration limits.
Design and build AI agents for business, research, operations, or creative work. Define essential actions and knowledge, start with a simple execution loop, and add progress tracking or separate child agents as needs emerge.
Run one cycle of autonomous task work in Claude Code: check progress, select and execute the next action, log the work, and schedule another cycle. Stop when all tasks are complete or the iteration limit is reached.
Design the operating layer around a coding agent so it can read and edit code, run checks, and correct errors. Define completion criteria, permission boundaries, feedback, and recovery methods, and assess which tasks suit autonomous execution.
Design AI agents that break down goals, plan actions, use tools, and correct their own mistakes. The guidance focuses on reliable execution, clear operating boundaries, and managing conversation context as tasks grow longer.
Find autonomous AI agents, frameworks, and tools through AgentFolio. Compare their capabilities, intended users, integrations, and deployment options to shortlist existing products or gather examples and ideas before designing an agent of your own.
Plan and build AI agents through selected stages of design, implementation, tool integration, memory, and evaluation. The workflow points to specialized skills for single agents, coordinated agent teams, and stateful workflows using CrewAI or LangGraph.
Design autonomous agents for Claude Code plugins, including when they should run, what they should do, and which tools they may use. Provides file templates and guidance for validating configuration and testing behavior.
Design autonomous agents for Claude Code plugins, including when they should run, what tools they may use, and how they should respond. Provides configuration templates, prompt guidance, and validation steps for creating agent files.
Design AI agents that plan tasks, call tools, and retain useful information. Covers coordination between agents, evaluation, and debugging, with practical patterns for execution limits, error handling, and tracing what an agent does.
Build collaborating AI teams with CrewAI by defining roles, tasks, and shared context. Configure ordered execution or manager-led delegation, add memory and tools, and create workflows that branch based on events or results.
Plan and improve AI agent systems by managing the information models receive. This collection covers memory, agent coordination, tool design, context compression, evaluation, and the operating controls needed for reliable autonomous workflows.
Iteratively improve research by having Claude Code review code, results, and drafts while Codex implements fixes. Repeat until the assessment meets the stopping criteria or the round limit is reached, preserving feedback and unresolved issues.
Improve research through repeated Gemini reviews, code changes, experiments, and analysis. The workflow records full feedback and actions, then stops when both the score and readiness criteria are met or the round limit is reached.
Improve research code, results, and paper drafts through repeated review by a second Codex agent. The workflow implements fixes, checks them again, and records assessments and unresolved issues across up to four rounds.
Add pedestrians to a CARLA map and let them walk autonomously. Adjust crowd size, walking speed, road-crossing frequency, and placement seeds, create stationary crowds, and remove pedestrians together with their movement controllers in the correct order.
Populate a running CARLA simulation with autonomous traffic, evenly spaced vehicles in one lane, or a single vehicle for control and sensors. Filter vehicle models, keep automated driving active, and remove vehicles when the scene is finished.
Creates a Python agent skeleton for CARLA Leaderboard and checks its sensor configuration offline against the installed version’s rules. Covers version-specific initialization, driving logic, and ROS1 or ROS2 agent integration.
Build teams of AI agents with CrewAI, assigning roles such as researcher, writer, and analyst. Guidance covers passing results between tasks, running work in sequence or under a manager, adding memory, and creating workflows with conditional branches.