Requirement and testability review
Reviews a Jira or Linear ticket before implementation or QA begins, exposing ambiguity, contradiction, hidden dependencies, missing acceptance criteria, and untestable expectations.
Repository overview
A specification layer plus the files needed to maintain it
Every skill includes a full self-contained HTML overview, a platform-neutral SKILL.md, examples, and a structured report template. Shared policies and JSON schemas prevent each skill from inventing its own safety and evidence rules.
- 25
- detailed QA skills
- 6
- workflow collections
- 8
- phases in every skill
- 0
- runtime dependencies for docs
These files are workflow specifications. Production use still requires tool-enforced permissions, version-bound approvals, safe evidence storage, idempotent integrations, and repository validation.
Collection 1
Planning and scope
4 production-oriented QA workflow specifications.
Risk-based test plan generation
Creates a reviewable test plan from approved requirements, implementation context, and known risk, with explicit scope, required scenarios, evidence, data, and exit criteria.
Change-based regression scoping
Determines the smallest defensible regression set for a change by combining code impact, architecture, risk, historical failures, platform exposure, and operational behaviour.
Risk-based platform coverage matrix
Builds and maintains a defensible compatibility matrix across browsers, operating systems, devices, firmware, resolutions, roles, regions, and feature states.
Collection 2
Execution and product behaviour
8 production-oriented QA workflow specifications.
Controlled end-to-end feature QA
Turns a ticket and its implementation into a version-bound, evidence-backed QA run with explicit approvals, deterministic release rules, regression protection, publication, and cleanup.
Structured exploratory QA session
Runs a time-boxed exploratory session with a clear charter, controlled data, evidence, notes, coverage map, findings, and follow-up recommendations.
Fast release health verification
Runs a short, version-bound health check across the most critical user and system paths to decide whether deeper testing or rollout should continue.
Role, tenant, and object-permission QA
Validates authentication and authorisation across roles, tenants, ownership states, endpoints, operations, cached sessions, and direct-object access.
Contract, behaviour, and resilience API QA
Plans and executes API validation across contracts, authentication, authorisation, data integrity, errors, pagination, rate limits, idempotency, concurrency, and compatibility.
Application network-path investigation
Investigates connectivity failures across interfaces, DNS, proxy, TLS, firewall, redirects, private-network rules, endpoints, and application behaviour while protecting network and customer secrets.
Offline, cache, and reconnection QA
Validates startup, cached operation, interruption, reboot, clock changes, queued work, reconnection, synchronization, and long-offline limitations with explicit observation duration.
Media and content playback QA
Validates media startup, decoding, layout, looping, transitions, audio, synchronization, interruption, recovery, long-running stability, and platform-specific rendering.
Collection 3
Defects and verification
5 production-oriented QA workflow specifications.
Evidence-backed defect report
Converts an observed problem into a precise, reproducible, environment-bound defect report without overstating cause, severity, or scope.
Defect classification and prioritisation
Reviews an incoming issue and determines what it most likely represents, how severe it is, who should own it, what evidence is missing, and what action should happen next.
Defect fix verification
Determines whether a reported defect is fully fixed in the intended build and whether related behaviour remains safe across the agreed regression scope.
Customer issue reproduction
Transforms a support case into a privacy-safe, controlled reproduction plan that compares customer conditions with known-good conditions and returns a clear confidence-based outcome.
Flaky automated test diagnosis
Diagnoses inconsistent test results by separating product nondeterminism, automation defects, shared data, timing, infrastructure, environment, order, and concurrency effects.
Collection 4
Release and operations
3 production-oriented QA workflow specifications.
Release readiness and QA sign-off
Combines ticket-level results, open defects, platform coverage, rollout safeguards, monitoring, rollback readiness, and accepted risk into one auditable release recommendation.
Staged rollout health decision
Evaluates each rollout stage using version adoption, product health, device state, support signals, cohort comparison, and predefined rollback thresholds.
Production incident QA investigation
Provides a controlled QA workstream during an incident: reproducing impact, validating mitigations, comparing affected and healthy states, and preserving evidence without disrupting response ownership.
Collection 5
Automation and maintenance
2 production-oriented QA workflow specifications.
Automated test quality audit
Audits an automated test suite for correctness, reliability, isolation, maintainability, coverage value, security, runtime cost, and false-confidence patterns.
Manual test case quality review
Audits existing manual test cases for correctness, clarity, traceability, duplication, maintainability, execution value, automation suitability, and obsolete assumptions.
Collection 6
Communication and improvement
3 production-oriented QA workflow specifications.
Evidence-grounded daily QA summary
Produces a concise daily or stand-up update from verified work records without inventing progress, hiding blockers, or exposing restricted detail.
Continuation-ready QA handoff
Creates a precise handoff so another tester or team can continue from the correct build, state, evidence, and next action without repeating work or losing uncertainty.
Evidence-based QA retrospective
Reviews a completed release, incident, project, or testing cycle to identify escaped-risk patterns, process failures, effective controls, and owned preventive actions.
Start here
Choose one skill, read its boundaries, then implement the runtime controls.
The documentation is intentionally detailed enough for review, but no agent should be granted production access merely because a skill file describes safe behaviour.