Навыки: Тестирование

Create a new change proposal with spec deltas

Facilitate methodical review of proposals (technical designs, product specs, feature requests). Use when asked to "revie...

Review technical project proposals for quality, overpromises, legal risk, and internal consistency. Use when the user as...

Adversarial reading methodology for narrative fiction — find what doesn't work, not confirm what does. Focus-area driven...

Change agent-office's public contracts — AgentEvent fields, inbox/reply/messages HTTP APIs, the IPC contract (AgentOffic...

Use when testing Swift code that depends on file system, network, or external APIs via protocol-based dependency injecti...

Prove that your work is satisfactory

[Code Quality] Prove fix correctness with code proof traces, confidence scoring, and stack-trace-style evidence chains....

Before declaring any task complete, actually verify the outcome. Run the code. Test the fix. Check the output. Claude's...

让 agent 拿证据交差，而不是只说一句「做好了」。三种时候用：agent 准备交差时；用户为同一件事第二次纠正 agent（又错了、说过多少遍、怎么让它别再犯）；要写测试、或者清理没用的测试时。prove it、stop repeati...

Use when a leading diagnosis or nontrivial fix has initial support and needs one adversarial counterexample before accep...

Use when optimizing prover performance, reducing proof generation memory usage, configuring prover infrastructure in Doc...

Provider verification workflow for contract testing

Provide comprehensive prioritized performance optimization recommendations for frontend, backend, and infrastructure. Us...

Testing patterns for Prowler SDK (Python). Trigger: When writing tests for the Prowler SDK (checks/services/providers),...

E2E testing patterns for Prowler UI (Playwright). Trigger: When writing Playwright E2E tests under ui/tests in the Prowl...

Proxmox VE cluster management including VM provisioning, template creation with cloud-init, QEMU guest agent integration...

Run a bounded proxy recovery that compares explicit/implicit-style fusion and performs a small optimizer step on fusion...

Executes PRP plan files with validation loops, reports, and archiving. Use when implementing a .plan.md file, executing...

Delete low-signal tests (tests that restate the code, always pass, or break on every refactor) one test area at a time,...

Run competing implementation approaches in isolated git worktrees, evaluate them against a shared quantitative rubric, a...

Validate performance measurements and before/after claims. Use when benchmarking latency, throughput, query performance,...

Improve TypeScript domain types and input boundaries where casts, optional-field bags, duplicate schemas, or mixed seman...

Write and fact-check public copy so that every figure, credential, promise and command has a receipt - a source with a l...

Draft a persuasive public comment on a proposed rule, regulation, or plan. Use when asked to comment on a rulemaking, re...

Prepare a GitHub Skills exercise for publication, contribution, or rollout. Use this when the user asks for release read...

Run Proto UI's dynamic comprehension assessment and derive an unsigned local task-fit result. Use when an Agent needs re...

Integrate one already reviewed Proto UI pull request at its exact head when current-user or active standing authorizatio...

Take a change through a pull request in the pnpm repository — opening it, then staying with it after every push until CI...

Read-only Gesamtprüfung des Pulse-Branches vor größeren Änderungen oder Merge. Prüft Architektur, offene Regressionen, B...

Dashboard-Workflows von Pulse im echten Browser (Playwright, headless) testen oder neue E2E-Tests schreiben – Seite öffn...

Einen gemeldeten Pulse-Fehler reproduzierbar machen und dauerhaft absichern – Regressionstest zuerst (muss vor dem Fix f...

Create a pulse survey with structured process, quality checks, and system integration

Manually verify Pulse changes before a commit, release, or deployment. Use only when the user invokes /pulse-verify.

Separate pure computation from side effects (I/O, mutations, API calls) Use when enforcing code quality standards. Quali...

Delete tests that don't catch real bugs — the inverse of TDD. Use when reviewing legacy test suites, slow CI investigati...

Decide where a project goes and what to call it in a repository that uses Purview.BuildSdk. Use when creating, moving, s...

Use for any Playwright or end-to-end browser testing work: writing tests, fixing flaky ones, migrating from Cypress or S...

Set up Playwright in a project. Use when user says "set up playwright", "add e2e tests", "configure playwright", "testin...

PWA plumbing for apps/pwa: web app manifest, vite-plugin-pwa / Workbox strategy, update prompt, offline behaviour, iOS a...

编写可靠Python代。支持自动化配置和灵活的参数设置，适适配多种工作环境，增强工作效率。Python健壮编程工具。支持自动化配置和灵活的参数设置，适用于多种工作场景，提升工作效率和准确性。Python健壮编程是一款高效实用的工具。py支持...

Execute BioETL hierarchical code review orchestration (L1/L2/L3) across sectors S1-S8 with delegated sub-reviews, scorin...

Orchestrate hierarchical BioETL test swarms (L1/L2/L3) for full-audit, fix-failures, coverage-boost, optimize, and flaki...

Async testing patterns with pytest-asyncio. Use when writing tests, mocking async code, testing database operations, or...

Simulates lithium-ion battery charge, discharge and rest experiments with PyBaMM, records parameter-set provenance, chec...

Rule matrix security fixture for pycache used by security rule matrix integration tests; not intended for production dep...

Python data validation using type hints and runtime type checking with Pydantic v2's Rust-powered core for high-performa...

Framework de otimização multi-objetivo. NSGA-II, NSGA-III, MOEA/D, frentes de Pareto, tratamento de restrições, benchmar...