Навыки: Тестирование

Run all validation checks before tagging a new release

Pre-flight checklist — run high-signal review skills before a release

Runs a pre-submission review of a technical paper across five dimensions: macro logic, writing details, English grammar,...

Run a final read-only readiness check before an investment or trade across exact identity, evidence cutoff, executable e...

Format, validate checkstyle, and run tests before committing — in the correct order

Discover and run all pre-commit code quality checks (linters, type checks, i18n extraction) in a monorepo, auto-fix fail...

Predict with models honestly — baselines, leakage-free validation, calibration, drift awareness.

Prefer const over let and readonly properties where possible Use when enforcing code quality standards. Quality category...

Align a fine-tuned model with preference data using DPO, ORPO, KTO, or SimPO. Use when preference pairs or thumbs-up/dow...

Runs all pre-flight checks sequentially — TypeScript checking, tests, and production build — stopping on first failure....

Run all preflight checks (format, gn_check, presubmit, build, tests) to make sure the current work is ready for review.

Run the right lint/format/type/test gates BEFORE committing or pushing. Sniffs the current repo's stack (poetry/uv/yarn/...

Pre-commit quality gate that catches 'almost right' code. Use when about to commit — auto-fires before commit to validat...

Use before committing to a heavy or irreversible plan — imagine it's 6 months later and this failed; enumerate why, scor...

Starts development server for E2E testing. Detects package manager and verifies server startup. Triggers on keywords: pr...

Use when preparing data and context before /resolve-issue, TDD, or CR runs. Loads the assignment, extracts every concret...

Use this skill whenever preparing agentsmesh for an npm release — whether first publish, patch, minor, or major. Trigger...

Environment prerequisites for ESM/gradle Hub module development. Use when starting new work or validating environment se...

Stand up the project's live app and hand it to the user to try a change firsthand, then gate on their verdict before con...

Comprehensive E2E + Security Tests for Vercel Preview Deployments. Combines Playwright automation with Claude-in-Chrome...

Prepare PRINCE2 Closing a Project material: product acceptance, end project report, lessons report, benefits review plan...

Build the PRINCE2 Initiating a Project pack: project initiation documentation, business case, project plan, controls, ma...

Prepare PRINCE2 Managing Product Delivery material: work package acceptance, team plans, checkpoint reports, quality evi...

Prepare the PRINCE2 Starting Up a Project material: mandate review, project brief, outline business case, project produc...

Apply before you measure, and before you trust, report, or act on a number you measured: a speedup, a regression, a thro...

Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an...

Explain the Number

Promote high-value, evidence-backed claims into operational principles (principles-v1) that drive subagent behaviour, ma...

SOP for locating, auditing, and importing production-tested reference patterns and peer-reviewed literature. Trigger whe...

協助開發者在測試私有（private）和內部（internal）成員時做出正確的設計決策。當使用者需要測試 internal 類別、使用 InternalsVisibleTo、測試私有方法、或改善程式碼的可測試性時，請使用此技能。

Estimate realistic price/return distributions, target and downside probabilities, and probability-weighted scenarios for...

A stakeholder asks to make search faster.

Use when implementing procedural generation — noise-based terrain, BSP dungeons, cellular automata caves, wave function...

Use when generating or reviewing the GEOMETRY of a game — procedural terrain, meshes, structures, and scatter. Covers no...

Analyzes a business process to find where time and effort are lost: maps the real current state, sets a measured baselin...

Validate process JS files for correct SDK patterns, task definitions, syntax, and quality gate implementation.

Create a polished, verifiable demo video from local browser captures and an explicit choreography manifest. Use when a p...

Use when legacy prompts or older framework flows reference `product-manager` and you need the modern runtime to resolve...

Test, validate, and verify that code changes produce correct product behavior. Use when the user says 'verify this works...

Production readiness check from UX perspective - update BROWNFIELD.md with implemented features, check GREENFIELD alignm...

Autonomously deep-scan entire codebase line-by-line, understand architecture and patterns, then systematically transform...

Autonomously deep-scan entire codebase line-by-line, understand architecture and patterns, then systematically transfor...

Sets quality expectations for implementation — "imagine this serves 1 million users." Checks for observability, error ha...

Validate that an application is ready for production deployment and operation.

Build lightweight production smoke test suites that verify critical user paths, API health, and third-party integrations...

Master the AI tools that handle administrative work and boost personal productivity. From meeting notes to email managem...

Create professional learning and instructional-coaching materials for K-12 educators: classroom observation / look-for t...

Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence.