test-gap-finder
Finds behaviour changed on the current branch that no test exercises, by mapping each changed function and branch in git diff to the tests that cover it, then…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-02 00:09
Testing & quality
13,035 results
proof
Use proof to capture test runs as shareable, replayable evidence artifacts. Invoke this skill whenever the user wants to preserve or share proof that tests…
rocketsim-setup
Connect an AI coding agent to RocketSim so it can read, tap, type, swipe and verify an app running in the iOS Simulator. Use when the user wants an agent to…
threads-post-spoiler
Creates and publishes a spoiler-style post to Meta Threads using Playwright browser automation. Trigger when the user says "spoiler post on Threads", "hide…
integration-test
Full SDK integration test that runs actual queries through the Claude SDK sandbox. Use after making changes to SDK client code, session management, skill…
good-skill
A well-structured test skill that follows the agentskills.io spec. Use when testing skill evaluation tools.
scoped-skill
Test fixture for scoped vs full scanning
fsa-announcements
Fetch announcements from the Financial Services Agency of Japan (FSA), combining the official news RSS feed (~15 latest items) with archive pages…
qa-studio
Create, edit, and execute browser-based UI tests using QA Studio and Amazon Nova Act. Use when the developer wants to build a test case (in JSON or via the…
caveman-review
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix.…
pic-integration
Run an integration study to test components together
test-a11y
Run comprehensive WCAG 2.1 AA+ accessibility tests on a URL. Use when user wants to test accessibility, a11y compliance, screen reader support, or keyboard…
test-responsive
Run responsive design and visual adaptation tests across 4 viewports. Use when user wants to test responsive layout, mobile design, viewport behavior, dark…
experiment-stats
This skill should be used when the user asks 'is this A/B test significant', 'did the variant actually win', 'compute lift and confidence interval', 'score a…
sg-change-report
Use after visual runs, screenshot capture, frontend PRs, or before stakeholder review — creates the durable ShipGuard before/after report for UI-visible…
repo-test-audit
Use when the user asks where tests live, which test directory holds them, how complete the tests are, or which tests are not collected by CI.…
baidu-wenku-aippt
Baidu Wenku AI PPT Generation Tool — Automatically generate high-quality PPTs from a single sentence, supporting multiple styles, scenarios, and color schemes. TRIGGER: Triggered when the user mentions "generate PPT/make a PPT/create a PPT/AI PPT/aippt/slides/presentation". DO NOT TRIGGER: Non-PPT-related operations, file management operations, cloud drive upload/download operations, etc.
quality-checklist
Code review quality checklist. Use before commits and during code review.
testing-procedures
Testing procedures for Kalahari project. Use for running tests and analyzing results.
gate-plan
Authors a gate document for a queue item — a production validation plan that defines what must be proven before work is considered done. Applies the quality…
gate-review
Audits an existing gate document against the gate-plan quality bar — the quality assurance step between plan and work. Produces findings (structural…
ad-test-loop
Plan, launch and read paid social ad tests so the spend buys a decision: a test plan before production, a safe launch in the ad platform (Meta Ads Manager…
scienceclaw-benchmark-for49
Use when a task gives SMT-LIB v2 scripts (quantifier-free nonlinear integer or integer-real arithmetic, QF_NIA / QF_NIRA, SMT-COMP style single-query…
skillify
Turn a working solution into a permanent, tested skill — extract pattern, create SKILL.md, write tests, publish to registry