NeVibeCode · 569 items
Testing and QA: skills, plugins, subagents, slash commands and mcp servers
Testing and QA for Claude Code, Codex and Cursor: skills, plugins, subagents, slash commands and mcp servers, from popular to niche.
mem0-test-integration skill Checks the Mem0 integration that /mem0-integrate left behind: installs dependencies, runs the test suite and a live smoke flow, then prints a scorecard.
Claude Code CX Codex Cursor +1
323installs
audit-prep-assistant skill Prepares codebases for external security reviews using Trail of Bits' checklist. It helps run static analysis, boost test coverage, and generate system documentation.
Claude Code CX Codex Cursor +1
5,700installs
semgrep-rule-creator skill A skill that walks you through creating custom Semgrep rules to detect security vulnerabilities and code patterns in your projects. Use it when you need static analysis tailored to your codebase.
Claude Code CX Codex Cursor +1
5,700installs
superpowers-lab skill Sets an evaluation workflow to test experimental upstream skills against a baseline in an isolated environment before adopting them.
Claude Code CX Codex Cursor +1
1,400installs
test-driven-development skill Guides coding agents through a strict test-driven development workflow: red, green, and refactor. Useful when fixing bugs or implementing new features with regression checks.
Claude Code CX Codex Cursor +1
1,400installs
fix-merge-conflicts skill Resolves merge conflicts in a branch, then checks the build and tests before wrapping up. Use it when several conflicted files need focused fixes without a refactor.
Claude Code CX Codex Cursor +1
2,700installs
visual-verdict skill A visual QA skill that compares generated UI screenshots against reference images and returns a structured JSON verdict for layout iterations.
Claude Code CX Codex Cursor +1
890installs
backend-developer subagent Subagent for building backend APIs and microservices in Node.js, Python, and Go. Helps implement relational schemas, caching, and OWASP security rules.
Claude Code
2,724installs
ai-debt-detector skill This skill audits AI-generated code for missed failure paths, orphaned resources, fake dependencies, and architecture drift before a merge.
Claude Code CX Codex Cursor
2,900installs
cargo-fuzz skill Sets up cargo-fuzz inside a Cargo-based Rust crate and walks through the harness, sanitizers and crash triage.
Claude Code CX Codex Cursor +1
5,400installs
coverage-analysis skill Measures code reached by a fuzzing campaign and helps explain stalled path discovery. Use it to inspect harness changes, corpus results, and unreachable branches.
Claude Code CX Codex Cursor +1
5,400installs
arize-experiment
official skill Runs Arize experiments with the ax CLI to benchmark models and export evaluation scores across dataset versions.
GitHub Copilot
1,100installs
arize-evaluator
official skill Runs LLM-as-judge workflows in Arize for spans and experiments, with evaluator management, task control, column mapping, and continuous monitoring.
GitHub Copilot
1,100installs
arize-dataset
official skill This skill manages Arize datasets and examples through ax. Use it for test sets, evaluation examples, and dataset exports.
GitHub Copilot
1,100installs
fuzzing-dictionary skill Generates and connects token dictionaries for parsers and protocols in libFuzzer or AFL++ when coverage stalls on initial checks.
Claude Code CX Codex Cursor +1
5,300installs
semgrep-rule-variant-creator skill Ports completed Semgrep rules to selected languages and creates separate rule and test directories. Use it when you already have a rule to adapt.
Claude Code CX Codex Cursor +1
5,300installs
fuzzing-obstacles skill Patches anti-fuzzing patterns like checksums and time-seeded PRNGs in C, C++, and Rust. Useful when fuzzers get stuck on early validation checks.
Claude Code CX Codex Cursor +1
5,300installs
lint-and-validate skill Runs configured linters and type checkers after code changes, telling actual failures apart from tools that never ran.
Claude Code CX Codex Cursor +1
1,300installs
atheris skill Guides setup of coverage-guided fuzzing for Python code and C extensions with Atheris. Use it to investigate crashes and memory corruption.
Claude Code CX Codex Cursor +1
5,200installs
ossfuzz skill Guides your AI agent through enrolling projects in Google OSS-Fuzz and running fuzzer targets locally with helper scripts.
