Skip to content
Agentmart
Submit a tool

debugging

Use when the user says 'diagnose', 'debug this', reports something broken/throwing/failing/slow, when encountering a bug/test failure/unexpected behavior and…

Skill by Leostruka

IndexedMIT
Write a review

Chalk Labs

Need help deploying debugging?

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/leostruka-debugging

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

Use when the user says 'diagnose', 'debug this', reports something broken/throwing/failing/slow, when encountering a bug/test failure/unexpected behavior and a fix is not yet obvious, or when CI is failing and the cause needs to be found across builds, jobs, or environments.

Use cases: testing, devops

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
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/debugging

What's inside

Skill name
debugging
Description
Use when the user says 'diagnose', 'debug this', reports something broken/throwing/failing/slow, when encountering a bug/test failure/unexpected behavior and a fix is not yet obvious, or when CI is failing and the cause needs to be found across builds, jobs, or environments.
License
MIT
Instructions
49 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (7)

  • SKILL.md
  • ci.md · modes/
  • local.md · modes/
  • condition-based-waiting.md · reference/
  • defense-in-depth.md · reference/
  • root-cause-tracing.md · reference/
  • hitl-loop.template.py · scripts/

SKILL.md (first lines)

# Debugging

**Core principle:** ALWAYS find root cause before attempting fixes. Symptom
fixes are failure. `NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.`

Two modes; full detail in `modes/<mode>.md` — read it when you enter.

| Mode | When | Detail |
|---|---|---|
| **Local** | Bug/test failure/slowness in the codebase, fix not obvious | `modes/local.md` |
| **CI** | Pipeline failing across builds/jobs/environments | `modes/ci.md` |

## Local — the discipline (summary)

1. **Phase 1 — build a feedback loop FIRST.** A tight pass/fail signal that
   goes red on *this* bug is the whole skill; bisection and instrumentation
   just consume it. Spend disproportionate effort here. Without it you cannot
   propose fixes — that is the Iron Law.
2. Then trace data flow, form hypotheses, test one at a time, fix root cause.
3. Redact every secret in shown output (`<REDACTED>`); quote only signal
   lines.

Red flags — return to Phase 1: "quick fix for now", "just try changing X",
"add multiple changes", proposing before tracing, 3+ fix attempts, each fix
revealing a new problem elsewhere.

Reference: `reference/root-cause-tracing.md`,
`reference/condition-based-waiting.md`, `reference/defense-in-depth.md`,
`scripts/hitl-loop.template.py`.

## CI — essentials

- **Access:** `gh run list/view` (GitHub), `glab ci list/view` (GitLab),
  CircleCI MCP, jenkins-cli, or parse the dashboard/logs manually.
- **Flow:** identify project+CI → check pipeline status (skip if green) →
  fetch failure logs (`gh run view <id> --log-failed`) → check for flaky
  tests (intermittent across runs/seeds) → reproduce locally → fix → verify
  by re-running the workflow.
- Distinguish real failures from flaky: same test failing intermittently or
  on retry → flag as flakiness, not the fix target.
- Never push "fixes" to make CI green without a reproduced local failure.

## Cross-skills

- `gates` — verification evidence before declaring fixed.
- `research` deep-mode — when the bug spans modules you can't trace in a pass.
- `computer-use` — when the failure is in a GUI/desktop app and needs screen evidence (screenshot, UIA tree) the shell can't see.

From Leostruka/devin-bundle, MIT.

More from Leostruka/devin-bundle

Signals

Stars
0
Forks
0
Open issues
1
Last commit (this folder)
Oct 10, 2026 (21 days ago)
Last release
Oct 24, 2026 (6 days ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from Leostruka

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 debugging 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 debugging?

CallGet help
Cite this page

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