12,927 tagged Testing, measured the same way as everything else here.
Browse within: LLM 203cli 135agents 134agentic-ai 130agent 104ai-coding 95skills 77cursor 59openai 55agent-orchestration 43javascript 42antigravity 38gpt 35hacktoberfest 35
Skill Claude CodeCodex
Guardrail for coding agents. Loads the SDD contract and the prompt pool before code is written, then calls the agentseed MCP server's verifycode and scanhallucination tools; a task may only be marked complete when both pass and the completion report attaches evidence. Use whenever the agent writes, edits, or claims…
Skill Claude CodeCodex
Verify that a portable Agent Plugin loaded correctly in Pi by checking this skill and calling the bundled official MCP everything test server. Use when testing pi-agent-plugins installation, skill discovery, MCP trust, or MCP tool connectivity.
raphaelbarbosaqwerty/maestro-dev-skills
Skill Claude CodeCodex
E2E UI testing with Maestro for iOS, Android, Flutter, React Native, and Web.
Skill Claude CodeCodex
Create system-level or epic-level test plans. Use when the user says "lets design test plan" or "I want to create test strategy".
microsoft/aibast-agents-library
Skill Claude CodeCodex ✓ vendor
Pilot an AIBAST industry-solution workshop end-to-end in a live Copilot Studio environment -- build the agent, run every demo prompt fresh, capture real screenshots, fix annotation boxes, file real product bugs -- then rotate to the next solution. Designed to be re-run nightly against all solutions/ workshops.
Skill Claude Code
Run a candidate against the baseline over an Opik test suite and read the numbers back — which cases broke, which got fixed, the per-metric deltas, worst rows, and whether the two runs are comparable — with the Opik compare-view link. Runs via the SDK; reads results via the MCP when connected. Does not issue a…
Skill Claude Code
Execute sprint tasks with production-quality code and tests.
jleechanorg/agent-orchestrator-ts
Skill Claude CodeCodex
Evidence standards for testing and verification, including evidence classes, mock/real boundaries, and proof bundle requirements.
Skill Claude CodeCodex
Comprehensive .NET skill for WinForms modernization, backend services refactoring, unit & integration test generation, and automated project upgrades.
Skill Claude CodeCodex
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login ...
hellogxp/skill-runtime-intelligence
Skill Claude CodeCodex
Executes the declared deterministic boundary probe and returns its exact JSON result.
Skill Claude Code
Internal test harness for plugin maintainers. End users should not invoke this. Runs synthetic personas through critical journeys against the plugin and produces LLM-judge findings reports. Trigger words "/test-personas", "run the test harness", "test the plugin end-to-end", "run the test personas".
Skill Claude CodeCodex
Drive the PowerAppsControl MCP server to UX-test a Power App end to end: open and verify an app URL, let the user choose a mode (smoke test = in-depth read-only exploration that produces a repeatable natural-language test plan; or run my test plan), then run it in a recorded session and produce a video + HTML report…
Skill Claude Code
Enterprise-grade browser automation using WebDriver protocol. Use when the user needs to automate web browsers, perform web scraping, test web applications, fill forms, take screenshots, monitor performance, or execute multi-step browser workflows. Supports Chrome, Firefox, and Edge with connection pooling and health…
Skill Claude CodeCodex
Evaluate Julia through the warm AgentREPL MCP session rather than julia -e, hot-reload edits with Revise, and filter TestItemRunner suites while iterating. Use for any Julia evaluation, package iteration, or test run, and to decide when a fresh process is needed instead.
mashhoorahdal/shipd-olympus-skill
Skill Claude CodeCodex
Use when creating or reviewing a shipd.ai Olympus quest submission — picking a candidate GitHub repo, designing a challenge task hard enough for the ≤50% pass-rate bar, writing the test patch, solution patch, test.sh, or Dockerfile, or when a platform check fails (naming collisions, Dockerfile warnings, description…
Skill Claude CodeCodex ✓ vendor
Run vLLM Buildkite CI-equivalent tests locally on NVIDIA GPUs using the current shell environment. Use when the user asks to run CI tests locally, reproduce CI failures, run a specific test file or test area, or match Buildkite test behavior.
ZeusYue/acceptance-driven-development-skill
Skill Claude CodeCodex
Use when creating or changing a software project, or when the user explicitly requests ADD, acceptance criteria, or verifiable done conditions.
Skill Claude CodeCodex
Runs end-to-end verification of the project. Executes test suite, type checker, linter, and dev server. Reports pass/fail with specific failure details.
flyingsquirrel0419/squirrel-skill
Skill Claude CodeCodex
Full-cycle software development agent: plans, builds, tests, lints, fixes bugs, and writes production-grade README docs. ALWAYS use this skill when the user wants to: build or scaffold a new project, add features to existing code, fix bugs, improve code quality (lint, format, refactor), write or improve a README, add…
Skill Claude CodeCodex
Write Java microbenchmarks with JMH (Java Microbenchmark Harness) that produce trustworthy numbers — not numbers distorted by JIT dead-code elimination, constant folding, insufficient warmup, or single-fork JIT contamination. Use this skill whenever the user writes @Benchmark, mentions JMH, microbenchmark, throughput…
Skill Claude CodeCodex
A debugging workflow that reproduces a problem with a failing test, collects evidence, finds the underlying cause, applies a fix, and runs regression checks. Regression checks verify that the fix does not break behavior that already worked.
Skill Claude Code
Drive the Vite desktop SPA to verify AppShell / Workbench sidebar changes.
chenxihuang1028-a11y/verification-before-completion
Skill Codex
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: