coinbase-agentkit
Coinbase AgentKit — build AI agents with onchain capabilities. Wallet creation/management, token transfers, swaps, contract deployment, NFT minting, and ENS…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,648 results
goat
GOAT (Great Onchain Agent Toolkit) — 200+ protocol integrations across 30+ chains. Tool creation, framework adapters (AI SDK/LangChain/Eliza), DeFi actions…
simple-skills-manager
Manage skills from local paths or git repositories - add, update, or remove skill tips in ~/.claude/skills with group-skillname format
atai-rare-event-detection-agent-data-prep
Prepare a labelled sensor recording for Archetype AI's Rare Event Detection (RED) agent, locally and with no API key: put it on an exact sample grid, map its…
mcp-harness-repo-maintainer
Maintains repo-local action contracts and harness repositories where product CLI and MCP adapters stay thin over core libraries. Use when adopting or improving…
skill-source-citations
Requires durable citations when authoring or researching Agent Skills—maintain references/sources.md per skill, link external research, and record provenance…
subagent-dev
This skill MUST be invoked when tasks.md is ready and autonomous parallel execution by subagents (implementer + reviewer for each task) is required. SHOULD…
ai-for-science-ankh
Ankh protein language model Ascend NPU migration Skill, suitable for migrating Ankh base/large, Ankh3 large/XL, and similar protein models based on HuggingFace Transformers and PyTorch from CUDA/GPU to Huawei Ascend NPU…
external-mindstudio-msmodelslim-model-adapt
Create a basic Transformers model adapter for msModelSlim. Includes creating the adapter, implementing the required interfaces, and a four-step verification process. Applies to: Decoder-only LLMs, understanding-type VLMs (LLM/text part only). Does not apply to: multimodal generation models (image/video/speech generation), Encoder-only, non...
external-mindstudio-msmodelslim-model-analysis
Analyze the candidate model before implementing the adapter. Determine the model implementation source (transformers or model directory), structural features, whether layer-by-layer loading is required, and MoE fused weight risks. Use when the user asks about model adaptation feasibility or when performing pre-adaptation analysis.
mindspeed-mm-weight-prep
MindSpeed-MM weight conversion guide using mm-convert CLI tool. Covers HuggingFace to MindSpeed-MM format conversion, reverse conversion, and PP weight…
wave-planner
Plan and execute large multi-step, multi-stack changes with contract-first waves, parallel worker ownership, user approval gates, ordered integration, and…
shape
Interview the user to resolve material branches of a decision tree and converge on a shared plan before acting. Use when multiple reasonable choices would…
abap-vscode-pce
ADT VSCode guidance for agents working on ABAP code and Repository Objects in VS Code with the virtual ABAP workspace folder, where uri starts with abap:/ For…
argus
Argus — the all-seeing scanner suite. Six automated scanners for high-value web + LLM bug classes — CORS misconfiguration (origin reflection / null /…
eks-genai
Use whenever someone is building, training, fine-tuning, or serving a generative AI / LLM workload on Amazon EKS — phrased as "GPU vs Trainium/Inferentia",…
convergence-loop
Use when orchestrating a large multi-agent audit, review, sweep, or migration that must converge rather than finish in one pass — whole-repo quality audits,…
omo-agents
A multi-agent orchestration system in the style of oh-my-opencode. Provides 7 specialized agents working together: Sisyphus (main orchestrator), Oracle (architecture advisor), Librarian (documentation research), Explore (code search), Frontend Engineer (UI/UX), Document Writer (documentation writing), Multimodal...
autoboy
AutoBoy by The Firm — the pre-launch order book for Bankr launches on Base. Use when an agent wants to buy a token before it launches, or launch its own token…
gate
Harness-portable quality gate for branch changes — spawns parallel reviewer subagents (Bug, SOLID, Security, Simplify+Slop, optionally…
ai-sdk-core
Expert guidance for AI SDK Core: text generation, structured data, tool calling (tool/dynamicTool), MCP integration (createMCPClient,…
bmad-os-review-prompt
Review LLM workflow step prompts for known failure modes (silent ignoring, negation fragility, scope creep, etc). Use when user asks to "review a prompt" or…
agent-harness
Test and evaluation harness for AI agents — scenario suites, deterministic replay, regression diffing, cost and latency budgets. Use when agent quality is…
judge
DEPRECATED: Use /council instead. Multi-model validation council.