Explee product ai agents

Skill Sheshiyer/skill-clusters/skills/explee-product-ai-agents

Run Explee pre-built and custom AI agents, then poll run status and return structured outputs. USE WHEN a task matches the Craft workspace workflow for explee-product-ai-agents.From its SKILL.md

Install

npx -y skills add Sheshiyer/skill-clusters --skill explee-product-ai-agents

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.8 KB, 430 tokens by cl100k_base, as published. Nobody here has run it

Explee Product Skill — AI Agents

Use this skill for extraction, reasoning, and automation tasks powered by Explee Agents.

Authentication

Use API key auth:

Header: X-API-Key: <api_key>
Base URL: https://api.explee.com

export EXPLEE_API_KEY='<your_api_key>'

Primary Endpoints

GET /public/api/v1/agents
POST /public/api/v1/agents/{agent_id}/runs
POST /public/api/v1/agents/runs
GET /public/api/v1/agents/runs/{run_id}

Execution Pattern

List available agents and inspect input schema.
Choose pre-built agent if available; otherwise run custom agent.
Submit run with minimal valid input.
Poll until completion, then return normalized result.

Request Templates

List Agents

curl 'https://api.explee.com/public/api/v1/agents' \
  -H 'Accept: application/json' \
  -H "X-API-Key: ${EXPLEE_API_KEY}"

Run Pre-built Agent

curl 'https://api.explee.com/public/api/v1/agents/<agent_id>/runs' \
  -X POST \
  -H 'Accept: application/json' \
  -H 'Content-Type: application/json' \
  -H "X-API-Key: ${EXPLEE_API_KEY}" \
  --data '{"input":{}}'

Poll Agent Run

curl "https://api.explee.com/public/api/v1/agents/runs/${RUN_ID}" \
  -H 'Accept: application/json' \
  -H "X-API-Key: ${EXPLEE_API_KEY}"

Guardrails

Validate payload against returned input_schema before run.
For custom agents, keep system prompts concise and deterministic.
Always report run status lifecycle (pending → completed/failed).

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.