parallel-verification
Build a Parallel Verification (PV) harness — an out-of-band, last-mile integration check that proves a system actually does what it claims by driving its real…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-27 00:15
Testing & quality
12,766 results
bun-test
Write and debug Bun tests with proper mocking, coverage, and isolation. Use when writing tests, debugging test failures, setting up test infrastructure,…
unity-playmode-testing
Drive Unity runtime verification with unity-cli. Use when the user asks to run PlayMode tests with Domain Reload, simulate keyboard, mouse, gamepad or touch…
dbt-test
Add schema tests, unit tests, and data quality checks to dbt models. Use when validating data integrity, adding test definitions to schema.yml, writing unit…
dbt-unit-tests
Generate dbt unit tests automatically for any model. Analyzes SQL logic (CASE/WHEN, JOINs, window functions, NULLs), creates type-correct mock inputs from…
code-review-amplifier
Apply this skill whenever the user asks to review code, a PR, a diff, or a merge request — or when they paste code and ask for feedback on it. Also trigger…
monte-carlo
Run Monte Carlo simulations for Finance Guru portfolio strategy. USE WHEN user mentions monte carlo OR run simulation OR stress test portfolio OR probability…
universal-debug
Meta-level consciousness engineering protocol for systematic problem-solving across all domains. Apply when facing ANY loop (code, life, strategy,…
environment-setup-android
Prepare and validate Android SDK, Java, and device tooling for Appium Android drivers
environment-setup-uiautomator2
Set up and validate a UiAutomator2 Appium environment on Android
playwright-test
This skill MUST be invoked when the user says "write a UI test", "create a playwright test", "scaffold playwright", "test a feature in the browser". SHOULD…
web-test
This skill MUST be invoked when the user asks to check or test 1C through the browser in interactive mode (quick manual checks). SHOULD…
python-testing
Design, extend, and review Python tests across the existing repository's test architecture, with emphasis on observable behavior, clear subject-under-test…
ascendc-operator-compile-debug
ascendc-operator-compile-debug — an installable skill for AI agents, published by ascend/agent-skills.
nautobot-sot
Nautobot IPAM & source of truth — IP address queries, prefix lookups, VRF/tenant/site filtering, IPAM search, connection testing. Use when looking up IP…
qa-prepare
Prepare the QA for completed work, with the paths to check, the tests, the documents and the useful data. To be used to define the QA for a task or…
pentesting-web-apps
Web application pentesting guidance for URL-driven assessments. Use this skill when testing an authorized web app from a single starting URL to map endpoints,…
nuke-fix
Use when executing a fix spec produced by nuke-audit, nuke-review, nuke-spec, or nuke-verify — "nuke fix", "execute the fix spec", "run the audit fixes".
test-delete-skill
A test skill created specifically for deletion testing
test-skill-litellm
A test skill created by LiteLLM automated tests
autoreview
Run a Codex-only structured code review closeout for local, branch, or commit diffs. Use when the user asks for autoreview, Codex review, structured closeout…
error-handling-test
Write tests for error paths, including exceptions, rejected promises, fallback behavior, and invalid inputs. Use when the user wants to cover failure modes,…
hypothesize-before-fix
State the likely root cause before writing code. Use when debugging bugs, errors, or failing tests to enforce hypothesis-driven fixes.
behavior-first-planning
Behavior-first planning discipline — intent → Gherkin behaviors → EXECUTED-red acceptance tests → spec → acceptance-gated bead DAG. No runnable acceptance…