メニュー
Run Explee pre-built and custom AI agents, then poll run status and return structured outputs. USE WHEN running agent workflows for extraction, reasoning, or automation.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Shared reference for all Explee skills: base URL, full endpoint catalog, API-key authentication, canonical curl templates, and shared error/retry/guardrail rules. Other Explee skills reference this instead of repeating boilerplate.
Cookie/session and EXPLEE_SECRETS KV credential model for Explee: build the Cookie header, the cookie-first/key-fallback rule, and the cookie-vs-tracking-param pitfalls. USE WHEN setting up or refreshing Explee auth. Endpoints and API-key auth: see explee-api-core.
Orchestrate an end-to-end AutoGTM flow: ICP query → account/person discovery → enrichment → prioritized outreach list. USE WHEN building a full GTM pipeline from a natural-language objective.
Route user intent to the correct Explee product skill (Search, Enrichment, Agents, AutoGTM), using cookie-first auth with API-key fallback. USE WHEN a user has an Explee task but hasn't named the specific product.
Use Explee Search APIs to find companies and people with natural-language targeting and optional AI scoring. USE WHEN finding accounts, prospects, or converting an ICP to filters.
Use Explee enrichment APIs to find emails for contacts in single or batch mode and track async task status. USE WHEN completing outreach data or finding/verifying work emails.
| name | Explee Agents |
| description | Run Explee pre-built and custom AI agents, then poll run status and return structured outputs. USE WHEN running agent workflows for extraction, reasoning, or automation. |
Use this skill for extraction, reasoning, and automation tasks powered by Explee Agents.
Auth & endpoints: see explee-api-core. List uses T1, runs use T3, polls use T4.
GET /public/api/v1/agents — list agents + input_schemaPOST /public/api/v1/agents/{agent_id}/runs — run a pre-built agentPOST /public/api/v1/agents/runs — run a custom agentGET /public/api/v1/agents/runs/{run_id} — poll a runinput_schema.Run a pre-built agent (<agent_id> in the path, template T3):
{"input":{}}
input_schema before running.pending → completed / failed.