skill

test-fixing — Claude Code skill: what it does, how to install

Q: How to install test-fixing in Claude Code?

Run `npx claude-code-templates@latest --skill development/test-fixing` in your terminal.

Q: Which command-line tools does the skill expect?

It relies on `git diff` to inspect modifications, `make test` for full suite runs, and `uv run pytest` with file or pattern flags for focused checks.

Structures how Claude Code diagnoses and repairs failing test suites by grouping errors from import issues to logic bugs.

Install into Claude Code · claude-code-templates All methods and platforms ↓

npx claude-code-templates@latest --skill development/test-fixing

Open on GitHub

What test-fixing does

This skill establishes an ordered debugging routine for broken test suites. Instead of editing arbitrary files, Claude Code starts with make test to capture failures and groups them by root cause: missing modules, changed call signatures, or failed assertions.

Repairs proceed in batches by dependency order. The agent resolves import errors and configuration problems first, applies API signature updates second, and addresses logic assertions last. It inspects recent edits using git diff, checks conventions in CLAUDE.md, and runs targeted checks with uv run pytest before moving to the next batch.

Without make test or pytest configured in the workspace, you will need to adjust the test commands manually. A final full run verifies that the targeted fixes introduced no regressions.

What it helps with

group broken test runs by failure category after refactoring
resolve import mismatches and dependency issues first
verify isolated test batches with targeted pytest commands
fix altered function signatures across test modules

Example prompts for the agent

Fix the failing test suite and make sure make test passes.
The tests broke after my recent refactor, group the errors and resolve them.
Run the test suite and fix import failures before checking logic assertions.

How to install test-fixing

1claude-code-templates

npx claude-code-templates@latest --skill development/test-fixing

2Skills CLI (Vercel)

npx skills add davila7/claude-code-templates --skill test-fixing -a claude-code

3Manually: put the files in place

~/.claude/skills/test-fixing/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/test-fixing/

Manually: put the files in place

.agents/skills/test-fixing/SKILL.md

For all projects use ~/.agents/skills/

Manually: put the files in place

.cursor/skills/test-fixing/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install davila7/claude-code-templates test-fixing

2Manually: put the files in place

.github/skills/test-fixing/SKILL.md

Platform CLI

gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/development/test-fixing

Manually: put the files in place

.devin/skills/test-fixing/SKILL.md

The legacy .windsurf/skills/ path still works

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about test-fixing

How to install test-fixing in Claude Code?

Run npx claude-code-templates@latest --skill development/test-fixing in your terminal.

What order does test-fixing follow when resolving errors?

It resolves infrastructure and import failures first, updates altered function signatures second, and tackles assertion logic issues last.

Which command-line tools does the skill expect?

It relies on git diff to inspect modifications, make test for full suite runs, and uv run pytest with file or pattern flags for focused checks.

Similar skills

All skills for Testing and QA →

improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. 1,163,035installs design-taste-frontend Leonxlnx This skill directs the design of public pages and work screens, then checks the result in a browser through screenshots. Use it when an interface feels generic or unfinished. CX Codex +1 678,700installs tdd Matt Pocock Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. 1,141,062installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. 414,180installs agent-browser vercel-labs A CLI skill for browser control: it opens pages, fills forms, clicks buttons, and tests web apps. Use it when an agent needs to act inside a website. CX Codex +1 1,200,000installs prototype Matt Pocock Creates throwaway prototypes for checking state logic or exploring UI before committing the decision to the main codebase. 986,201installs

From the same set804

The whole set →

geopandas This skill gives Claude Code a workflow for reading, transforming, and analyzing vector geodata. Use it for spatial operations, coordinate systems, area calculations, and maps. 87installs shodan-reconnaissance Guides Claude Code through network reconnaissance using Shodan CLI and API. Helpful for discovering exposed internet hosts, open ports, and known service vulnerabilities. 86installs creative-portfolio-resume Build a resume for a creative role with both visual character and ATS-friendly structure. The skill helps when you need separate versions for online applications and portfolio use. 86installs azure-role-selector Finds an Azure role that matches an identity’s required permissions with minimal access, then provides ways to assign it. Useful when setting up access controls. 86installs gws-drive Use this command to manage Google Drive files and shared drives through Claude Code. It helps when you want an agent to run Drive operations through the gws CLI. 84installs drizzle-orm-expert Guides schema authoring, relational queries, and migrations in Drizzle ORM. Helpful when structuring type-safe database layers in TypeScript. 83installs ship-learn-next Takes a transcript, article or tutorial and turns it into concrete steps through the Ship-Learn-Next loop: ship something, reflect, plan the next rep. 82installs git-context-controller Maintains agent memory inside a versioned .GCC/ folder. It records task milestones, isolates experimental branches, and restores historical context across development sessions. 82installs