release-smoke-test
Test an oh-my-opencode-slim release candidate or bugfix before publishing. Use when validating a packed plugin artifact, release branch, crash fix, OpenCode…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-02 00:09
Testing & quality
13,037 results
ai-cli-benchmark
Design, run, and review fair performance, token, and cost comparisons across GitHub Copilot CLI, Codex CLI, and direct model APIs. Use for AI CLI benchmark,…
deep-novel-system
A comprehensive system for writing high-quality long-form novels, skilled in complex narratives, sensory description, cross-chapter memory management, and feedback loops. Supports multiple genres and adult themes (within the scope of user authorization). Use this skill when the user wants to start a new novel, continue an existing novel, or needs long-form structured narrative guidance.
rebound
Rebound recomposition budget monitor skill for Compose performance analysis. Guides budget class interpretation, violation diagnosis, skip rate analysis,…
jira-qa-scope
Draft the QA scope and plain-language Given/When/Then test scenarios for a Jira ticket, built from the full ticket, the decisions made in its comments, and the…
lfg
Run the full autonomous engineering pipeline end-to-end (recall prior learnings, plan, implement with TDD, review and autofix, verify, commit, push, open PR,…
msw
Mock Service Worker (MSW) v3 rules and official best practices. Use before writing or editing any code that imports from 'msw' (msw, msw/node, msw/browser,…
lfg
Run the full autonomous engineering pipeline end-to-end (recall prior learnings, plan, implement with TDD, review and autofix, verify, commit, push, open PR,…
pr
Generate or update a structured pull request with summary, user impact, acceptance criteria, QA scope, risk areas, and executable test scenarios, then open it…
android-app-submission
End-to-end submission of a native Android app (AAB) to the Google Play Console for review and closed testing, driven through the Play Console web UI with…
e2e
LoongCollector E2E testing full-process guide: design, writing, running, and debugging. Use this skill when you need to write new E2E tests, run existing tests, or troubleshoot E2E test failures.
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web…
test-driven-dev
[project] OPC-Starter test-driven development specification. Complete workflow for managing and executing Playwright E2E tests, demo mode tests, and unit tests. Applicable when adding test cases for new features, running authentication/registration/demo tests, and maintaining test planning documents. Use when the user mentions testing, E2E, Playwright, demo, test cases, quality, or adding tests.
control-ui
Build or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI. Use for local UI verification, screenshots, accessibility…
run-smoke-tests
Run Playwright smoke tests, debug failures, and verify fixes
thermo-nuclear-code-quality-review
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality…
verify-this
Explicit-only local experiment for a measurable behavior claim. Use only when the user invokes $verify-this or explicitly asks for a baseline/treatment…
diagnosing-bugs
Rigorous diagnosis loop for hard, unresolved, intermittent bugs and performance regressions. Use when the user explicitly asks to diagnose, debug, or find a…
grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
solopi-ai
Run Android real-device tests through SoloPi Harness, select the built-in Alipay template, and generate an acceptance report with full screenshots. Rules are used by default; Laya is an optional local desktop experimental mode. It also supports compiling verification plans from requirements/AC, interaction recording, replay, dynamic Agent, performance monitoring, signed on-device models, and multi-device CI.
agent-regression-evals
Use when an agent, prompt, model or tool change needs proof it did not make the agent worse — setting up a regression eval suite, deciding whether a pass-rate…
testing-dbt-models
Adds schema tests and data quality validation to dbt models. Use when working with dbt tests for: (1) Adding or modifying tests in schema.yml files (2) Task…
code-review
Alias for Codex-led multi-model code review. Use when the user invokes code-review, asks for code review with multiple models, or requests consensus code…