skill-quality-review
Use when auditing or reviewing skill quality — batch checks across a library, deep per-skill grep methodology, usage stats, efficacy testing, or fix planning.…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-24 00:15
Testing & quality
12,627 results
tk-code-review
[user/auto] Review the diff after a fixed reference point along the two axes of Standards and Spec. Use it for branch, PR, commit-range review or for independent review of implementation results, and do not use it for requests that directly modify code.
test-provenance-guard
Detects tests that pass by construction — tests that define a private copy of the function under test instead of importing the production module — and…
pp-air-quality
Use OpenAQ and AirNow source-backed recipes for air-quality snapshots, nearby monitors, sensor history, point comparison, and AirNow AQI setup/current…
worktrees
Use when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparing…
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…
test-scope
How wide a test run must be at each gate of the workflow, what a run may execute, and when a run already made can be cited instead of re-run. Shared definition…
dotnet-sentinel-test
Test-only skill for verifying sibling file access in Copilot CLI
ads-landing
Score and diagnose Google Ads landing pages. Use when asked to audit a landing page, check landing page quality, diagnose high-CTR but low-conversion-rate ad…
debug-k8s-collection
Troubleshoot and debug Observe Agent data collection on Kubernetes. Use this skill whenever the user reports any K8s-side problem with Observe — pods crashing,…
address-review
Systematically address code review findings using TDD. Fixes in-scope issues, creates GitHub issues for out-of-scope items. Keywords: address review, fix…
write-validation-documentation
Write IQ/OQ/PQ validation documentation for computerized systems in regulated environments. Covers protocols, reports, test scripts, deviation handling, and…
positron-e2e-tests
This skill should be used when writing, debugging, or maintaining Playwright e2e tests for Positron. Load this skill when creating new test files, adding test…
aqe-plan-quality
Create risk-based quality and test plans for Agentic QE changes. Use when scoping a feature, translating requirements into verification work, selecting QE…
aqe-review-quality
Review Agentic QE changes and issue an evidence-backed quality verdict. Use for code review, regression-risk assessment, release readiness, quality-gate…
qe-court
Adversarial review court — a delivery (diff, PR, test suite, or artifact) is prosecuted by independent AI reviewers from different vendors, each with its own…
architecting-test-infra
Use when setting up or redesigning test infrastructure, BDD frameworks, fixtures, state isolation, data builders, seed layers, local services, preflight…
doing-code-review
Reviews code changes, PRs, diffs, branches, and agent-written code. Use when reviewing finished work, checking whether work is ready to merge, commit, or hand…
high-level-testing-strategy
Use when deciding what behavior needs tests, designing test cases, choosing automated vs manual verification, reviewing test coverage quality, or planning…
manual-interacting-with-claude-code-via-cli
ALWAYS LOAD THIS SKILL WHEN USER ASKS TO CHECK, VERIFY, SMOKE-TEST, REPRODUCE, OR RUN SOMETHING THROUGH `claude` OR Claude Code CLI, OR WHEN A PLAN CONTAINS A…
manual-interacting-with-codex-via-cli
ALWAYS LOAD THIS SKILL WHEN USER ASKS TO CHECK, VERIFY, SMOKE-TEST, REPRODUCE, OR RUN SOMETHING THROUGH `codex`, OR WHEN A PLAN CONTAINS A STEP TO VERIFY…
manual-testing
Use when verifying real runtime behavior manually: browser UI, API, CLI, infrastructure, smoke tests, e2e flows, logs, database/admin side effects, or when…
systematic-debugging
Use when builds break, behavior does not match expectations, or you encounter a bug, test failure, CI failure, flaky behavior, or unexpected behavior.…
test-driven-development
Use when implementing automated tests and code for new behavior, bug fixes, regressions, or behavior changes after test cases are known. BDD/test-first…