auto-improve-tests
Iteratively write, review, and improve frontend unit tests until quality score >= 9.2. Supports Vue 3 (Vitest + @vue/test-utils) and React (Vitest/Jest + React…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-04 00:13
Testing & quality
13,090 results
e2e-testing
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies. Use when writing,…
review-tests
Test Review / Audit Existing Tests / Find Test Blind Spots — Read an existing test, identify blind spots and suggestions, and produce a self-contained HTML report (without modifying any source/test/config). Each finding in the report carries a severity level and can be toggled…
tdd
Test-Driven Development skill for the ikigai project
browser-testing-playwright
A skill for setting up and running end-to-end browser tests using Playwright. It includes guidance on project setup, the Page Object Model, user flow testing,…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing…
capture-api-response-test-fixture
Capture API response test fixture.
no-mistakes
Validate your code changes through the no-mistakes pipeline - automated code review, tests, lint, docs, push, PR, and CI - before they reach the configured…
move-setup
Move package setup (Move.toml, edition, dependencies), building, testing, and common pitfalls from other Move dialects.
crap-check
CRAP metric, cyclomatic complexity, risky-to-change code, coverage audit. Ranks functions by change risk across languages and drives them under threshold.
coverage-report
Measure VivaDicta test code coverage from the terminal. Use when asked what the test coverage is, a module's or the whole-app coverage %, which lines/files are…
ios-simulator-skill
21 production-ready scripts for iOS app testing, building, and automation. Provides semantic UI navigation, build automation, accessibility testing, and…
loc-report
Count Swift lines of code across the VivaDicta codebase and refresh the production-vs-test history chart. Use when asked how many LOC / lines of code the…
screenshot
Capture screenshots from iOS Simulator using native xcrun simctl command for documentation, debugging, and visual verification. Optionally analyze the…
xcodebuild-testing
Run unit tests, UI tests, or specific test cases for VivaDicta using xcodebuild command-line tool
scientific-statistical-testing
Skills for statistical testing, multiple comparison, and enrichment analysis. Used when performing t-tests, chi-square tests, ANOVA, Bonferroni/BH correction, Fisher's exact test, and Bayesian inference. Patterns established in Scientific Skills Exp-03, 04, 06, 07.
chrome-browser-validation
Use the official @Chrome extension to connect to the user's existing Chrome for web page debugging, interaction testing, and visual acceptance. Across projects, it applies to browser verification after development is complete and to reproducing existing web page issues; static code checks and unit tests are not subject to this browser choice.
verify
Verify a code change does what it should by running the app.
plugin-runtime-debug
Use when an installed DSH Web plugin misbehaves only at runtime in the browser — paste/attachment/composer features that work once then fail, chips or panels…
plugin-test
Use when writing or reviewing tests for DeepSeek Harness plugins, external DSH plugin packages, or package changes in the deepseek-harness repository. Select…
writing-tests-first
Use when implementing non-trivial code changes that should follow TDD (write a failing test first, make the smallest passing change, then refactor safely).
predictive-coding-information-bottleneck
Build lightweight hallucination detection pipelines using Predictive Coding surprise signals and Information Bottleneck perturbation testing. Implements the…
seta-statistical-fault-attribution
Diagnose and attribute faults in compound AI systems (multi-model pipelines) using SETA's modular robustness testing framework. Applies perturbations, traces…
test-api
Use this skill when writing, reviewing, or maintaining automated tests for HTTP/REST APIs to keep them deterministic, isolated, and behaviour-focused. Acts as…