investigate

Synthesize end-of-chat context and docs into a reviewer-only investigation plan.

1|Updated Feb 25, 2026

Search Tags:#planning #documentation #investigate #task-generation #reviewer #research-mode #end-of-chat

Ready to run

npx skills add https://github.com/danalexilewis/taskgraph --skill investigate-danalexilewis

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: investigate
Source: https://github.com/danalexilewis/taskgraph/tree/main/.cursor/skills/investigate
Command: npx skills add https://github.com/danalexilewis/taskgraph --skill investigate-danalexilewis

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates quick, high-level investigations by synthesizing end-of-chat context and docs into a concrete investigation plan and tasks, then dispatches only the reviewer sub-agent in research mode to gather evidence without edits.

Core Features & Use Cases

Reads the end-of-chat context (summary, post-action) and relevant docs to identify focus areas and hypotheses.
Drafts a clear investigation plan and a set of reviewer-only tasks, then dispatches the reviewer sub-agent in research mode.
Synthesizes findings into a final plan and actionable tasks for user presentation.

Quick Start

Run /investigate to start a quick end-of-chat review and plan.

Frequently Asked Questions about investigate

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

FAQPage Schema

How do I generate an investigation plan from end-of-chat context and documentation?▼

To generate an investigation plan from end-of-chat context and documentation, run /investigate to synthesize chat summaries and relevant docs into a defined focus, hypotheses, and a set of actionable tasks.

Can I gather evidence for a code review without making edits to the repository?▼

You can gather evidence without making edits by dispatching a reviewer sub-agent in read-only research mode, which scopes work to safely collect information and synthesize findings without modifying files.

What is the best way to automate high-level research and task generation after a chat session?▼

Automating high-level research and task generation after a chat session is best done by identifying end-of-chat context and relevant docs to define an investigation focus, then dispatching a reviewer sub-agent to produce a plan.

Does the investigate skill require any specific dependencies or components to run?▼

The investigate skill requires no external dependencies or components to run, relying entirely on read-only access to chat context, docs, and the correct dispatch channel for the reviewer sub-agent.

When should I use a read-only research mode for software engineering investigations?▼

You should use a read-only research mode for software engineering investigations when you need to safely gather evidence and synthesize findings into an actionable plan without risking unintended edits to your codebase.

How does the reviewer sub-agent synthesize findings into an actionable plan?▼

The reviewer sub-agent synthesizes findings into an actionable plan by operating in research mode to gather evidence via read-only access, then compiling that evidence into a final plan and tasks for user presentation.