eks-to-agentcore
Guide for migrating AI agents from Amazon EKS to Amazon Bedrock AgentCore. Use when assessing EKS agent workloads for migration, scaffolding AgentCore…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-08 00:04
Agents & models
25,893 results
agentcore-browser
Browse web pages using a headless Chromium browser running inside the AgentCore container. Navigate to URLs, take screenshots, and interact with page elements…
incident-response
Receives CloudWatch/Prometheus alarms and automates severity classification, runbook lookup, hypothesis generation, diagnostic MCP queries, and human-approval-based remediation. SEV1 immediately pages on-call, SEV2/3 are drafted by the agent…
vllm-serving-setup
Design, deploy, and tune vLLM v0.18.2 inference serving on EKS with PagedAttention v2, Multi-LoRA, FP8 KV Cache, Chunked Prefill, and Continuous Batching.…
agent-admin
Used for the Agent's system_prompt, referencing/changing Knowledge, and creating a new Agent.
coralogix-ai-center
Coralogix AI Center — observe, evaluate, and guard GenAI/LLM applications and agents. Use for questions or actions about the user's AI/GenAI applications or…
agent-skills-best-practices
Apply this skill whenever creating, refining, restructuring, renaming, or auditing an agent skill under the host project's skill root (e.g., `.agents/skills/`)…
demand-intake
Pre-drafting context gathering for a demand letter — parties, facts, basis, leverage, BATNA, and privilege filters — written to a structured intake.md the…
escalation-flagger
Route a contract issue to the right approver per the escalation matrix in `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`, and draft the…
oc-status
Generate weekly status-request email drafts to outside counsel across the active portfolio — markdown per matter, plus Gmail drafts when the MCP is available.…
review-proposals
Review and approve (or reject) pending playbook update proposals from the playbook-monitor agent and apply approved changes to the practice profile. Use when…
skill-manager
Reference: detailed uninstall, disable, and re-enable workflows for community skills installed via the legal builder hub. Safe by default — refuses to touch…
academic skill eval team
Use this skill whenever the user wants to evaluate a skill or skill pack with an agent team, audit trigger phrases, inspect workflow completeness, stress-test…
ljg-push
Sync all updated skills in ~/.claude/skills/ljg-* to the github repo (ljg-skills): first push the master branch (org-mode output style), then switch to the md branch (markdown output style) and push after basic markdown conversion. Use when user says…
ljg-read
Reading companion agent. Accompanies user through any text (books, articles, essays, papers, news) with translation, structural annotation, deep questioning,…
subagents-and-teams
Comprehensive guide to creating custom subagents and orchestrating agent teams in Claude Code. Use when creating custom subagents, configuring agent teams,…
reinforcement-learning
Reinforcement Learning best practices for Python using modern libraries (Stable-Baselines3, RLlib, Gymnasium). Use when: - Implementing RL algorithms (PPO,…
skill-advisor
Skill hygiene tool: analyzes the installed skill ecosystem, identifies overlapping, conflicting, removable, and trimmable skills, and uses interactive Action Cards to guide the user through cleaning them up one by one. Triggers: "analyze skill", "skill cleanup", "skill advisor", "analyze skills", "skill health", "too many skills…
action-patterns
This skill should be used when understanding how @1sat/actions work — the action/context pattern, two-phase signing (createAction/signAction), BEEF resolution,…
collections
This skill should be used for 1Sat collection protocol and collection-overlay questions — including 'create a collection', 'collectionItem', 'collectionId',…
codex-agent-setup
Explicit-only installer for the Product Skills Anthony and Caal Codex custom agents. Use ONLY when the user explicitly asks to install, update, check,…
legal-agentic-build
Use when designing or building agentic legal workflows, multi-agent compliance pipelines, or legal AI architecture with Vercel AI SDK or CrewAI. Not for…
orchestrator
Use this skill when a capable current Claude Code or Codex main session should coordinate native specialist agents, external implementation workers such as…
add-gmail-agent
Wire Gmail MCP server into the agent so it can read, search, and send emails. Optional — not core functionality.