scrutinize
Outsider-perspective deep review of a plan, PR, design doc, or code change — questions intent first (should this exist?), then traces the actual code path…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-31 00:15
12,984 results
Outsider-perspective deep review of a plan, PR, design doc, or code change — questions intent first (should this exist?), then traces the actual code path…
4-phase systematic debugging methodology with root cause analysis and evidence-based verification. Use when debugging complex issues.
Testing patterns and principles. Unit, integration, mocking strategies.
Audit and improve accessibility in Flutter apps. Use when the user wants to check WCAG compliance, add semantic labels, verify screen reader support, or review…
Use this skill when the user wants to write, generate, or improve Flutter tests at any level. Trigger phrases: "write Flutter tests", "generate tests", "widget…
Use when designing quality snapshots, generated quality reports, structural metrics, debt thresholds, regression budgets, quality gates, or gradual cleanup…
Test MCP servers through mcp-use inspector. Two commands: protocol-level verification across 19 checks, and LLM-powered end-to-end testing with domain-adaptive…
Use skill if you need reliable @anthropic-ai/playwright-cli browser automation for navigation, forms, screenshots, tab flows, console/network debugging, or…
Use if testing or debugging an iOS app via agent-device CLI — simulator flows, evidence, bug triage.
Use skill if you are validating an MCP server, debugging broken primitives, or testing tools, resources, prompts, and transports before shipping.
Test-driven development — vertical red-green-refactor slices through public interfaces.
Enforce auditing of paper generation quality to prevent model substitution, broken logic, and empty content. Invoke when the user requests checking/auditing/acceptance/ensuring/verify/QA, or when gatekeeping is needed before merging.
Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions. Covers: launching Chrome in debug…
Verify a game with evidence on its selected target runtime. Launch the actual build and prove real rendering, input, the core loop, at least one designed…
Use when test time is limited and priorities must be set. Suitable for release test planning, urgent fix verification, and cross-module risk assessment. Combines the probability × impact matrix, Bach Heuristic Risk-Based Testing, and HAZOP.
Used when designing test cases. Suitable for functional testing, regression testing, and test case preparation before UAT. Integrates five black-box methods: equivalence partitioning, boundary value analysis, decision tables, state transition testing, and error guessing.
Build and run evals for LLM and agent systems: golden datasets, LLM-as-a-judge with bias control, trajectory/step/outcome scoring, adversarial refuters, and CI…
When the user wants to find and fix bugs, or says 'QA this,' 'test this,' 'find bugs,' 'why is this broken,' 'it doesn't work,' 'check for bugs,' 'smoke test,'…
When the user wants to prevent regressions, improve test coverage, or says 'add tests,' 'improve coverage,' 'we keep breaking this,' 'write regression tests,'…
Red-green-refactor cycle for test-driven development
Enforce evidence-based verification before claiming any task is complete
Use when the user requests acceptance testing, regression testing, visual inspection, or defect retesting of a deployed OneOS test environment, including Midscene and Playwright automation.
Audit a CS or AI research project for reproducibility across environment, data, code, configuration, logging, and documentation. Use this skill whenever the…
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles