Interactive, human-in-the-loop QA walkthroughs of finished functionality — drives a browser, an API, and a CLI against a ticket's acceptance criteria and its merged PR, with an adversarial critic pass on both the behavior spec and the step plan, drafter/critic revision rounds, and a report with embedded screenshots. Not automated test-code authoring; that's what the testing plugin is for
Plugin agentic-qa from marketplace bobtat-plugins in bobtat/claude-plugins. Commands read from the repo's manifest — today.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
agentic-qaThis skill should be used whenever running or invoking a live QA walkthrough — e.g. "walk through ticket ABC-123", "verify this PR works end to end against staging" — via the interactive /agentic-qa:walkthrough command, an agent-invoked run through agentic-qa:qa-runner, or a direct Skill call. Carri
behavior-coverageUse when turning a validated ticket into a behavior spec for a live walkthrough — spawning agentic-qa:behavior-extractor to draft it and agentic-qa:behavior-coverage-critic to review it, with the orchestrator relaying each round. Governs the grounding split between what the acceptance criteria asked
qa-reportingUse when building the walkthrough report — spawning agentic-qa:qa-reporter just before agentic-qa:step-executor to write a live, incrementally-updated report and render the finished, self-contained HTML deliverable at finalization. Governs the report template, the Traceability table, the report-dest
step-executionUse when running an approved step plan against a live system — spawning agentic-qa:step-executor to drive the browser, API, and CLI. Governs the five verdicts (pass/fail/blocked/skipped/not verified), which evidence is required by surface, the choice between the claude-in-chrome and playwright brows
step-planningUse when turning a resolved behavior spec into an ordered, executable step plan — spawning agentic-qa:step-planner to draft it and agentic-qa:step-plan-critic to review it, with the orchestrator relaying each round. Governs surface selection (browser vs. API vs. CLI), the reversibility and containme
/agentic-qa:walkthroughWalk through a finished feature or fix — a ticket and its merged PR — against a live browser, API, and CLI, with a human decision before anything irreversible runs
behavior-coverage-criticAdversarially reviews a draft behavior spec against the PR diff — arguing for affected-but-unstated behaviors and auditing the drafter's own doc-grounded citations. Returns findings for the orchestrator to relay to behavior-extractor, and may be resumed for a second round. Spawned by /agentic-qa:wal
behavior-extractorDrafts behavior-spec.md from a validated ticket, following testing:behavior-extraction — reasoning from acceptance criteria and given docs, never from code. Revises against behavior-coverage-critic's findings when the orchestrator resumes it with them. Spawned by /agentic-qa:walkthrough; expects an
qa-reporterWrites the live walkthrough-report.md incrementally as step-executor completes steps, then renders the self-contained walkthrough-report.html deliverable at finalization with browser screenshots embedded. Spawned by /agentic-qa:walkthrough just before step-executor, not after it, and resumed by mess
qa-runnerSelf-contained agent-invoked entry point for a walkthrough — takes a brief instead of asking questions, runs the full six-phase pipeline itself, and returns the finished report or pauses per the escalation mechanism. Use when another agent needs to run agentic-qa unattended and doesn't hold the tool
step-executorRuns an approved step plan against the live system — browser, API, and CLI — one step at a time. Records each result to step-results.md and nudges qa-reporter by agent ID as it completes; returns to the orchestrator to escalate anything only a human can resolve, and is resumed with the answer. Spawn
step-plan-criticAdversarially reviews a draft step plan — traceability completeness, surface-choice fit, and grounded reversibility/containment calls. Returns findings for the orchestrator to relay to step-planner, and may be resumed for a second round. Spawned by /agentic-qa:walkthrough; expects absolute paths to
step-plannerDrafts step-plan.md from a resolved behavior spec — choosing browser/API/CLI per behavior, classifying reversibility and containment, marking blocked/cascading steps. Revises against step-plan-critic's findings when the orchestrator resumes it with them. Spawned by /agentic-qa:walkthrough; expects a
playwrightruns: npx -y @playwright/[email protected] --caps=testing,storage --output-dir ${CLAUDE_PLUGIN_DATA}/playwright-output
node "${CLAUDE_PLUGIN_ROOT}/hooks/target-guard.mjs"
Teaches Claude to write, review, and audit tests worth having — behavior-focused design, disciplined test doubles, browser and component testing, a plan-gated pipeline that turns a ticket or PR into tests of the described behavior, a check on whether pushed code still matches the description that specified it, and a repo-scale map of where test protection is weakest
7 skills · 4 commands · 5 agents
Teaches Claude to build the evidence record a performance review needs before the evidence is gone — a session hook that distils each transcript into a redacted digest of your own prompts before Claude Code's 30-day purge deletes it, keeping the decisions and discarding the tool output where the secrets live; a sweep that reconciles git, PR, and review history against the journal and interviews the gaps; and authoring that turns dated entries into a review, a promotion case, or resume bullets without inventing a number
4 skills · 5 commands · 1 agent · hooks
Teaches Claude to model and check jewelry in Blender with the JewelCraft add-on over a Blender MCP connection — prong grip, seat clearance and stone overlaps measured rather than eyeballed, ring sizes read from the band's actual inner surface, metal weight with overlapping parts counted once, print/cast checks that confirm an STL comes out in millimetres, and metalwork built from editable paths fused with Geometry Nodes, split into a cast part and a hand-built wire head with a 1:1 bending template, with the add-on's scripting traps documented and worked around
11 skills
Teaches Claude to treat version control as a deliverable — atomic conventional commits split from a working tree, branch history made legible without interactive rebase, and pull requests that describe the change rather than the diff, with hooks that route version-control requests to it and block the irreversible mistakes
3 skills · 3 commands · 1 agent · hooks
Teaches Claude to edit its own prose — the catalog of tells that mark machine-written text, the clarity moves that rebuild a sentence around its real subject and verb, and the never-invent rules that keep an edit from becoming a rewrite, with a command that runs an edit pass over a draft and an agent that reads a finished document cold
2 skills · 2 commands · 1 agent
Adversarial review of a PR, plan or document by an isolated reviewer that never sees the author's context, with a triage pane deciding which findings reach the author
1 MCP server
Install the "AAS QA & Test Automation" editorial skill bundle for Claude Code.
14 skills
Web scraping, Google search, structured data extraction, and MCP server integration powered by Bright Data. Includes 7 skills: scrape any webpage as markdown (with bot detection/CAPTCHA bypass), search Google with structured JSON results, extract data from 40+ websites (Amazon, LinkedIn, Instagram, TikTok, YouTube, and more), orchestrate Bright Data's 60+ MCP tools, built-in best practices for Web Unlocker, SERP API, Web Scraper API, and Browser API, Python SDK best practices for the brightda...
21 skills
Your AI development teammate. Turns a story file into a shipped, reviewed, and tested feature via orchestrator → architect → developer → PR reviewer → QA → Playwright.
1 skill · 2 commands · 6 agents
Web scraping, Google search, structured data extraction, and MCP server integration powered by Bright Data. Includes 7 skills: scrape any webpage as markdown (with bot detection/CAPTCHA bypass), search Google with structured JSON results, extract data from 40+ websites (Amazon, LinkedIn, Instagram, TikTok, YouTube, and more), orchestrate Bright Data's 60+ MCP tools, built-in best practices for Web Unlocker, SERP API, Web Scraper API, and Browser API, Python SDK best practices for the brightda...
21 skills
45 advanced engineering skills: agent designer, agent workflow designer, RAG architect, database designer + schema designer + SQL assistant, migration architect, observability designer, dependency auditor, changelog generator, API design reviewer, API test suite builder, CI/CD pipeline builder, MCP server builder, skill security auditor, skill tester, performance profiler, focused-fix, browser-automation, full-page-screenshot, git-worktree-manager, monorepo-navigator, codebase-onboarding, interview-system-designer, runbook-generator, spec-driven-workflow, secrets-vault-manager, env-secrets-manager, pr-review-expert, self-eval, tc-tracker, feature-flags-architect, kubernetes-operator, chaos-engineering, ship-gate, slo-architect (error-budget + multi-window burn-rate alerts per Google SRE Workbook), tech-debt-tracker, agent-regression-evals, coding-agent-rollout, commit-craft, agent-run-forensics and i18n-localization. Agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw.
48 skills · hooks
Testing, security, and code quality experts - code review, penetration testing, QA automation
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.