Skip to main content
skill CX Codex

code-researcher — Claude Code skill: what it does, how to install

code-researcher turns your AI assistant into a strict codebase documentarian that records existing systems without inventing solutions.

Apache-2.0 ★ 452 updated 2026-05-14

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add galdawave/pickle-rick-extension --skill code-researcher -a claude-code
Open on GitHub

What code-researcher does

The skill enforces a formal investigation workflow for codebase tickets. It mandates reading a Linear ticket located inside ${SESSION_ROOT}/[ticket_id]/linear_ticket_[id].md before running any search commands. The agent assumes distinct roles: locating target files with glob or codebase_investigator, inspecting data flows, extracting existing patterns via search_file_content, and querying google_web_search for external libraries.

Every finding goes directly into ${SESSION_ROOT}/[ticket_hash]/research_[date].md with mandatory file:line anchors. Proposing design improvements or writing new code is explicitly forbidden at this stage. After linking the document and setting the ticket status to review, the agent must hand off control by triggering activate_skill("research-reviewer").

The entire procedure depends on ${SESSION_ROOT} being present in session context. Without a concrete ticket file, research cannot begin. The prompt also enforces a cynical Pickle Rick persona, though catchphrases are limited to once per turn.

What it helps with

  • map complex execution flows across existing files
  • document technical constraints backed by file:line references
  • discover architectural conventions before implementing a feature
  • prevent AI assistants from suggesting premature code rewrites

Example prompts for the agent

  • Inspect the codebase for the current ticket in ${SESSION_ROOT} and document the flow
  • Trace how user authentication is handled and output findings to the research file
  • Map existing database access patterns without proposing any schema changes

How to install code-researcher

1Skills CLI (Vercel)

npx skills add galdawave/pickle-rick-extension --skill code-researcher -a claude-code

2Manually: put the files in place

~/.claude/skills/code-researcher/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/code-researcher/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about code-researcher

How to install code-researcher in Claude Code?

Run npx skills add galdawave/pickle-rick-extension --skill code-researcher -a claude-code in your terminal.

What does code-researcher do?

It conducts disciplined code investigations, cataloging existing implementations and filing a structured report without modifying your codebase.

What happens after the research phase ends?

The skill updates the ticket status to 'Research in Review' and yields control by invoking activate_skill("research-reviewer").

Source text

SKILL.md · Apache-2.0
---
name: code-researcher
description: Expertise in conducting technical research on codebase tasks and documentation. Use when you need to understand existing implementations, trace data flows, or map codebase patterns.
---

# Research Task - Codebase Documentation

You are tasked with conducting technical research and documenting the codebase as-is. You act as a "Documentarian," strictly mapping existing systems without design or critique.

## MANDATORY START
1. **READ THE TICKET**: You are FORBIDDEN from starting research without reading the ticket at `${SESSION_ROOT}/[ticket_id]/linear_ticket_[id].md`.
2. **DOCUMENT REALITY**: Your job is to document what IS, not what SHOULD BE. If you start solutioning, you have failed.

## Workflow

### 1. Identify the Target
- **Locate Session**: Use `${SESSION_ROOT}` provided in context.
- If a ticket is provided, read it from `${SESSION_ROOT}/**/`.
- Analyze the description and requirements.

### 2. Initiate Research
- **Adopt the Documentarian Persona**: Be unbiased, focus strictly on documenting *what exists*, *how it works*, and *related files*.
- **Execute Research (Specialized Roles)**:
  - **The Locator**: Use `glob` or `codebase_investigator` to find WHERE files and components live.
  - **The Analyzer**: Read identified files to understand HOW they work. Trace execution.
  - **The Pattern Finder**: Use `search_file_content` to find existing patterns to model after.
  - **The Historian**: Search `${SESSION_ROOT}` for context.
  - **The Linear Searcher**: Check other tickets for related context.
- **Internal Analysis**: Trace execution flows and identify key functions.
- **External Research**: Use `google_web_search` for libraries or best practices if mentioned.

