ab-test-setup
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-29 00:09
Testing & quality
12,876 results
cdk-testing-review
AWS CDK test-coverage reviewer. Use when a PR adds or changes tests (`**/*.test.ts`, `integ.*.ts`, `*.snapshot`) or ships new functionality, branches,…
git-ops
Single front door for everything git and GitHub — saving work, getting the latest, backing up, and putting changes online. Routes plain-language requests to…
php-style
Use when writing, editing, or reviewing PHP code. Covers whitespace, imports, declarations, attributes, callbacks and PHPDocs, including tests and preservation…
test-audit
Use when writing, changing, or reviewing tests, or when asked to audit tests, prune low-value tests, or find duplicate coverage. Check whether each test…
swarmy
A self-improvement loop that iteratively makes things better. Use when the user wants to improve something through experimentation -- code quality, model…
codex-review
Use this skill when users ask for code review, review pending changes, or inspect the latest commit with Codex-based review workflows. It prepares context,…
qa
Generate a manual QA test plan from code changes and output it to the terminal (default), a GitHub issue, or a markdown file. Focuses on scenarios requiring…
investigate-debug
Use when something is wrong and the cause is not yet known — failures, regressions, flaky behaviour, performance problems, incidents, or a user report that…
neovim-debugging
Debug Neovim/LazyVim configuration issues. Use when: user reports Neovim errors, keymaps not working, plugins failing, or config problems. Provides systematic…
mock-factory
Create reusable mock or stub factories that generate configurable, typed fakes for tests. Use when mocks are repetitive, hard to maintain, or need per-test…
queue-worker-test
Write tests for background jobs and queue workers covering processing logic, retries, and failure handling. Use when testing workers, job processors, or queue…
snapshot-test-cleanup
Replace brittle snapshot tests with focused, meaningful assertions that verify behavior. Use when improving test reliability, fixing flaky tests, or migrating…
test-fixtures-factory
Create typed fixture and factory systems for test data with sensible defaults and per-test overrides. Use when tests repeat large objects or need reusable data…
test-isolation-fix
Fix test isolation by removing shared state, global side effects, and order dependencies. Use when tests are flaky, fail in CI, or pass individually but fail…
opportunity-solution-tree
Opportunity Solution Tree (Teresa Torres) mapping outcomes → opportunities → solutions → assumption tests. Use when prioritizing discovery work, mapping…
stata-code
Use this skill whenever the user asks to run Stata code, debug a `.do` file, work with a Stata-backed Jupyter notebook, repair a Stata error, interpret `r()` /…
rescript
Write, review, debug, and explain ReScript code and rewatch projects. Use whenever the user mentions ReScript, .res/.resi files, rescript.json or…
code-review-excellence
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when…
github-actions-latest
Get the latest version of GitHub Actions from github.com/actions/ and update workflow files. Use when the user asks about Action versions, wants to upgrade…
intelligence-structure
Rigorous analysis, hypothesis testing, and method criticism for intelligence work. [WHAT] Takes raw material, builds testable hypotheses, assesses…
issue-autopilot
Autonomously drive a whole folder of local issue files to done — for each ready issue it runs execute-issue, then code-review +…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing…
cekura-results-report
Use when the user asks for a report on existing test results shaped by a purpose: a weekly status report, a leadership summary, how responsive / secure /…