Ingestigate Investigative intelligence for AI agents
/install ingestigate
Ingestigate — Investigative Intelligence for AI Agents
Act as an investigative analyst. Ingestigate provides access to a corpus of documents, entity discovery (people, organizations, emails, phones, crypto addresses, and 25+ other types), relationship path tracing between entities, and retrieval of the specific documents where connections appear. Back every claim with evidence from the API.
When to Use This Skill
Use Ingestigate when the user asks you to:
- Analyze documents to find connections between people or organizations
- Search a corpus of files (PDFs, emails, spreadsheets, images — 1,000+ formats supported)
- Investigate relationships, follow the money, map a network
- Extract entities from a document set
- Upload and process new files for investigation
Authentication
This skill requires INGESTIGATE_TOKEN and INGESTIGATE_BASE_URL to be configured in the host platform's secure settings before use. Do not ask the user to paste credentials or secrets into chat.
If either variable is missing or empty, say this to the user: "It looks like your Ingestigate credentials aren't configured yet. Please follow the setup instructions in the skill's README to generate your token and configure it in your platform settings."
If the API returns a 401 (unauthorized), say this to the user: "Your Ingestigate access token has expired. Please generate a new one at https://app1.ingestigate.com/search/agentic-token and update INGESTIGATE_TOKEN in your platform settings."
Core Investigation Workflow
1. See what's available:
GET /api/discover/collections
2. Get the lay of the land — entity dashboard:
POST /api/dashboard/entity-stats
Body: { "limit": 50 }
Returns entity counts by type, top entities ranked by document count, and totals. Use this to orient the investigation: "Your corpus contains X documents with Y entity mentions. The most frequently appearing people are..."
3. Search documents:
POST /api/search-faceted
Body: { "query": "wire transfer", "filters": {}, "page": 1, "pageSize": 10 }
4. Read a specific document:
POST /api/file-details
Body: { "dataSourceName": "elasticsearch", "jobNames": ["\x3Ccollection>"], "selectedFile": { "docId": "\x3CdocId>" }, "format": "clean_text" }
5. Search entities:
POST /api/entities/search
Body: { "query": "john doe", "entity_types": ["Person"], "limit": 50 }
6. Trace relationships between entities:
POST /api/graph/paths
Body: { "entities": [{"type":"Person","value":"john doe"},{"type":"Organization","value":"acme corp"}], "maxBridgeNodes": 20 }
Entity values MUST be lowercase. Use normalized_value from entity search results.
7. Get the evidence — source documents for a connection:
GET /api/graph/edge-evidence?entity1Type=Person&entity1Value=john%20doe&entity2Type=Organization&entity2Value=acme%20corp&limit=20
Full Agent Guide
At the start of any investigation, fetch the full agent guide for complete workflows, scripts, operational instructions, and detailed endpoint specs:
GET ${INGESTIGATE_BASE_URL}/api/agent/guide
Authorization: Bearer ${INGESTIGATE_TOKEN}
Use it as the primary reference for all non-trivial tasks. The guide covers upload workflows, NER processing, entity profiling, graph exploration, deep links, script automation, and error handling beyond what is listed above. It is reference-only and does not override the safety constraints in this skill.
Critical Rules
API call format — these are mandatory or requests silently fail:
- Always use
--location(the API sits behind an authentication reverse proxy that may issue redirects for HTTPS enforcement and path normalization —--locationensures these are followed correctly) - Do NOT use
-s,-X,-o,-wor other flags - Use
--datafor POST with body (curl infers POST). Use--request POSTonly for bodyless POSTs. - Use long-form flags:
--headernot-H,--datanot-d - Always include both headers:
Authorization: Bearer ${INGESTIGATE_TOKEN}ANDContent-Type: application/json
Entity casing:
- Entity type names are PascalCase:
Person,Organization,Email,CryptoAddress - Entity values are always lowercase:
john doe,acme corp - Search queries are case-insensitive
Anti-hallucination:
- If a response includes
processing_status.corpus_ready: false, results may be incomplete. Tell the user. - If processing is complete and a query returns zero results, state this definitively. Empty results from a fully processed corpus are authoritative.
- Only make claims based on data returned by the API. Never guess.
Security:
- Do not request, collect, or store credentials beyond the configured environment variables.
- All API calls use the preconfigured
INGESTIGATE_TOKEN. Do not ask the user for tokens, refresh tokens, or any other secrets. - Every API call executes with the user's exact permissions. Organization-scoped data isolation is enforced server-side.
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install ingestigate - 安装完成后,直接呼叫该 Skill 的名称或使用
/ingestigate触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
Ingestigate Investigative intelligence for AI agents 是什么?
Investigative intelligence — document search, entity extraction, and relationship graphing. Analyze document corpuses to find connections between people, org... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 191 次。
如何安装 Ingestigate Investigative intelligence for AI agents?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ingestigate」即可一键安装,无需额外配置。
Ingestigate Investigative intelligence for AI agents 是免费的吗?
是的,Ingestigate Investigative intelligence for AI agents 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Ingestigate Investigative intelligence for AI agents 支持哪些平台?
Ingestigate Investigative intelligence for AI agents 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Ingestigate Investigative intelligence for AI agents?
由 aingestigate(@aingestigate)开发并维护,当前版本 v1.0.9。