ipps-deep-research

Capture multi-source evidence with provenance across six structured research phases.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/karstenheld3/SharePoint-GPT-Middleware --skill ipps-deep-research
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ipps-deep-research
Source: https://github.com/karstenheld3/SharePoint-GPT-Middleware/tree/main/.windsurf/skills/ipps-deep-research
Command: npx skills add https://github.com/karstenheld3/SharePoint-GPT-Middleware --skill ipps-deep-research

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a rigorous, repeatable framework for in-depth technology research, ensuring multi-source evidence is captured with provenance and auditable reasoning.

Core Features & Use Cases

  • Structured workflows: MEPI/MCPI-guided phases (preflight, TOC creation, template, tasks planning, file-by-file research, final verification) to organize complex investigations.
  • Source hierarchy & verification: Enforces official-first sources, structured citations with IDs, and explicit verification labels to distinguish fact, assumption, and community input.
  • Planning & tracking: Automatically creates STRUT for orchestration and TASKS for granular execution, including time tracking and credit estimation to improve discipline and collaboration.
  • Reproducible outputs: Generates standardized INFO-like documents, TOCs, and templates that can be reused for audits, compliance, or knowledge transfer.
  • Use Case: You need exhaustive documentation for a new API, its variants, and integration patterns; you’d run MCPI-driven research and generate an end-to-end report with sources and a verified summary.

Quick Start

Start a deep research session by initializing STRUT for a topic, then create a TASKS plan and begin Phase 1 with source collection.

Frequently Asked Questions about ipps-deep-research

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I organize exhaustive research across multiple sources with verified provenance?

Deep research with verified provenance uses a six-phase structured workflow: preflight planning, table-of-contents creation, template setup, task planning with TASKS tracking, file-by-file investigation, and final verification. This ensures multi-source evidence is captured with explicit source hierarchy, verification labels, and auditable reasoning preserved throughout.

What's the best way to ensure my research results are repeatable and auditable?

Enforcing strict source hierarchy, structured citations with IDs, and explicit verification labels distinguishes fact from assumption and community input. Standardized outputs like INFO-like documents and reusable templates create repeatable research that supports audits, compliance reviews, and knowledge transfer across teams.

How do I plan and track complex research investigations systematically?

Create a STRUT for orchestration and TASKS for granular execution to plan research phases. Time tracking and credit estimation built into task planning improve discipline and collaboration, while phase-by-phase tracking ensures nothing is missed in exhaustive investigations.

Can I use this approach for API documentation and integration research?

Yes. The MCPI-driven research workflow generates end-to-end documentation for APIs, variants, and integration patterns. It produces standardized reports with sources, verified summaries, and reusable templates suitable for technical documentation and knowledge bases.

What verification labels does this framework use to distinguish research quality?

The framework applies explicit verification labels to distinguish fact (official sources), assumption (inferred or unconfirmed), and community input (third-party contributions). Source hierarchy enforces official-first precedence, ensuring transparent research lineage and auditable confidence levels.

Do I need prior research experience to start deep research with structured phases?

No. The framework provides a quick start by initializing STRUT for a topic, then creating a TASKS plan before Phase 1 source collection. Step-by-step phases and automatic template generation guide investigation regardless of prior research depth or methodology experience.