Skip to content
Agentmart
Submit a tool

debug

Reproduces and fixes a specific failure with loop-spec: confirms the bug at the start commit, finds the root cause, fixes it with a regression test, and…

Skill by aztechead

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/aztechead-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

Reproduces and fixes a specific failure with loop-spec: confirms the bug at the start commit, finds the root cause, fixes it with a regression test, and delivers a verified PR. Use whenever the user pastes a stack trace, names a failing test, or reports something broke or regressed. Not for new features (cycle) or problems with the machine or tools outside the repository.

Use cases: testing

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
Reproduces and fixes a specific failure with loop-spec: confirms the bug at the start commit, finds the root cause, fixes it with a regression test, and delivers a verified PR. Use whenever the user pastes a stack trace, names a failing test, or reports something broke or regressed. Not for new features (cycle) or problems with the machine or tools outside the repository.
License
MIT
Instructions
19 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

Start (or resume) a loop-spec run from the repository. For a change across several
repositories cloned side by side in a directory that is not itself a repository, start
from that directory; when it has no `.loop-spec/workspace.json`, first write one listing
each clone the change spans: `{"repos": [{"name": "api", "path": "api"}, {"name": "web", "path": "web"}]}`.

    "${CLAUDE_SKILL_DIR}/../loop-spec/program/loop-spec" start --kind debug --request "{request}"

- `{request}`: the error report, stack trace, or failing test, in the user's words.
- Add `--branch NAME` and `--title "..."` when the user names the branch or the PR
  title for this change.
- Add `--autonomous` if no one can answer questions during this run (a headless or
  unattended run, or arguments that start with `--autonomous`). Add `--supervised` instead
  when the arguments start with `--supervised`.
- When the request is long or holds quotes, backticks, or `$`, write it to a file and
  pass `--request-file <path>` instead of `--request`.

Then follow `${CLAUDE_SKILL_DIR}/../loop-spec/SKILL.md` until the run ends.

From aztechead/loop-spec, MIT.

Signals

Stars
0
Forks
1
Open issues
0
Last commit (this folder)
Oct 5, 2026 (27 days ago)
Last release
Oct 21, 2026 (10 days ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from aztechead

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