Chainlink Confidential AI Attester Skill
Chainlink Confidential AI Attester: submit private documents to an LLM inside an AWS Nitro Enclave and get back a cryptographically attested result — raw documents never leave the TEE. Use for these hackathon scenarios: (1) undercollateralized DeFi lending — upload a bank statement, get an attested approved/denied JSON decision without exposing financials on-chain; (2) accredited investor verification — check SEC Rule 501 qualification from brokerage statements privately; (3) KYC/AML screening — analyse ID docs and transaction history inside a TEE, return a pass/fail with flags; (4) proof of reserves — verify custodian balance reports against claimed reserves; (5) any use case where an AI must read sensitive user documents and the result needs a cryptographic proof of what model ran on what data. Trigger on: private inference, attested AI, TEE inference, confidential AI, or undercollateralized lending / KYC / accredited investor mentioned alongside document analysis.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/smartcontractkit/chainlink-agent-skills --skill chainlink-confidential-ai-attester-skillWhat comes with it
51 284 bytes besides the instructionWhat it tells the agent to use
found in the instruction textThe instruction itself
4 sections, as written by the authorChainlink Confidential AI Attester
Runs LLM inference inside Trusted Execution Environment (TEE). Documents go in, LLM analysis comes out — the raw documents are never stored or exposed.
Beta product for the EthGlobal NYC hackathon. Get an API key at the Chainlink booth or via the #partner-chainlink channel in the EthGlobal Discord.
Playground UI: https://confidential-ai-dev-preview.cldev.cloud/playground — easiest way to try it. Everything there maps 1:1 to the API calls below.
Workflow 1 — Submit: POST /v1/inference
Auth: Authorization: Bearer $API_KEY — always use an env var, never hardcode.
Request shape:
{
"model": "gemma4",
"system_prompt": "",
"prompt": "...",
"resources": [{ "filename": "doc.pdf", "content_type": "application/pdf", "content_base64": "<base64>" }],
"cre_callback": { "url": "https://..." }
}
cre_callbackis optional — omit it and poll instead.- Models:
gemma4(images/general, default),qwen3.6(long text). - Prefer PNG over PDF for demos — PDF preprocessing can take up to 5 minutes.
Response: 202 Accepted → { "id": "...", "status": "queued" } — save the id.
For curl examples and multi-language snippets → references/code-examples.md
For full request/response spec, error codes, resource types → references/api-reference.md
Workflow 2 — Poll: GET /v1/inference/{id}
Poll every 2–5 s until status is completed or failed.
Key fields on completion: output (LLM text), usage, completed_at.
For error symptoms → references/troubleshooting.md
Writing Prompts That Work
Always enforce JSON output with two layers:
- System prompt — keep the default unless you have a specific reason to change it.
- User prompt — binary question + exact JSON schema to return
For per-use-case prompt templates (lending, KYC, accredited investor, proof of reserves) → references/prompts.md
Other skills for the same job
different authors, same section of the catalogue
Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.
Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.6 Flash for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.
Context is the complete state available to a language model at inference time. It includes everything the model can attend to when generating responses: system instructions, tool definitions, retrieved documents, message history, and tool outputs.
Build semantic vector search systems with AgentDB for intelligent document retrieval, RAG applications, and knowledge bases using embedding-based similarity matching
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases.
Cherry Studio 产品知识库、源码路径索引、故障排查和页面导航。当用户询问 Cherry Studio 的功能、配置、报错、使用方法时触发。也适用于用户提到 provider、模型、知识库、Agent、MCP、OpenClaw、PDF、快捷短语等关键词的场景。
Add a persistent wiki knowledge base to a NanoClaw group. Based on Karpathy's LLM Wiki pattern. Triggers on "add wiki", "wiki", "knowledge base", "llm wiki", "karpathy wiki".
How to use it
Take smartcontractkit/chainlink-confidential-ai-attester-skill from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.