SuperAPI AI DirectoryFind an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-03 00:11
13,055 results
Three-layer browser testing workflow (E2E + AI acceptance + debugging diagnosis). When the user requests "E2E testing", "interface acceptance", "UI automation acceptance", "browser test", "acceptance test", "playwright testing", "accept this feature/page", "browser testing", or needs to diagnose page interaction, rendering, Shadow…
Analyzes a module or function and generates appropriate tests. Detects the project's test framework, discovers existing test patterns, and produces tests that…
Generates a test strategy document for a project or module. Analyzes existing coverage, identifies gaps, prioritizes what to test, and recommends test types…
Use when evaluating the quality of a GitHub README, judging whether it reads as human-written or AI-generated, and producing concrete fixes. Triggers on…
writing, running, and debugging Playwright tests. working with their output from github actions
Verification steps for code changes. Debug mode defers lint; full checklist before merge. Use after changes or when planning.
Write comprehensive tests for all components using Jest, Effect-TS, and test helpers. Use when creating new tests, adding test cases, or when the user asks to…
Triage the team's open GUS backlog — propose closing done-but-open work items (with code/test citations), flag under-specified items for grilling, catch…
Operate a real VS Code instance through drivable-vscode. Use for drivable VS Code, exploratory testing, customer bug reproduction, feature verification,…
Verification steps for code changes. Use after ANY code change to ensure quality, or when creating plans because those should include verification steps.
Use when it is necessary to verify whether a checklist.md file conforms to the forge_checklist-best-practice specification, including decidability, example completeness, classification structure, and Bad Case section review. Trigger words: check checklist specification, checklist review, verify checklist quality.
Use when you need to check the code implementation consistency of multiple components of the same type (such as Button, Page), cross-compare implementation-level differences in Props, events, styles, hooks, etc., and ensure code patterns are unified. Trigger words: check component consistency, compare component implementations, component pattern audit.
Use when you need to scan and verify whether React component folders comply with the forge_component-unit-best-practice specification, including integrity checks of folder structure, unit tests, and Storybook story files. Trigger words: check component specification, component folder review, check components, component structure scan.
Use when you need to check whether native try-catch is used in violation in the code, ensure the project uses neverthrow for functional error handling; scan and report all native exception handling code. Trigger words: check error handling, neverthrow check, error handling specification check, Result type check.
Use when you need to check whether native HTML elements (such as button, input, select, etc.) are used in violation of the rules in the code, ensuring compliance with the component library conventions, and prioritizing the use of component library components over native elements. Trigger words: check UI components, check native elements, UI component convention check.
Use when you need to implement features, fix bugs, or refactor behavior in a test-first manner, strictly following the Red-Green-Refactor cycle: write a failing test first, then write the minimal production code, and complete refactoring verification. Trigger words: TDD, test-first, red-green-refactor, write tests first.
Preview, validate, and debug OpenGraph cards and social link previews locally via the metaprev CLI. Use whenever the user asks about how their site looks when…
Check air quality, AQI, PM2.5, PM10, pollution levels for any city from the terminal using airq CLI. Installs, configures, and runs air quality queries. Use…
Diagnosis loop for hard bugs and performance regressions — build a tight feedback loop first, hypothesise second. Use when user says "diagnose", "debug this",…
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B…
Behavior-driven development: Discovery → Formulation → Automation. Use when the user wants to build features or fix bugs via Gherkin scenarios and the BDD…
Review a diff for correctness, risk, and missing proof. Do not rewrite it unless asked.
Run the repository's own check for the files that changed, and report the result.
Frank's personalized lifestyle design and joy optimization