20,069 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Skill Claude CodeCodex
Debug a failed dynobox run from its terminal output. Use this skill when the user pastes or references output from npx dynobox run (especially --debug output with failed assertions), asks why a dyno run, scenario, or assertion failed, or wants a failing dyno fixed. Produces a root-cause diagnosis and proposed fixes…
Skill Claude CodeCodex
Operational rules for a 60-minute single-shot exploratory verification of a Kotlin project's main branch (Android / JVM / KMP / Compose / server-side Kotlin). Runs sequentially through cat1–cat5 inside a single CI job (e.g. a nightly GitHub Actions workflow), writes findings Markdown-by-Markdown to…
Skill Claude Code
End-to-end test for a converted Unity project. Delegates the full conversion (including agent-driven Steps 4a and 4c) to /convert-unity, then launches Studio with the produced rbxlx, drives the gameplay-feature fixtures via Studio MCP, and writes a combined pass/fail report. Upload step (6) is skipped — cached asset…
Skill Claude CodeCodex
Browser automation CLI for AI agents. Use when you need to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, or testing web apps.
Skill Claude CodeCodex
Repo-local guide for testing the Every Code TUI interactively, including live-terminal visibility limits, VT100 snapshot evidence, restart dogfooding, and how to avoid overclaiming visual verification.
Skill Claude CodeCodex
Staged orchestration for genuinely multi-stage builds — stage map, warm implementer / fresh adversarial verifier, witnessed-red TDD, re-verify on every change. Builds on the always-on operating discipline in /.claude/CLAUDE.md (verify by re-execution, [confirmed]/[inferred] labeling, cost/blast gating), which applies…
Cursor rule Cursor
A pre-commit and pre-pull-request review for OneKey QA changes. It scans staged, unstaged, and untracked files for security leaks, test-case and rule quality, and script problems, then writes a detailed report.
Skill Claude CodeCodex
An end-to-end workflow that turns a product requirements document, or MRD, into planned and tested code. It can clarify requirements, create a more detailed plan, design the technical approach, generate code and tests, and archive the work.
Plugin Claude Code
Bundles 1 command, 4 agents · 410 tokens together
Revisão pré-build em paralelo (QA · Sênior · Gerente UX) com baseline/delta por branch, checklists determinísticos, retrospectiva automática e veredito orientado ao que mudou. Customização por projeto via overlay em docs/triple-review-tuning/customizacao.md.
Skill Claude CodeCodex
Use when starting VAT work or deciding which VAT sub-skill applies. Router that points at sub-skills for adoption, skill/agent authoring, audit, distribution, RAG, knowledge resources, skill review, and enterprise org admin.
Plugin Claude Code
Bundles 2 skills, 1 hook · 390 tokens together
Agentiqa for your coding agent: test what it builds before you ship. Free with Community Edition.
Skill Claude CodeCodex
A skill for creating test data, meaning sample inputs used to check whether software works correctly.
Skill Claude CodeCodex
Show and maintain a discrete-node progress panel while ChatGPT uses its built-in browser for an authorized website acceptance test. Use when the user starts an @Browser acceptance task, asks to test a website with the in-app browser, or asks to show browser test progress. Do not use for ordinary browsing, research, or…
Skill Claude Code
A Traditional Chinese teaching guide for a software lab on golden datasets and prompt regression. A golden dataset is a set of expected examples used to check whether changes still produce acceptable results.
orbitlinktracer/linkskill-bench
Skill Claude CodeCodex
Benchmark and evaluate the quality of any AgentSkill. Use when asked to test, evaluate, benchmark, or assess a skill's effectiveness. Triggers on phrases like 'benchmark this skill', 'evaluate skill quality', 'test this skill', 'how good is this skill', 'skill audit', 'skill assessment'. Works by generating test…
Skill Claude CodeCodex
Provision temporary Hetzner Cloud VMs for Ansible role QA, bootstrap OS prerequisites such as Rocky 8 Python 3.9, run verified work, clean up cloud resources, and report sanitized evidence.
Skill Claude CodeCodex
Full project test coverage. Analyzes the entire codebase, identifies coverage gaps, and writes tests to achieve 100% coverage (minimum 80%). Ensures every source file with exportable logic has at least one test. Use when the user mentions 'alltest', wants comprehensive testing, or asks for full test coverage.
Skill Claude CodeCodex
An automated review of a user flow shown in a PNG image or Figma design. It creates a Markdown document covering the understood flow, missing scenarios, edge cases, and UI/UX improvements.
SaiHemanthMaddi/AI-Agent-QA-Skills-Lab-Repo
Skill Claude CodeCodex
Cypress end-to-end testing with custom commands, intercepts, and component testing.
Skill Claude CodeCodex
A tool for creating PCAP files, which are recordings of network packets, from plain-language descriptions of HTTP traffic. The files include the TCP connection setup and close sequence.
Skill Claude CodeCodex
Deterministic simulation testing for containerized services. Write Lua scripts to inject chaos (pause, kill, resource deprivation) into Docker containers with reproducible, seeded fault injection. Use when writing chaos experiments, testing service resilience, or debugging distributed systems.
Skill Codex
Route the aoa-evals skill family for central proof selection, review, evolution, named results or verdicts, source-linked reports, Eval Forge owner review, and proof lifecycle. Hand repository-local eval selection, application, intake/design, or session-hit classification to aoa-eval. Candidates, readiness checks…
Skill Claude CodeCodex
How to write good tests - behavior-focused assertions, the AAA structure, red/green/refactor, small vertical slices, and what to mock versus leave real. Use whenever writing a new test, modifying or fixing an existing test, reviewing someone else's tests, deciding whether something needs a test, choosing what to mock…
Skill Claude Code
Apply standard Python refactoring patterns and re-run pytest.
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: