Search everything...

Stats

Actions

Available In

traxxall-delivery-qa

Traxxall blind, adversarial QA skill set — deliberately isolated from implementation. From the acceptance criteria + the running TEST app ONLY (never the diff, PR, product source, or dev-side tests), authors adversarial Playwright suites covering happy/edge/negative/abuse/cross-module cases with role/text locators, deterministic waits (no hard sleeps), storageState auth, and trace/screenshot/video on failure; records PASS/FAIL/ERROR for the PH QA / Ready-to-Test flow. Refuses any leaked implementation context (isolation gate). Targets TEST only, never prod.

Publisher marketplacetraxxall-delivery-qa@personal-skills · marketplace and plugin share one repository (skobyn/upskill-me)

npx claudepluginhub skobyn/upskill-me --plugin traxxall-delivery-qa

Popularity

Stars

Med: 0·Avg: 488

Copy clicks

Med: 0·Avg: 1

What's Inside

Slash Commands2

qa-author

/qa-author

Authors an adversarial Playwright test suite from an acceptance criterion, without executing it against TEST. Enforces the isolation gate, runs the spec-reader → test-author → adversarial-critic loop-until-dry sequence, and returns the suite and JSON envelope with all results at NOT_RUN.

qa-run

/qa-run

Executes a previously authored Playwright QA suite against the Traxxall TEST environment. Records PASS/FAIL/ERROR per case, captures screenshots and traces on failure, and posts results to the ADO QA child ticket. Never hangs — records ERROR on timeout and moves on.

Agents1

qa-panel-agent

/qa-panel-agent

Autonomous blind adversarial QA panel for Traxxall delivery. Accepts an acceptance criterion and the TEST environment URL, enforces physical context isolation (refusing diffs and source), sequences spec-reader → test-author → adversarial-critic loop-until-dry → executor, and returns a fully populated PASS/FAIL/ERROR envelope shaped for the ADO QA child ticket.

Skills5

qa-adversarial-critic

/qa-adversarial-critic

Loops adversarially over a drafted test suite, hunting boundary conditions, invalid inputs, permission boundaries, and cross-module side-effects that the acceptance criterion implies but does not state. Terminates after two consecutive passes that produce zero new cases. Never reads product source or diffs.

qa-executor

/qa-executor

Executes the adversarially-reviewed Playwright suite against the Traxxall TEST environment via Playwright MCP tools. Records PASS, FAIL, or ERROR per test case — ERROR-not-hang on timeout — and shapes results for posting to the ADO QA child ticket.

qa-spec-reader

/qa-spec-reader

Parses an acceptance criterion into a structured list of atomic, observable, surface-tagged testable claims. Operates exclusively from the acceptance criterion text; never reads source code, diffs, or author-side artefacts.

qa-test-author

/qa-test-author

Authors a Playwright TypeScript test suite from the structured claim list produced by qa-spec-reader. Drives the running TEST application via Playwright MCP to discover locators and UI flows. Follows strict locator, wait, fixture, and page-object conventions. Never reads product source code or diffs.

traxxall-delivery-qa

/traxxall-delivery-qa

Primary orchestrator for the blind adversarial QA panel. Enforces the isolation gate — refusing diffs, PRs, and source access — then sequences spec-reader, test-author, adversarial-critic (loop-until-dry), and executor to produce a uniform PASS/FAIL/ERROR envelope shaped for the ADO QA child ticket.

Stats

Version0.1.0

LanguageJavaScript

Stars0

MaintenanceGood

Last CommitJul 2, 2026

AddedJul 3, 2026

Actions

View on GitHub View README Plugin Marketplace JSON

Own this plugin?

Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).

Available In

personal-skills

More by Skobyn

peer-review-prep

0·

Use when a tech lead, senior developer, or author needs a structured prep briefing before a live synchronous peer code review — given a diff or codebase path, produces intent narrative, correctness questions, design-fit observations, advisory security/standards/performance findings, a verdict suggestion, and a re-review action-item checklist. Read-only; never writes code or mutates anything.

v0.1.0

Skobyn

traxxall-delivery

0·

Traxxall author-side delivery skill set. Pull/analyze ADO work items into structured intake briefs (flagging Requires-Specification when under-specified), author implementation specs with blind-QA-ready acceptance criteria, draft/create PBIs and child dev Tasks with compliant users/{short}/{WI#}-… branches, and outline UnitTests.Core/TransactionScope dev tests — all under Traxxall conventions (branch/PR rules incl. VS403660, PBI/Bug/Task model, area Traxxall Solution, AI tags, dual-framework legacy vs modern, egress-safe dev.azure.com auth). Drafts by default; creates ADO items only on explicit go. Never authors QA tests (separate traxxall-delivery-qa plugin) and never runs destructive test projects.

v0.1.0

Skobyn

memory-mirror-harness

0·

A 'Memory and a Mirror' agentic harness for long-running unattended coding sessions: a prunable structured learnings file read at session start, a proof-discipline gate that blocks 'done' claims without fresh cited evidence, and a fresh-context reviewer subagent that returns only a gap list against spec. Chains into one plan -> act -> prove -> review -> remember loop via /mirror-loop. Model-agnostic by construction.

v0.1.0

Skobyn

architecture-viewer

0·

Reviews a target repository and produces two grounded board-review deliverables: a self-contained JSSI-branded interactive HTML viewer (16 diagram tabs, built by editing a copy of the approved reference template verbatim) and docs/architecture/index.md (narrative plus two strictly separate tables — Findings for code-level gaps, Open Decisions for architecture choices needing a human ruling). Supports a silent/autonomous generation mode and a distinct post-complete interview mode that walks a reviewer through Open Decisions one row at a time.

v0.1.0

Skobyn

talon

0·

71-skill bug-hunting & external red-team bundle for Claude Code — 48 hunt-* web/vuln-class + framework skills, enterprise platform attack chains (M365/Entra, Okta, SharePoint, vCenter, SSL-VPN, APK), recon/OSINT, reporting & validation gates, and Burp MCP integration. Skills auto-load by topic; 15 slash commands included.

v2.1.0

Skobyn

traxxall-delivery-qa

Popularity

What's Inside

Confidence

Similar Plugins

fullstack-dev-skills

feature-dev

ecc

prompts.chat

claude-council

claude-code-toolkit

More by Skobyn

peer-review-prep

traxxall-delivery

memory-mirror-harness

architecture-viewer

talon

Popularity

Health & Quality

More by Skobyn

peer-review-prep

traxxall-delivery

memory-mirror-harness

architecture-viewer

talon

Similar Plugins

fullstack-dev-skills

feature-dev

ecc

prompts.chat

claude-council

claude-code-toolkit