Claude Code CX Codex Cursor +1
5,200installs
libfuzzer skill A skill that walks the agent through libFuzzer: the harness, the -fsanitize=fuzzer build, corpus handling, campaign triage. For C/C++ built with Clang.
Claude Code CX Codex Cursor +1
5,200installs
burpsuite-project-parser skill Explores and queries Burp Suite project files from the command line. It extracts proxy history, scanner findings, and HTTP traffic without opening the desktop app.
Claude Code CX Codex Cursor +1
5,100installs
wycheproof skill Validates cryptographic implementations using Project Wycheproof test vectors. It helps your agent spot known vulnerabilities and edge cases across AES, RSA, and ECDSA.
Claude Code CX Codex Cursor +1
5,100installs
dart-add-unit-test skill Writes Dart and Flutter unit tests with package:test: files under test/, mockito mocks when dependencies get in the way, and a rerun loop until the suite is green.
Claude Code CX Codex Cursor +1
19,100installs
review-and-ship skill This skill automates code review before shipping: checks for bugs, tests, and intent fit, then commits and opens a PR. Use it to verify your work is ready before merge.
Claude Code CX Codex Cursor +1
2,500installs
prek skill Guides agents in configuring and running Git hooks with prek, a Rust alternative to pre-commit. Useful when you need speed, workspace support, or native TOML configuration.
Claude Code CX Codex Cursor +1
728installs
testing-setup skill Analyzes your Android app's testing strategy and installs libraries, infrastructure, and frameworks for unit tests, UI tests, screenshot tests, and end-to-end tests.
Claude Code CX Codex Cursor +1
2,500installs
write-e2e-tests skill Guides Playwright E2E testing for tldraw, including UI actions, menus, and canvas shapes. Use it when adding coverage for SDK examples or the tldraw.com client.
Claude Code CX Codex Cursor +1
430installs
phoenix-evals
official skill Build and run evaluators for AI and LLM applications with Phoenix. Use it to investigate failures, evaluate RAG systems, and check model output.
GitHub Copilot
1,000installs
phoenix-cli
official skill A GitHub Copilot skill that drives the Phoenix CLI to pull traces, spans and sessions, then turns what it finds into a failure taxonomy for your LLM app.
GitHub Copilot
1,000installs
dart-generate-test-mocks skill A Dart testing skill: the agent injects external services through constructors, generates mock classes with mockito and build_runner, then writes the unit test.
Claude Code CX Codex Cursor +1
18,200installs
quantized-export skill Exports promoted checkpoints and LoRA adapters as FP8, AWQ, GGUF, or merged safetensors. Use it before deploying a model.
Claude Code CX Codex Cursor
2,600installs
eval-harness-first skill Builds the evaluation harness before fine-tuning with goldens, graders, judge calibration, and a base-model baseline. Useful for tracking regressions.
Claude Code CX Codex Cursor
2,600installs
checkpoint-promotion skill Gates a trained checkpoint before release by checking data quality, capability drift, forgetting, and paired results against the base model.
Claude Code CX Codex Cursor
2,600installs
control-ui skill Inspects and tests local web, IDE, or Electron interfaces via browser automation and CDP. Captures screenshots, traces, and verifies UI changes without extra dependencies.
Claude Code CX Codex Cursor +1
2,400installs
fix-ci skill This skill finds failed PR checks, examines logs, and guides small fixes. Use it when branch or pull request CI is failing.
Claude Code CX Codex Cursor +1
2,400installs
control-cli skill Builds a local harness to drive, test, and profile interactive CLI or TUI tools. Catches UI regressions, memory leaks, and hangs without third-party services.
Claude Code CX Codex Cursor +1
2,400installs
dart-migrate-to-checks-package skill Migrates Dart test suites from legacy package:matcher to package:checks. Useful when modernizing test assertions for static type safety and detailed diagnostics.
Claude Code CX Codex Cursor +1
18,000installs
validate-skills skill Checks skills in skills/ against the agentskills.io specification and Claude Code practices. Use it when authoring or reviewing a skill collection.
Claude Code CX Codex Cursor +1
7,200installs
penetration-tester subagent Runs authorized security tests, validates vulnerabilities and reports remediation steps. Use it to assess systems within an agreed scope.
Claude Code
2,407installs
361–400 of 569