senior-computer-vision
Computer vision engineering workflow for dataset design, model selection (detection/segmentation/classification), evaluation, inference optimization, and…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,657 results
dual-llm-contradiction-dialog
Orchestration of a structured dialogue between two LLMs (A and B) around the same topic, with intent framing, blind-spot generation, research…
intent-guard-shield
Skill for protection against silent bypassing, false successes, and interpretive drift in agentic systems. It helps to formalize…
agent-card-templates
A2A agent card JSON templates with schema validation and examples for different agent types. Use when creating agent cards, implementing A2A protocol…
mem0-fastapi-integration
Memory layer integration patterns for FastAPI with Mem0 including client setup, memory service patterns, user tracking, conversation persistence, and…
ai-llm-integration-in-fullstack-apps
Integrate LLM features safely with prompt governance, guardrails, observability, and cost controls in fullstack apps.
file-storage-and-media-delivery
Manage object storage for uploads, media, and documents across S3, Azure Blob, or GCS with secure access patterns.
slack-agent
Use when working on Slack agent/bot code, Chat SDK applications, or projects using @chat-adapter/slack. Provides development patterns, testing requirements,…
git-guardrails-claude-code
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent…
write-a-skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be handled without shared state or sequential dependencies
executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
add-rules
Compile durable constraints into OpenViking Rules with rules/compile. Use when the user asks to add rules or import a policy. Do not use for preferences,…
autonomous-agents-papers-guide
Daily-updated collection of autonomous AI agent papers
agent-context-budget
Use when an agent task needs bounded context packets, checkpoint-aware compaction, a fresh-session primer, or policy-controlled child results without loading…
agent-plan-act-reflect
Use when one agent must iteratively plan, act, evaluate evidence, and revise under a readable policy until acceptance, checkpoint, stop, or human escalation.
agent-task-splitter
Use when a goal needs multiple bounded agent roles, parallel or dependent task packets, explicit scope partitions, and a provider-neutral DAG. Not for…
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
jev-simulation
Use for game, NPC, interactive-story or training-simulation decisions from explicit world state and legal actions. Humans or a planner define objectives; a…
mcp-builder
mcp-builder — an installable skill for AI agents, published by xenitv1/claude-code-maestro.
subagent-engineering
Design and maintain Claude Code subagents: the delegation decision, the frontmatter that governs a run, and the system prompt the agent wakes up with.
only-you
Propose the tasks on a repository that only a frontier-tier model can execute — the work the model one tier below or a routine engineer would fail at or do…
gjc-delegation
Delegate planning and execution workflows to gajae-code via the coordinator MCP server.