← Back to Skills Marketplace
aingestigate

Ingestigate Investigative intelligence for AI agents

by aingestigate · GitHub ↗ · v1.0.9 · MIT-0
cross-platform ✓ Security Clean
191
Downloads
0
Stars
0
Active Installs
10
Versions
Install in OpenClaw
/install ingestigate
Description
Investigative intelligence — document search, entity extraction, and relationship graphing. Analyze document corpuses to find connections between people, org...
README (SKILL.md)

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 — --location ensures these are followed correctly)
  • Do NOT use -s, -X, -o, -w or other flags
  • Use --data for POST with body (curl infers POST). Use --request POST only for bodyless POSTs.
  • Use long-form flags: --header not -H, --data not -d
  • Always include both headers: Authorization: Bearer ${INGESTIGATE_TOKEN} AND Content-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.
Usage Guidance
This skill appears internally consistent and limited to calling the Ingestigate API. Before installing, verify you trust ingestigate.com/app1.ingestigate.com, confirm the token you configure is scoped/short-lived as described, and store INGESTIGATE_TOKEN and INGESTIGATE_BASE_URL only in your platform's secure skill settings (do not paste tokens into chat). If you will upload sensitive documents, confirm the provider's privacy, retention, and access controls (and consider an air-gapped deployment if required).
Capability Analysis
Type: OpenClaw Skill Name: ingestigate Version: 1.0.9 The ingestigate skill is a legitimate integration for an investigative intelligence platform, providing tools for document analysis, entity extraction, and relationship graphing. It follows security best practices by using short-lived environment-based tokens and explicitly instructs the agent not to solicit credentials from users. The API interactions described in SKILL.md and README.md are well-documented and focused entirely on the stated investigative purpose, with no evidence of data exfiltration or malicious execution.
Capability Assessment
Purpose & Capability
Name/description map to the declared behavior: accessing an external investigative API, searching corpora, extracting entities, and tracing relationships. The only required secrets are an access token and API base URL, which are appropriate for a remote API integration.
Instruction Scope
SKILL.md contains explicit API endpoints and rules for calling them; it does not instruct the agent to read local files, pull other environment variables, or exfiltrate data to unrelated endpoints. It requires the configured token and base URL and tells the agent to use the API for all evidence and workflows.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so nothing is written to disk and there is no installer risk.
Credentials
Only two env vars are required (INGESTIGATE_TOKEN and INGESTIGATE_BASE_URL). Both are justified by the skill's need to call a remote API; no unrelated credentials or high-privilege config paths are requested.
Persistence & Privilege
The skill does not request always:true or other elevated persistence. It relies on short-lived tokens (30-minute expiry), and instructs users to configure credentials in the host platform's secure settings—standard and proportionate.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install ingestigate
  3. After installation, invoke the skill by name or use /ingestigate
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.9
- Added a homepage field to the skill configuration, linking to https://ingestigate.com. - No other changes to skill logic, endpoints, or functionality.
v1.0.8
- Added new instructions to fetch the full agent guide at the start of any investigation for complete workflows and endpoint specs. - Clarified that the agent guide provides operational, automation, and error-handling reference, but does not override skill safety constraints. - No code or interface changes; documentation only.
v1.0.7
No visible changes were detected in this version. - No updates were made to the skill files or documentation. - Functionality and usage instructions remain unchanged from the previous version.
v1.0.6
Version 1.0.6 of ingestigate has no detected code or documentation changes. - No changes were made in this release.
v1.0.5
- No code or documentation changes in this release; files remain unchanged. - Version incremented to 1.0.5 for tracking purposes.
v1.0.4
No changes detected in this release. - Version 1.0.4 contains no modifications to files or documentation. - All functionality and instructions remain unchanged from the previous version.
v1.0.3
**Credential input and storage process streamlined — now requires secure platform configuration only.** - Credentials (`INGESTIGATE_TOKEN`, `INGESTIGATE_BASE_URL`) must now be configured in the platform's secure settings; do not request or accept secrets in chat. - Updated user instructions to reference platform settings, with specific error and expiry messages. - Removed legacy onboarding, credential parsing, and refresh token instructions. - Security and privacy requirements clarified: no handling, storing, or requesting of user credentials in conversation. - Core API usage and investigation workflow remain unchanged.
v1.0.2
Minor update to credential instructions for clarity and reassurance. - Added messaging to clarify the short-lived nature of credentials when users paste them in chat. - Reassured users that expired credentials are useless to others, even if they appear in chat history. - No changes to core functionality or workflow.
v1.0.1
**Improved environment variable support and refined credential handling.** - Introduced required environment variables: `INGESTIGATE_TOKEN` and `INGESTIGATE_BASE_URL`, with clear descriptions and usage instructions. - Clarified credential management: credentials are now stored in environment variables for the session only; no persistence beyond the session. - Updated security information to highlight short-lived tokens, refresh lifecycle, and reduced blast radius by using session-based storage. - Aligned all authentication instructions and API examples to use the new environment variable names. - No functional API or workflow changes; documentation and usage guidance only.
v1.0.0
- Initial release of the Ingestigate investigative intelligence skill. - Search, extract entities, trace relationships, and retrieve evidence across 1,000+ document formats. - Self-teaching: agent fetches the full developer guide from the API and operates autonomously. - Processing-aware responses prevent hallucination about incomplete data. - Validated end-to-end: agent mapped a financial crimes network across 144 documents with zero prior knowledge.
Metadata
Slug ingestigate
Version 1.0.9
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 10
Frequently Asked Questions

What is Ingestigate Investigative intelligence for AI agents?

Investigative intelligence — document search, entity extraction, and relationship graphing. Analyze document corpuses to find connections between people, org... It is an AI Agent Skill for Claude Code / OpenClaw, with 191 downloads so far.

How do I install Ingestigate Investigative intelligence for AI agents?

Run "/install ingestigate" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Ingestigate Investigative intelligence for AI agents free?

Yes, Ingestigate Investigative intelligence for AI agents is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Ingestigate Investigative intelligence for AI agents support?

Ingestigate Investigative intelligence for AI agents is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Ingestigate Investigative intelligence for AI agents?

It is built and maintained by aingestigate (@aingestigate); the current version is v1.0.9.

💬 Comments