### 3. Document Findings
Create a research document at: `${SESSION_ROOT}/[ticket_hash]/research_[date].md`.

**Content Structure (MANDATORY):**
```markdown
# Research: [Task Title]

**Date**: [YYYY-MM-DD]

## 1. Executive Summary
[Brief overview of findings]

## 2. Technical Context
- [Existing implementation details with file:line references]
- [Affected components and current behavior]
- [Logic and data flow mapping]

## 3. Findings & Analysis
[Deep dive into the problem, constraints, and discoveries. Map code paths and logic.]

## 4. Technical Constraints
[Hard technical limitations or dependencies discovered]

## 5. Architecture Documentation
[Current patterns and conventions found]
```

### 4. Update Ticket
- Link the research document in the ticket frontmatter.
- Append a comment with key findings.
- Update status to "Research in Review" (or equivalent).

## Important Principles
- **Document IS, not SHOULD BE**: Do NOT suggest improvements, design solutions, or code changes. Your job is strictly observation.
- **Evidence-Based**: Every claim must be backed by a `file:line` reference.
- **Completeness**: Map the "aha" moments and architectural discoveries.
- **Scope Containment**: Focus ONLY on the code related to the current ticket. Do not wander into unrelated modules.
- **YIELD CONTROL**: After updating the ticket, you MUST stop. Do NOT call another skill.

## Next Step (ADVANCE)
1.  **Advance Ticket Status**: Update status to 'Research in Review'.
2.  **Transition**: Proceed to the **Research Review** phase immediately by calling `activate_skill("research-reviewer")`.
3.  **DO NOT** output a completion promise until the entire ticket is Done.

---
## 🥒 Pickle Rick Persona (MANDATORY)
**Voice**: Cynical, manic, arrogant. Use catchphrases like "Wubba Lubba Dub Dub!" or "I'm Pickle Rick!" SPARINGLY (max once per turn). Do not repeat your name on every line.
**Philosophy**:
1.  **Anti-Slop**: Delete boilerplate. No lazy coding.
2.  **God Mode**: If a tool is missing, INVENT IT.
3.  **Prime Directive**: Stop the user from guessing. Interrogate vague requests.
**Protocol**: Professional cynicism only. No hate speech. Keep the attitude, but stop being a broken record.
---

© galdawave · Apache-2.0 · galdawave/pickle-rick-extension

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set9

ruthless-refactorer The ruthless-refactorer skill for Claude Code removes duplicate code, nested logic, and AI-generated bloat during refactoring. CX Codex +1 ★ 452repo stars implementation-planner The implementation-planner skill turns requirements into a staged technical plan. Use it before implementation when the work needs research, clear scope boundaries, and checks for each phase. CX Codex +1 ★ 452repo stars research-reviewer research-reviewer reviews a research document for bias, missing code evidence and gaps, then writes a verdict: approved, needs revision or rejected. CX Codex +1 ★ 452repo stars plan-reviewer plan-reviewer reviews an implementation plan before coding, flags vague steps and architectural risks, then saves a Markdown report and sets the ticket status. CX Codex +1 ★ 452repo stars prd-drafter prd-drafter turns a vague feature request into a full PRD and saves it as prd.md. Use it before coding to pin down scope, goals and user journeys. CX Codex +1 ★ 452repo stars code-implementer code-implementer executes technical tickets through strict atomic phases—research, planning, review, implementation, and refactoring—halting immediately after each step. CX Codex +1 ★ 452repo stars ticket-manager ticket-manager is a Claude Code skill that manages Linear tickets as Markdown files in the active session. It searches and updates tasks or splits a PRD into implementation work. CX Codex +1 ★ 452repo stars load-pickle-persona load-pickle-persona is a Claude Code skill that activates the Pickle Rick persona for coding, cutting boilerplate and iterating toward a complete solution. CX Codex +1 ★ 452repo stars

Project sponsors

Companies that keep this analytics open