Skip to content
Agentmart
Submit a tool

fix-issue

Use when a GitHub issue should be handled end-to-end, including issue analysis, code changes, tests, verification, and an optional commit.

Skill by nexttylabs

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying fix-issue?

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/nexttylabs-fix-issue

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 a GitHub issue should be handled end-to-end, including issue analysis, code changes, tests, verification, and an optional commit.

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 and code. Checked Nov 1, 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/fix-issue

What's inside

Skill name
fix-issue
Description
Use when a GitHub issue should be handled end-to-end, including issue analysis, code changes, tests, verification, and an optional commit.
License
MIT
Instructions
85 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Fix Issue

Use this skill when the user wants an issue handled from start to finish.

## Preconditions

- `gh auth status` succeeds
- The current repository matches the issue's repository
- `AGENTS.md` exists or the project has another clear source of build and verification rules

## Phase 1: Resolve the Issue

1. Parse the user input to extract the issue number or URL.
2. Fetch the issue details:
   ```bash
   gh issue view <number> --json number,title,body,labels,comments,assignees,milestone
   ```
3. Summarize:
   - What is broken or requested
   - Where it likely lives
   - Acceptance criteria
   - Constraints or related issues

## Phase 2: Create a Branch

1. Ensure the working tree is clean with `git status --porcelain`.
2. Update the default branch.
3. Create a fix branch:
   ```bash
   git checkout -b fix/<number>-<slug>
   ```

## Phase 3: Load Project Context

1. Read `AGENTS.md` first.
2. Re-read the issue with the project rules in mind.
3. Identify likely files, tests, and risks.

## Phase 4: Research

1. Search for issue keywords, module names, and error strings.
2. Read all relevant files, not just the first match.
3. Trace the affected path from entry to failure or desired behavior.
4. Find tests that already touch the same area.

## Phase 5: Plan

Present a short structured plan and wait for approval before editing code.

Include:
- Files to change
- Tests to add or update
- Risks or trade-offs
- Scope estimate

Follow `skills/plan-mode/SKILL.md` when writing the plan.

## Phase 6: Implement

1. Make the approved changes.
2. Add or update tests.
3. Re-read every changed file for correctness, naming, and error handling.

## Phase 7: Quality Gate

Run the quality gate defined in `AGENTS.md`. Stop on the first failure, fix it, and re-run.

If `AGENTS.md` does not define the needed checks, ask the user how to verify the change.

## Phase 8: Commit

1. Stage changes with `git add -A`.
2. Commit with an issue-referencing message.
3. Do not push unless the user asks.

## Output Format

Return these sections in order:

1. Issue summary
2. Proposed plan
3. Verification result
4. Final outcome

From nexttylabs/kubebar, MIT.

More from nexttylabs/kubebar

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Apr 18, 2026 (6 months ago)
Last release
Oct 4, 2026 (28 days ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from nexttylabs

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 fix-issue 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 fix-issue?

CallGet help
Cite this page

fix-issue skill. Agent Mart. https://agentmart.dev/skills/nexttylabs-fix-issue (last updated 2026-10-24)