KS
Killer-Skills

investigate-and-plan — Categories.community

v1.0.0
GitHub

About this Skill

Ideal for Code Review Agents requiring meticulous investigation and planning capabilities. Record and transcribe conversations in Discord

Chronote-gg Chronote-gg
[0]
[0]
Updated: 3/5/2026

Quality Score

Top 5%
18
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add Chronote-gg/Chronote

Agent Capability Analysis

The investigate-and-plan MCP Server by Chronote-gg is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion.

Ideal Agent Persona

Ideal for Code Review Agents requiring meticulous investigation and planning capabilities.

Core Value

Empowers agents to thoroughly research external sources and codebases, producing detailed plans for changesets before implementing code, leveraging GitHub CLI and open clarifying questions.

Capabilities Granted for investigate-and-plan MCP Server

Investigating feature requests
Debugging complex issues
Planning comprehensive changesets

! Prerequisites & Limits

  • Requires GitHub CLI access
  • Dependent on quality of external sources and codebase documentation
Project
SKILL.md
1.6 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Investigate And Plan

Overview

Investigate the request, research external sources and the codebase, and produce a plan for a changeset before writing code. Ask open clarifying questions with defaults, then implement only after the plan is agreed.

Workflow

1) Confirm scope and gather context

  • Identify the exact error, feature idea, or decision to investigate.
  • If a PR or Issue is referenced, use the GitHub CLI to fetch details and comments.
  • List the codebase areas to inspect, including backend, frontend, bot, infra, scripts, tests, docs, and configuration.

2) Research

  • Use web.run for internet research, then cite sources for any external facts.
  • Search the codebase broadly with targeted deep dives into relevant subsystems.
  • Capture findings, constraints, and risks, including any existing TODOs or comments.

3) Propose the changeset

  • Provide a concrete plan with files to touch, key edits, data migrations, and test updates.
  • Call out assumptions and viable alternatives.
  • Ask open questions that block implementation, and provide defaults for each question.
  • Do not write code yet.

4) Implement after agreement

  • Wait for the plan to be accepted or adjusted.
  • Implement the agreed changes, keeping the scope aligned to the plan.
  • If new information changes the plan, pause and confirm the update.

5) Validate

  • Run the repo check command, prefer yarn run check unless a no-auto-fix run is required.
  • Ensure tests, build, lint, end-to-end, and complexity or code stats pass as required by the project.
  • Report command outcomes and any remaining gaps.

Related Skills

Looking for an alternative to investigate-and-plan or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication