Skip to content
Agentmart
Submit a tool

debug

Guide systematic debugging through hypothesis generation, evidence collection, and verification.

Skill by thoreinstein

IndexedMIT★ 3
Write a review

Chalk Labs

Need help deploying debug?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/thoreinstein-debug

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Guide systematic debugging through hypothesis generation, evidence collection, and verification. Uses scientific method for root cause analysis.

Use cases: research

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/debug

What's inside

Skill name
debug
Description
Guide systematic debugging through hypothesis generation, evidence collection, and verification. Uses scientific method for root cause analysis.
License
MIT
Metadata
author: thoreinstein · version: 1.0.0
Instructions
144 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • compatibility: must be text of at most 500 characters
  • allowed-tools: must be a space-separated string

Files (2)

  • SKILL.md
  • debug-session-template.md · references/

SKILL.md (first lines)

# Debug

Systematic debugging through hypothesis generation, evidence collection, and verification.

## When to Use This Skill

- When facing a bug with unclear root cause
- When initial debugging attempts haven't resolved the issue
- When you need structured investigation rather than guesswork
- When documenting a debugging session for future reference

## Input

Provide as much of the following as available:

1. **Problem Statement**
   - What's the expected behavior?
   - What's the actual behavior?
   - Steps to reproduce

2. **Context**
   - Recent changes that might be related
   - Error messages or logs
   - Environment details (OS, versions, etc.)

3. **Initial Hypotheses** (if any)
   - What do you think might be causing it?
   - What have you already ruled out?

## Debugging Framework

### Step 1: Problem Definition

Clearly define:
- Expected vs actual behavior
- Reproduction steps (minimal if possible)
- Scope: when does it happen, when doesn't it?
- Impact: severity and affected users/systems

### Step 2: Hypothesis Generation

Generate ranked hypotheses:
- List possible causes
- Assign probability (likely, possible, unlikely)
- Note evidence for and against each
- Identify what would confirm or rule out each

### Step 3: Investigation Plan

For each hypothesis, plan:
- What evidence to look for
- Where to look (files, logs, git history)
- What tests would confirm/deny
- Order of investigation (highest probability first)

### Step 4: Evidence Collection

Investigate systematically:
- Search codebase for relevant patterns
- Review git history for recent changes
- Examine logs and error messages
- Document findings with timestamps

### Step 5: Root Cause Identification

Synthesize findings:
- Identify the root cause (not just symptoms)
- Note contributing factors
- Document code locations involved
- Explain the causal chain

## Investigation Tracks

Run these investigation tracks in parallel where possible:

| Track        | Focus                                        |
| ------------ | -------------------------------------------- |
| **Codebase** | Explore structure, find related code         |
| **History**  | Recent changes, blame, related commits       |
| **Patterns** | Search for similar code, error handling      |
| **External** | Documentation, known issues, similar reports |

## Output

Produce a debug session report following the template in `references/debug-session-template.md`.

The report should include:
- Problem statement with reproduction steps
- Hypotheses with evidence assessment
- Investigation log with timestamps
- Root cause and contributing factors
- Recommended fix and prevention measures

## Constraints

- **Hypotheses first** - generate hypotheses before diving into code
- **Evidence-based** - support conclusions with specific evidence
- **Document as you go** - keep an investigation log
- **Root cause, not symptoms** - dig until you find the actual cause
- **Prevention** - recommend how to prevent recurrence

## Example

### Example: Intermittent API Timeout

**Problem:** `/api/users` endpoint times out ~10% of requests

**Hypotheses:**
```
H1: Database query is slow (70% likely)
    Evidence for: Timeout correlates with high DB load
    Evidence against: None yet
    Test: Check query execution time

H2: Connection pool exhaustion (20% likely)
    Evidence for: Happens under load
    Evidence against: Pool metrics look normal
    Test: Monitor pool during timeout

From thoreinstein/agents, MIT.

More from thoreinstein/agents

Signals

Stars
3
Forks
0
Open issues
0
Last commit (this folder)
Jan 20, 2026 (9 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
1.0.0
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from thoreinstein

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get debug running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying debug?

CallGet help
Cite this page

debug skill. Agent Mart. https://agentmart.dev/skills/thoreinstein-debug (last updated 2026-10-24)