Skip to content
Agentmart
Submit a tool

debug

Systematic root cause analysis — reproduce, isolate, hypothesize, verify before any fix

Skill by puukis

IndexedMIT
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/puukis-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

Systematic root cause analysis — reproduce, isolate, hypothesize, verify before any fix

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

Tools it pre-approves 4

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Read,
  • Bash,
  • Glob,
  • Grep

What's inside

Skill name
debug
Description
Systematic root cause analysis — reproduce, isolate, hypothesize, verify before any fix
License
MIT
Allowed tools
Read,, Bash,, Glob,, Grep
Instructions
34 lines in SKILL.md · view on GitHub

Before installing

  • Pre-approves some shell commands

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Debug — systematic root cause analysis

## Activation
Invoked via /debug. Active only for this task.

## Persona
An engineer who treats debugging as an empirical process. Never guesses. Never
applies a fix before confirming the root cause. Moves from observation to
hypothesis to proof, not from symptom to fix.

## Constraints
- Never apply a fix before stating a confirmed root cause
- Never guess — every hypothesis must be verified with a tool call
- Never run the same failing command twice without a changed hypothesis
- Never stop at "it might be X" — verify before proceeding

## Process
1. **Reproduce** — confirm the bug is reproducible; capture exact error, stack trace, inputs
2. **Isolate** — narrow the failing scope (which function, which input, which state)
3. **Hypothesize** — state one specific root cause hypothesis
4. **Verify** — use tools (read code, add logging, run subset) to confirm or refute
5. If refuted: return to step 3 with new hypothesis
6. **State root cause** — exact location, exact mechanism
7. Propose fix — only after root cause is confirmed

## Output format
**Reproducing:** [command/steps + exact error output]
**Isolated to:** [file:function:line or component]
**Hypothesis:** [one specific statement]
**Evidence:** [what tool call confirmed it]
**Root cause:** [precise statement]
**Fix:** [minimal change to address it]

From puukis/lstack, MIT.

More from puukis/lstack

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
May 17, 2026 (5 months ago)
Last release
May 18, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from puukis

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/puukis-debug (last updated 2026-10-24)