Навыки: Тестирование

Use when flattening complex branching dialogue trees, validating for dead ends and unreachable nodes, and ensuring local...

Deep QA skill for boundary value analysis — systematic identification of edge cases, off-by-one traps, state transitions...

How engineers handle rejected tasks — read feedback, find root cause, add regression tests, re-submit. The fix cycle tha...

How engineers map a confirmed plan to specific files and changes — the bridge from reasoning stage to work stage. Target...

How QA designs integration tests — what boundaries to test, test isolation, fixture patterns. Beyond unit tests into cro...

How QA thinks about test predefinition — structured TC-XXX criteria BEFORE implementation, phase-appropriate rigor, boun...

How QA identifies what needs re-testing when code changes — impact analysis, test selection, and the regression-checker...

How PM monitors and advances task stage progression — detecting stalled tasks, verifying methodology checks pass, coordi...

The structured protocol for producing qa_test_definition contributions — TC-XXX format, phase-appropriate criteria depth...

How QA validates completed work against predefined TC-XXX criteria — the review-side of QA's dual role. Verify each crit...

Guides an AI assistant through adding or changing an end-to-end test in flisk - deciding whether one is required, choosi...

This protocol evaluates the computational throughput and real-time efficiency of embedded CPU and GPU platforms. It meas...

4-phase systematic debugging for flow-fix. NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.

Enforces TDD Iron Law in flow-dev. NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST.

Use when defining or reviewing test strategy for Salesforce Flow, including Flow Tests, debug runs, path coverage, test...

Authors FlowMind .flow.yaml graphs with validate, fix, promote, and measure steps. Use when user writes or audits flows,...

Writes fluent, readable test assertions and validations using FluentAssertions library. Use when: Writing unit tests, va...

Atomically update all 6 Fluent learner databases (learner-profile, progress, mistakes, mastery, spaced-repetition, sessi...

此技能專注於使用 FluentValidation.TestHelper 測試資料驗證邏輯，涵蓋基本驗證、複雜業務規則、非同步驗證和測試最佳實踐。

Esta es una guía metodológica para el desarrollo guiado por pruebas que impone la escritura de casos de prueba antes de...

Flutter code quality: linting, DCM, analysis_options.yaml, static analysis. Use when setting up code standards or fixing...

FlutterアプリのE2Eテストとモバイル自動化の知見。Maestro、Mobile MCP、Dart MCPを使用したテスト作成・実行時に使用。

Flutter performance: DevTools profiling, widget optimization, memory management, const widgets. Use when optimizing rend...

Flutter/Dartプロジェクトの品質チェック。dart analyze/dart format/flutter testを実行。「Flutterの品質チェック」「Flutter テスト」「Flutterのテスト実行」「Flutter...

Generate high-quality Flutter tests for BLoC-based applications.

Flutter testing patterns with mocktail. Covers unit testing, widget testing, and BLoC/Cubit testing. Use when writing te...

Flutter testing patterns for Ballee mobile app. Covers unit tests, widget tests, golden tests, integration tests, and mo...

Comprehensive Flutter testing guidance covering unit tests, widget tests, and integration tests. Use when working with F...

Use when submitting or polling a FLUX 3 video API job. Also covers drafts, downloads, and technical validation.

Enforces that all new code, docs, and config match the existing codebase conventions, structure, and style — preventing...

Evaluate whether changes suggest new tests, modified tests, or new static analysis checks

Diagnose and repair selftest failures by running diagnostic commands and proposing fixes

Checks that the approved footage can actually do what each scene needs, using measured evidence only. Use before creatin...

The bar every automated test or guard must clear: green only when the real system works. Use when writing, fixing, or re...

Stack-agnostic test-driven development loop for a single Foreman issue. Implements one vertical slice with strict red-gr...

Break an approved PRD into small, dependency-ordered, vertically-sliced implementation issues written as local files in...

Headless self-verification gate a Foreman worker runs before it claims an issue is done. Re-run the real commands, read...

Headless end-to-end / web-app testing for the Foreman e2e stage. Derive end-to-end tests from the PRD's User Flows, driv...

LLM Council (FULL) — 5 independent advisors via the Agent tool, anonymous peer review, chairman synthesis with minority...

Use before calling work done: what would its user notice?

Forge: browser extensions (Chrome/Edge MV3): chrome extension, manifest v3, service worker, content script, permissions,...

Forge: full-stack apps — frontend + backend + database + auth: full-stack, SaaS, CRUD app, Postgres, Supabase, JWT, sess...

Bash/Shell scripting standards including shellcheck, shfmt, and bats testing. Use when working with shell scripts (.sh,...

Python development standards including pytest, ruff, black, and mypy. Use when working with Python files, tests, or depe...

Guide a first-time Forge builder through deploying a stock Rovo Agent, then turning it into Forge Guru, a documentation...

Phase 4 of the Forge pipeline. Summarize the whole workload — what was built, which Beads issues closed, a before/after,...

Standard test protocol for a new/changed Forge skill: activation-test (trigger vs near-miss phrases, target >=95%) + opt...

Use when writing or fixing tests: Playwright, Vitest, flaky (test faalt soms).