AGENT SKILL

test-fixing

Systematically identify and fix all failing tests using smart grouping strategies. Use when explicitly asks to fix tests ("fix these tests", "make tests pass"), reports test failures ("tests are failing", "test suite is broken"), or completes implementation and wants tests passing.

License 许可
MIT
最近更新
2026-11-10
Stars
★ 1
Forks
0

01 前言 Front Matter

name
test-fixing
risk
safe
source
community
date_added
2026-02-27
description
Systematically identify and fix all failing tests using smart grouping strategies. Use when explicitly asks to fix tests ("fix these tests", "make tests pass"), reports test failures ("tests are failing", "test suite is broken"), or completes implementation and wants tests passing.

03 SKILL.md 正文

Test Fixing

Systematically identify and fix all failing tests using smart grouping strategies.

When to Use

  • Explicitly asks to fix tests ("fix these tests", "make tests pass")
  • Reports test failures ("tests are failing", "test suite is broken")
  • Completes implementation and wants tests passing
  • Mentions CI/CD failures due to tests

Systematic Approach

1. Initial Test Run

Run make test to identify all failing tests.

Analyze output for:

  • Total number of failures
  • Error types and patterns
  • Affected modules/files

2. Smart Error Grouping

Group similar failures by:

  • Error type: ImportError, AttributeError, AssertionError, etc.
  • Module/file: Same file causing multiple test failure
  • Root cause: Missing dependencies, API changes, refactoring impacts

Prioritize groups by:

  • Number of affected tests (highest impact first)
  • Dependency order (fix infrastructure before functionality)

3. Systematic Fixing Process

For each group (starting with highest impact):

  1. Identify root cause

    • Read relevant code
    • Check recent changes with git diff
    • Understand the error pattern
  2. Implement fix

    • Use Edit tool for code changes
    • Follow project conventions (see CLAUDE.md)
    • Make minimal, focused changes
  3. Verify fix

    • Run subset of tests for this group
    • Use pytest markers or file patterns:
      uv run pytest tests/path/to/test_file.py -v
      uv run pytest -k "pattern" -v
      
    • Ensure group passes before moving on
  4. Move to next group

4. Fix Order Strategy

Infrastructure first:

  • Import errors
  • Missing dependencies
  • Configuration issues

Then API changes:

  • Function signature changes
  • Module reorganization
  • Renamed variables/functions

Finally, logic issues:

  • Assertion failures
  • Business logic bugs
  • Edge case handling

5. Final Verification

After all groups fixed:

  • Run complete test suite: make test
  • Verify no regressions
  • Check test coverage remains intact

Best Practices

  • Fix one group at a time
  • Run focused tests after each fix
  • Use git diff to understand recent changes
  • Look for patterns in failures
  • Don't move to next group until current passes
  • Keep changes minimal and focused

Example Workflow

User: "The tests are failing after my refactor"

  1. Run make test → 15 failures identified
  2. Group errors:
    • 8 ImportErrors (module renamed)
    • 5 AttributeErrors (function signature changed)
    • 2 AssertionErrors (logic bugs)
  3. Fix ImportErrors first → Run subset → Verify
  4. Fix AttributeErrors → Run subset → Verify
  5. Fix AssertionErrors → Run subset → Verify
  6. Run full suite → All pass ✓

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

04 同仓库更多 Skills

YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

vercel-sandbox

Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

slack

Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

electron

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

dogfood

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.

★ 1