Investigate

Deep investigation of errors, bugs, or codebase questions without making any code changes. Use when user mentions investigate, understand, explore, analyze, or pastes error tracebacks. Spawns parallel subagents for comprehensive exploration.

5 stars 1 forksFinance & Crypto

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add TalonT-Org/AutoSkillit --skill investigate
Manual install
git clone --depth 1 https://github.com/TalonT-Org/AutoSkillit.git /tmp/AutoSkillit
mkdir -p ~/.claude/skills
cp -r /tmp/AutoSkillit/src/autoskillit/skills_extended/investigate ~/.claude/skills/investigate

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Investigation Skill

Perform deep codebase investigation without making any changes. This skill uses parallel subagents to explore multiple aspects simultaneously.

## When to Use

- User pastes an error traceback and wants root cause analysis
- User wants to understand how a system/module works
- User asks "how did tests miss this" or similar
- User says "investigate", "explore", "understand", or "analyze"
- User explicitly says "do not change any code"

## Deep Analysis Mode

### Activation

Deep analysis mode is activated when ANY of the following conditions are met:

1. The `--depth deep` flag is present in ARGUMENTS
2. The user explicitly says "investigate deeply" or requests "deep analysis"
3. An explicit batch count is requested (e.g., "run 3 batches")
4. The user requests "maximum thoroughness"
5. The recipe passes `--depth deep` via the `skill_command`

### Model

When deep analysis mode is active, all subagents spawned via the Task tool always use `model: "sonnet"`. The main skill session model is controlled by the recipe or user — typically `opus[1m]` for the main session in deep mode.

### When NOT Activated

Deep analysis mode is never enabled by default. When none of the activation conditions above are met, the skill routes to Standard Mode (Steps 1–4).

## GitHub Issue Input

If the ARGUMENTS contain a GitHub issue reference, call `fetch_github_issue` via the MCP
Read the full skill on GitHub

Details

Skill name
investigate
Path
src/autoskillit/skills_extended/investigate/SKILL.md
License
MIT
Repo updated
8 November 2026

FAQ

What does the Investigate skill do?

Deep investigation of errors, bugs, or codebase questions without making any code changes. Use when user mentions investigate, understand, explore, analyze, or pastes error tracebacks. Spawns parallel subagents for comprehensive exploration.

How do I install the Investigate skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add TalonT-Org/AutoSkillit --skill investigate. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Investigate popular?

It lives in TalonT-Org/AutoSkillit, which has 5 GitHub stars and 1 forks.

Related skills

Analyze Prs

5

TalonT-Org/AutoSkillit

Analyze all open PRs targeting a base branch — determine merge order, identify file overlaps, and tag each PR as simple or needs_check for complexity. Use at the start of a PR consolidation workflow.

Git & Code Review

Arch Lens C4 Container

5

TalonT-Org/AutoSkillit

Create C4 Container architecture diagram showing static structure, building blocks, and technology choices. Anatomical lens answering "How is it built?

Software Development

Arch Lens Concurrency

5

TalonT-Org/AutoSkillit

Create Concurrency architecture diagram showing parallel execution patterns, thread pools, synchronization, and barriers. Physiological lens answering "How does parallelism work?

Software Development

Rectify

5

TalonT-Org/AutoSkillit

Deep investigation of test gaps and architectural weaknesses following an investigation, then devise a plan for architectural immunity rather than direct fixes. Use when user says "rectify", "rectify this", or wants to address root architectural causes after an investigation.

Finance & Crypto

Audit Bugs

5

TalonT-Org/AutoSkillit

Analyze historical bug patterns by mining Claude Code project logs for /autoskillit:investigate skill invocations since a specified date. Identifies recurring root causes, architectural gaps, and proactive detection strategies. Use when user says "audit bugs", "bug patterns", "analyze investigations", or "bug audit".

Finance & Crypto

Report Bug

5

TalonT-Org/AutoSkillit

Investigate a bug from provided error context, write a structured markdown report to the given path, and output a deduplication fingerprint. Lightweight — no parallel subagents.

Finance & Crypto

Browse the most popular Claude skills, all finance & crypto skills, or write your own with the skills generator.