aws-sagemaker
AWS SageMaker is a fully managed platform for building, training, and deploying machine learning models with integrated
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-26 00:15
Agents & models
24,835 results
nft
Skill for creating, managing, and interacting with Non-Fungible Tokens (NFTs) on blockchain networks.
prompt-engineering
Crafting effective prompts for AI models to optimize outputs and performance.
skill-graph
Neo4j query interface for skill discovery — replaces flat skill injection, Cypher traversal
agent-memory
Sets up and drives TencentDB Agent Memory (MemoryCore, MemoryHub, MemoryProxy, MemoryPanel) for agent teams. Use when the user mentions "memory hub", "team…
anycap-seedance-2
Compile user intent, scene beats, and reference assets into compact, controllable Seedance 2.0 prompts executed through the AnyCap CLI. Use when creating,…
veo-3.1-prompting
Expert guidance for Google Veo 3.1 video generation. Use when the user wants to (1) create text-to-video or image-to-video prompts, (2) optimize for cinematic…
secrets-hygiene
Audits which skills have access to secrets, flags stale or unrotated credentials, and prompts rotation. Use weekly to keep credentials clean.
workspace-integrity-guardian
Detects drift or tampering in SOUL.md, AGENTS.md, MEMORY.md, and other critical workspace files and prompts recovery
verify-patterns
Verify AI agent patterns including loop safety, retry limits, tool consistency, context size, and graph cycle analysis. Use when asked to "verify agent…
hackathon-track-analyzer
Parse hackathon track descriptions and sponsor briefs to extract structured constraints, evaluation criteria, and strategic opportunities.
cuihuo-audience-analysis
Deconstruct, from the audience's perspective, what value a video, image-text post, or piece of copy actually provides. Use the five-dimensional model of cognition, emotion, identity, action, and social to complete an overall, node-level, or sentence-by-sentence analysis; use when the user says "deconstruct this one," "audience-perspective analysis," "what value does this provide to the audience," or "deconstruct sentence by sentence."
cuihuo-chatroom
Legacy-name compatibility entry for "Quench Brainstorm." It accepts legacy invocations such as /cuihuo-chatroom, "bounce this idea around," "chat about an idea," and "idea collision," and passes the user's exact words through in full to Quench Brainstorm. The old semantics of "first step of the content pipeline, the host extracts judgment fragments, and automatically enters the logic chain" are no longer active.
gds-agent-game-architect
Game systems architect for technical architecture, engine design, and infrastructure. Use when the user asks to talk to Cloud Dragonborn or requests the Game…
account-rotation
Switch coding-agent accounts and verify runtime identity. Use when: the caller requests an account change; never rotate automatically to evade a quota.
automation-shape-routing
Front door for agent automation: choose inline, bounded fanout, reusable skill/workflow/gate, persistent agent-native workers, or explicit Gas City. Triggers:…
llm-wiki
Build external-knowledge wikis.
skill-architect
An integrated skill architect and format review tool that consolidates the official skill-creator workflow, the former skill-lint compliance check, and release specification synchronization. This skill should be used when users need to create new skills, edit existing skills, package skills, review skill format compliance, check Frontmatter/version/documentation consistency, or generate skill audit reports. Do not use for: creating non-Claude…
harness-engineering
Set up OpenAI's harness engineering methodology in any repository. Creates the full agent-first infrastructure: AGENTS.md progressive disclosure map,…
consult
AI consultation CLI — query Gemini, Codex, or Claude for reviews and analysis. ALWAYS check this skill before running any `consult` command. Use when reviewing…
agents-ui
Build React frontends for LiveKit voice AI agents. Use this skill when creating web interfaces for voice assistants using LiveKit's shadcn-based Agents UI…
setup-tracing
Configure an AI agent to send OpenTelemetry traces to Coval. Use when a user wants to add Coval tracing, instrument an agent for simulations or conversation…
storage-sync
Synchronize memories between Turso (durable) and redb (cache) storage layers. Use when cache appears stale, after failures, or during periodic maintenance.
claude-code-in-slack
Runs a local daemon connecting your machine to the Claude Code in Slack server. Receives tasks from Slack, drives Claude Code locally via…