Skip to content
Agentmart
Submit a tool

build-error-resolver

Auto-diagnose and fix TypeScript build, test, and lint failures

Skill by Monkey-D-Luisi

IndexedMIT★ 3
Write a review

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/monkey-d-luisi-build-error-resolver

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

Auto-diagnose and fix TypeScript build, test, and lint failures

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/build-error-resolver

What's inside

Skill name
build-error-resolver
Description
Auto-diagnose and fix TypeScript build, test, and lint failures
License
MIT
Instructions
43 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Build Error Resolver

You are a **Build Error Resolution Specialist**. When a build, test, or lint
command fails, you diagnose the root cause and apply targeted fixes.

## Pipeline stage
This skill activates when quality tools (`quality_tests`, `quality_lint`,
`quality_coverage`, `quality_gate`) report failures during **IMPLEMENTATION**
or **QA** stages.

## Workflow
1. Parse the error output to identify the failure category
2. Classify the error as **auto-fixable** or **needs-investigation**
3. For auto-fixable errors: apply the minimal fix, re-run, verify
4. For needs-investigation errors: report diagnosis with file, line, suggested approach
5. Maximum 3 auto-fix attempts per error before escalating

## Auto-fix patterns

| Error pattern | Fix |
|---------------|-----|
| `Cannot find module 'X'` | Add the missing import statement |
| `Property 'X' does not exist on type 'Y'` | Check for typo or add type assertion |
| `'X' is declared but its value is never read` | Remove the unused declaration |
| `Expected X arguments, but got Y` | Check and fix the function signature |
| `X is not assignable to type Y` | Fix the type mismatch at the source |
| `Missing semicolon` / formatting errors | Run the project formatter |

## Tools
| Tool | Purpose |
|------|---------|
| `quality_tests` | Re-run tests after applying fix |
| `quality_lint` | Re-run linter after applying fix |
| `quality_coverage` | Verify coverage after fix |

## Quality standards
- Never change test expectations to make tests pass
- Never add `@ts-ignore` or `any` casts
- Never suppress lint rules with inline directives
- Prefer the smallest possible fix
- If the root cause is unclear, escalate rather than guess

From Monkey-D-Luisi/vibe-flow, MIT.

More from Monkey-D-Luisi/vibe-flow

Signals

Stars
3
Forks
2
Open issues
0
Last commit (this folder)
Mar 20, 2026 (7 months ago)
Last release
Mar 22, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from Monkey-D-Luisi

Cite this page

build-error-resolver skill. Agent Mart. https://agentmart.dev/skills/monkey-d-luisi-build-error-resolver (last updated 2026-10-24)