reconcile-code-review
Reconcile raw specialist findings against the previous bot review and human PR comments to produce a final classified finding list.
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
skill-crafter
Create high-quality, production-ready Grok Build skills (SKILL.md files). Generates correct YAML frontmatter (name, description with specific triggers,…
benchmarking-transaction-patterns
Guides benchmarking and comparing explicit multi-statement transactions versus single-statement CTE transactions in CockroachDB, with fair test methodology,…
senpi-qa
Manual QA harness for the senpi coding agent itself. MUST USE after changing packages/ai, packages/agent, packages/coding-agent, or packages/tui — a green…
web-testing
Web testing patterns and best practices using Playwright for automated testing
codeant-resolve-quality-gates
Find the pull request for the current branch, locate the CodeAnt CI/CD Quality Gate comment, parse the failures (SAST, Secrets, Duplicate Code, SCA, IAC), and…
dogfood
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find…
bug-bash
Run an agent bug bash of the Xum web UI in the bug-bash sandbox (TesterArmy `e2e explore` charters, each in its own locked-down Docker container with a seeded…
crap-gate
Read and fix CRAP gate findings (crap-check, the commit hook report, Quality / CRAP). Use when a crap-gate or crap-check report names a function, before…
gauntlet
Read and fix DRY and mutation gate findings (make dry-check, make mutate-check, Quality / DRY, Quality / Mutation). Use when a report names a new…
tbench
Terminal-Bench integration for Xum agent benchmarking and failure analysis
tests
Testing doctrine, commands, and test layout conventions
code-review
Reviews code changes using CodeRabbit AI. Use when user asks for code review, PR feedback, code quality checks, security issues, or requests fix-review cycles.
meta-ads-audit
Meta Ads audit — audience analysis, creative fatigue, budget pacing, lead quality
validate
Run THIS project's full quality gate — tests, type-check, lint, and (for full-stack) the build — and report overall health with ✅/❌. Use before opening a PR;…
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web…
scoped-tests
Use after changing code, before claiming work is done — picks the correctly scoped pytest command instead of running the whole suite. Helps avoid the…
cli-autocalibrate
Tune the terminal status assessment engine (Stage 1 rules) and status.Tracker (Stage 2 debounce) against the committed calibration corpus. Use when a status is…
desktop-devserver
Drive the local devserver at http://127.0.0.1:7777 to simulate GitHub lifecycle events and webhook deliveries against a running Hive Desktop instance. Use when…
writing-e2e-tests
Use when a developer wants to add, write, or create an end-to-end test for an Opik feature, page, or branch — e.g. "add an e2e test for the experiments…
cometchat-angular-v5-testing
Test an Angular app that embeds CometChat — what to mock vs exercise for real, TestBed setup for standalone kit components, avoiding real network in unit…
cometchat-flutter-v5-testing
Testing patterns for CometChat Flutter UIKit v5 (GetX-based). Covers flutter_test (built-in), mocktail for SDK mocking, widget tests around CometChat widgets,…
cometchat-react-native-testing
Test a CometChat React Native integration — mock the SDK for Jest unit tests, assert init-before-render ordering and no-Auth-Key-in-source, and use Detox for…
cometchat-react-v7-testing
Test a React app that embeds CometChat v7 — what to mock vs exercise for real, rendering kit components under a test provider, waiting out the async init→login…