Angelo Huaraca
Community@ahuaracab
Angelo Huaraca maintains an MIT-licensed agentic QA skill registry covering test automation, performance, security, mobile, game, and LLM/RAG evaluation for coding assistants.
Agent Skills by Angelo Huaraca
Showing 31 vetted skills indexed across 1 GitHub repositories.
ahuaracabagentic-qa-core
Hosts shared QA doctrine references cited by agentic testing workflow skills.
ahuaracabperformance-testing
Run API, web, and mobile performance tests with K6, Gatling, JMeter, and Playwright.
ahuaracabprompt-evaluation
Evaluates and iteratively improves LLM prompts through rubric-based scoring against test datasets.
ahuaracabquality-metrics
Generates unified quality dashboards and ISTQB compliance audit reports from test execution metrics.
ahuaracabxray-cli
Manages Xray Cloud tests, executions, plans, and backups via the bun xray CLI.
ahuaracabrag-testing
Validates RAG pipelines across chunking, embeddings, retrieval, ranking, and answer generation layers.
ahuaracabagentic-qa-onboard
Guides new users through the Playwright + KATA QA boilerplate stack, pipeline, and setup.
ahuaracabadapt-framework
Adapts a KATA test boilerplate's auth, schemas, fixtures, CI, and MCP config to a discovered target project.
ahuaracabregression-testing
Executes CI regression suites, classifies failures, and produces GO/NO-GO release verdicts.
ahuaracabpr-review-lead
Reviews pull requests against KATA doctrine with evidence-grounded findings and calibrated severity scoring.
ahuaracabbug-screenshot-annotation
Annotates bug screenshots with circles, arrows, callouts, and badges rendered locally via HTML and Playwright.
ahuaracabgit-flow-master
Detects branching strategies and executes branch, commit, push, PR, and conflict-resolution workflows.
ahuaracabproject-discovery
Reverse-engineers an unknown codebase into PRD, SRS, glossary, and infrastructure context files.
ahuaracabjira-administration
Reconcile Jira project components and migrate Atlassian instances with approval-gated workflows.
ahuaracabtest-management
Orchestrate QA team capacity planning, execution monitoring, and issue triage per ISTQB CTAL-TM.
ahuaracabshift-left-testing
Refines backlog Story acceptance criteria and drafts pre-sprint ATP outlines in Jira.
ahuaracabacli
Automates Jira Cloud, Confluence Cloud, and org admin operations via the Atlassian CLI.
ahuaracabmobile-testing
Plan, automate, and review iOS, Android, and cross-platform mobile tests using XCTest, Espresso, and Detox.
ahuaracabsync-ai-context
Synchronize AI-critical repository documents against current project state and configuration.
ahuaracabtest-planning
Create ISTQB-compliant 10-section Test Plans with manual test cases for Jira, Azure DevOps, or Notion.
ahuaracabgame-testing
Plan, design, execute, and report game tests across mechanics, progression, multiplayer, AI, performance, and security.
ahuaracabframework-orientation
Explains the test-genesis QA framework and routes users to the correct skill.
ahuaracabsecurity-testing
Plan and execute security tests across OWASP web, API, mobile, and LLM domains.
ahuaracabgenai-testing
Evaluate LLM outputs for hallucinations, bias, instruction compliance, and OWASP security risks.
Frequently Asked Questions About Angelo Huaraca
FAQPage SchemaWhat tasks can I automate using Angelo Huaraca's skills?▼
You can automate E2E and API test authoring with Playwright + TypeScript under the KATA architecture, run CI regression suites with GO/NO-GO release decisions, execute K6/Gatling/JMeter performance tests, manage Xray test executions, annotate bug screenshots, and evaluate LLM prompts and RAG systems against OWASP and ISTQB standards.
Who are these QA skills designed for?▼
They target QA engineers, SDETs, QA leads, and test architects working in Jira-driven sprints. Personas include manual testers doing shift-left refinement, automation engineers writing KATA-compliant Playwright tests, performance engineers running load suites, and security testers applying OWASP Top 10 across web, API, mobile, and LLM surfaces.
How do the skills run in practice?▼
Skills load on demand inside compatible coding assistants (claude-code, copilot, cursor, codex, opencode) and trigger via slash commands or natural-language phrases. Execution flows through gated phases — analysis, explicit user approval, then writes — with integrations to Jira, Xray via `bun xray`, GitHub Actions, and six MCP servers including Playwright and Postman.
Are these skills open source and what do they cost?▼
Yes. Nearly all skills are MIT-licensed and free to use; the vendored judgment-day skill is Apache-2.0. There is no license cost, though usage requires a compatible AI coding assistant environment and any underlying services you connect, such as Jira Cloud, Xray Cloud, or CI runners.
What prerequisites and dependencies are required?▼
You need a compatible assistant (claude-code, copilot, cursor, codex, or opencode), a repo bootstrapped via the 4-phase setup path (foundation, Jira catalogs, project-discovery, Adapt-framework, git strategy), and runtime pieces like Playwright, bun for the Xray CLI, GitHub Actions for regression, and configured MCP servers and environment variables.