Навыки: Тестирование

Test automation support — test progress tracking, human interaction requests, and activity log. Triggers on "test progre...

Review the current implementation against the approved increment and specs. Identifies drift, regressions, and missing s...

Android UI testing with Espresso framework including view matchers, actions, assertions, idling resources, and RecyclerV...

Compute P3O effective sample size and derive adaptive clipping and KL coefficients from replay policy probabilities.

Produces a cost or effort estimate someone can defend — decomposing the work, choosing between analogous, parametric and...

Assess pilot workflows and deliverables for ethical considerations and policy alignment. Use when evaluating fairness, b...

This skill should be used when the user mentions "dark patterns", "accessibility", "a11y", "privacy", "tracking", "analy...

Passive ethical review skill. Activates when user-facing features touch the four ethical concerns: manipulation, accessi...

Top-level orchestrator for the Gaia Skill Tree evidence verification pipeline. Run this when you want to do a full evide...

Instrument Python LLM apps, build golden datasets, write eval-based tests, run them, and root-cause failures — covering...

Framework for capturing, storing, and comparing AI evaluations to measure consistency and completeness.Use when: compari...

Formal evaluation framework for Antigravity Code sessions implementing eval-driven development (EDD) principles. Enforce...

Formal evaluation framework for LLM features implementing Evaluation-Driven Development (EDD) principles.

克劳德代码会话的正式评估框架，实施评估驱动开发（EDD）原则

Claude Codeセッションの正式な評価フレームワークで、評価駆動開発（EDD）の原則を実装します

Complete collection of Claude Code configs for C++20 HPC development - agents, skills, hooks, commands, and rules

Configure and run the isolated eval loop pattern — generate, evaluate, refine until pass threshold met

Evaluate implementation plan before execution - validates architecture, coverage, dependencies, and best practices. TRIG...

Run eval scenarios to benchmark Mycelium effectiveness. Execute tasks using reflexion loop, validate against success cri...

Audit all skills in the current project for frontmatter completeness, effort level appropriateness, allowed-tools scopin...

Develop and run agent behavior evaluations. Use this skill when asked to "write evals", "test agent behavior", "create e...

Rule matrix security fixture for eval_user used by security rule matrix integration tests; not intended for production d...

Agent evaluation framework based on Anthropic's best practices. USE WHEN eval, evaluate, test agent, benchmark, verify b...

This SOP evaluates a completed brazil-bench attempt against the spec.md requirements, capturing metrics for comparison a...

Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choice...

This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent qua...

PluginEval quality methodology — dimensions, rubrics, statistical methods, and scoring formulas. Use this skill when und...

Evaluation and reporting for code quality, performance, security, architecture, team processes, AI/LLM outputs, A/B test...

Independent assessment without debate context — adversarial loop prevents gaming

Iterative refinement workflow for polishing code, documentation, or designs through systematic evaluation and improvemen...

Create new event scraping scripts for websites. Use when adding a new event source to the Asheville Event Feed. ALWAYS s...

Testing event sourcing patterns including event store validation, projection testing, saga orchestration, and event vers...

Complete Everhour time tracking integration for accessing and managing time entries via REST API

Produce visual PR evidence — a screenshot or video — whenever a change has on-screen impact. Tests are never a substitut...

Use when adding ShapeShift Labs Evidence Kit to a JS/TS project, initializing the full tests/fuzzers/benchmarks/package-...

Screenshot-obsessed, fantasy-allergic QA specialist - Default to finding 3-5 issues, requires visual proof for everythin...

Verifies completion claims with evidence before declaring done. Use before stating "done", "complete", "fixed", "shipped...

Estructura y estilo del template HTML para reportes de evidencia de ejecucion de test cases. Incluye header, tabla de pa...

Weights a pile of "validation" by what people DID, not what they said. Takes interview quotes, sign-ups, LOIs, pilots, p...

- Completing code implementation

Run the evm-wallet Docker e2e tests (build, start stack, wait for healthy, test, diagnose failures).

Validate PRD, UX, Architecture and Epics specs are complete. Use when the user says "check implementation readiness".

Perform adversarial code review finding specific issues. Use when the user says "run code review" or "review this code"

Audit EVO source files for file-reference convention violations using parallel Haiku subagents. Use when users requests...

Dual-layer PR review tool (Raven's Verdict). Runs adversarial cynical review and edge case hunter in parallel, merges an...

Generate end to end automated tests for existing features. Use when the user says "create qa automated tests for [featur...

Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something

Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial...