Skill Claude CodeCodex
Measure synthesized Web Audio when implementing sound effects or diagnosing playback and sound-quality defects.
not rated 1
changed 1mo ago A 20 tokens
original MIT
loop-engineering
866imMamdouhaboammar/loop-engineering-skill
Skill Claude CodeCodex
Use when designing, orchestrating, or executing autonomous multi-agent coding loops with financial budget caps, minimal fixes, and continuous dev-QA gates.
not rated 1 2mo ago A 33 tokens
original MIT
verify
867Skill Claude CodeCodex
Run the HUMHUM quality gates that are actually touched by the current diff — frontend typecheck + vitest, and Rust fmt/clippy/test — mirroring CI. Use before marking work done, opening a PR, or when asked to "verify", "check", or "run the gates".
not rated 1 2mo ago A 62 tokens
original MIT
Skill Claude CodeCodex
Scans a target project to extract idiomatic patterns (test framework, code style, architecture, conventions) and generates customized TDD agents that use the project's actual patterns instead of generic pseudocode. Use when the user wants to adapt the TDD agents to a specific codebase.
not rated 1 4mo ago A 62 tokens
original Apache-2.0
jrobelia/inventree-plugin-ai-toolkit
Skill Claude CodeCodex needs its repo
Run the InvenTree Plugin AI Toolkit devcontainer and execute a plugin's test-all.sh. Covers Docker setup, postCreateCommand, server startup, and the lint/unit/integration/frontend-build/E2E layers.
not rated 1
changed 1mo ago A 49 tokens
original MIT
qa-runner
870Skill Claude CodeCodex
Use when asked to "run QA", "qa check", "test checklist", or execute QA checklists against a running app via browser automation. Requires the browser-bridge MCP server and Chrome extension.
not rated 1 2d ago A 44 tokens
original MIT
adrianmikula/JakartaMigrationMCP
Skill Claude CodeCodex
This skill guides scanning the codebase for memory and performance code smells, debugging performance problems, writing performance/memory tests that follow established project conventions, and updating docs/patterns/ when new categories of issues are discovered and fixed.
not rated 1 2mo ago A 0 tokens
Skill Claude CodeCodex
A QA workflow for testing software changes and fixing reported bugs through an MCP server. QA means checking that software works as expected before release.
not rated 1 4mo ago A 67 tokens
Skill Claude CodeCodex
Run every applicable sensor and produce a unified PASS/FAIL report.
not rated 1 4mo ago A 13 tokens
original MIT archived
Skill Codex
Build, run, record, replay, debug, and maintain deterministic terminal, TUI, PTY cassette, and browser-terminal agent regression tests with ptywright. Use when an agent needs to drive CLI/TUI apps, create ptywright scripts, configure ptywright.config., record or replay PTY output, solidify browser terminal agent flows…
not rated 1 5mo ago A 93 tokens
original Apache-2.0
Skill Claude CodeCodex
Generate business-level test scenarios from a feature branch and push them to Kiwi TCMS. Use when asked to "generate tests for TICKET-XXXX", "push tests to Kiwi", or "update tests after PRD change".
not rated 1 4mo ago A 52 tokens
Skill Claude Code needs its repo
A coding workflow for implementing an existing feature or bug fix from a written plan, then adding unit tests and running integration tests.
not rated 1 5mo ago A 32 tokens
original MIT
ie-migration-vrt
877rayven122/mcp-ie-migration-vrt
Skill Codex
Compare a legacy page rendered in Microsoft Edge IE mode with its migrated Chromium Edge page, diagnose visual differences, fix the migrated implementation, and repeat VRT. Use when working on IE-to-Edge migrations with the mcp-ie-migration-vrt MCP server, especially when both browser sessions must be operated into…
not rated 1 1mo ago A 74 tokens
original MIT
Skill Codex
Maintain, debug, test, document, package, or release the Nolane Habitat repository. Trigger when work changes Habitat workspace lifecycle, storage, semantic providers, mutation safety, MCP, Observatory, tests, Codex integration, or release artifacts.
not rated 1 2mo ago A 56 tokens
git-asmt-repo
879Canvas-LMS-MCP/canvas-teacher-mcp
Skill Claude CodeCodex
GLOBAL, language-agnostic L1 abstract for building + testing a GitHub coding-assignment repo through the org-hub autograder. Owns the WHAT (audit → instruction-fidelity harness → prove 100/100 → ship the Starter → gates) with NO language mechanics. The HOW-to-compile/run/assert is delegated to an L2 language skill…
not rated 1 2mo ago A 126 tokens
original MIT
aar-operations
880phenomenoner/adaptive-agent-harness
Skill Codex
Operate the Adaptive Agent Runtime through its public MCP tools. For tasks that need tool use or analysis, consider AAR MCP early when bounded stateful computation, brokered jobs, operations, contracts, or artifacts can materially help; software planning, development, testing, and troubleshooting belong to this class…
not rated 1 1mo ago A 145 tokens
original MIT
bongo-test
881Skill Claude CodeCodex
A skill for testing the BongoCat MCP connection by checking its response, reading status, changing an expression by name, and sending a speech bubble.
not rated 1 2mo ago A 44 tokens
agent-mailbox
882Skill Codex
Create and use disposable, token-scoped email addresses through a configured Agent Mailbox MCP server. Use for testing signups, email verification, magic links, password resets, one-time codes, inbound messages, attachments, and transactional email flows.
not rated 1 yesterday A 52 tokens
original MIT
capture-failure
883Skill Claude CodeCodex
Turn a captured Codex tool failure into reviewed .tape evidence and an offline regression test. Use when the user asks to inspect a failed run, fork captured evidence, save a regression, or prepare AgentTape evidence for CI.
not rated 1 2mo ago A 50 tokens
original MIT
ilkuru/mcp-server-antigravity-hyperv
Skill Claude CodeCodex
Standard operating procedure for safely deploying, testing, validating, and debugging PowerShell and CMD scripts inside isolated Hyper-V virtual machines using MCP tools.
not rated 1 2mo ago A 34 tokens
original Apache-2.0
ck:cook
885huuanh20/awesome-ai-agent-skills
Skill Claude Code
Implement a feature phase by phase from a phased JSON master or Markdown plan. Before each phase, confirm whether to create/run unit tests and whether to run ck:quality, unless explicit flags supply those choices. Supports token-budgeted execution, resumable state, and TDD handoff to ck:test.
not rated 1 3mo ago A 64 tokens
original MIT
invarianteval
886Skill Claude CodeCodex
Before finalizing structured or extracted output in a domain with declared safety invariants, verify the output against your invariant suite and refuse to ship when a locked field was model-auto-filled. Invoke when the user or task involves high-stakes structured extraction, compliance fields, or pass/fail results…
not rated 1 4mo ago A 67 tokens
original MIT
glassbox
887Skill Claude CodeCodex
Verify and debug your own web UI on localhost. Use when you changed frontend code and need to check it actually works — console/network errors, layout/contrast/a11y problems, dead buttons, wrong colors, broken handlers — or when testing a dev server, reproducing a UI bug, or debugging why an element behaves wrong.…
not rated 1 1mo ago A 101 tokens
original MIT
hyprland-tester
888Skill Claude CodeCodex
Automated desktop UI testing through the Hyprland MCP server. Captures screenshots, analyzes them via the vision skill, clicks and types, and re-verifies. Use when asked to test a desktop app, verify UI behavior, run a visual regression check, or drive a background app without interrupting the user. Triggers: "test…
not rated 1 1mo ago A 0 tokens
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: