Agentic Qa Core

Agentic QA Core — Foundation reference host

agentic-qa-core is the shared reference library that every workflow skill in this repo cites. It exists so doctrine (briefing template, dispatch patterns, orchestration rules, skill composition tiers) lives in one place instead of being duplicated across every SKILL.md.

Loading a workflow skill (e.g. shift-left-testing, sprint-testing, test-automation) implies loading the relevant agentic-qa-core/references/*.md on demand — workflow skills declare a ## Dependencies block at the top so the AI knows what to pull in.

This skill does NOT orchestrate workflows, does NOT generate files, and does NOT bootstrap a target repo. The entire framework (skills, foundation files, scripts) ships together as one repo; à la carte adoption is not supported — see "Install model" below.

---

References hosted

| File | Cited by | Purpose | |------|----------|---------| | references/test-design-doctrine.md | shift-left-testing, sprint-testing, test-documentation, test-automation | Canonical doctrine for deriving test cases / ATCs from acceptance criteria: the 5 principles (AC-verify ≠ testing; AC = floor not ceiling; criterion-vs-test-case; 1:N explode-default/justify-collapse; risk-outside-criterion), the redefined coverage model, and the formal techniques (EP, BVA, State-Transition, Decision Tables, Pairwise, Error Guessing, Risk-based) with binding triggers + the Test-Design Checklist gate. | | references/briefing-template.md | shift-left-testing, sprint-testing, test-documentation, test-automation, regression-testing, project-discovery | The 7-component subagent briefing template, with concrete filled examples per dispatch pattern. | | references/dispatch-patterns.md | All workflow skills with a "Subagent Dispatch Strategy" section | Decision table + heuristic for picking Single / Sequential / Parallel / Background. | | references/stage-gates.md | All workflow skills (shift-left-testing, sprint-testing, test-documentation, test-automation, regression-testing) | Definition-of-Done checklist per workflow stage. The orchestrator verifies each stage's DoD (planning stages include the Test-Design Checklist) before appending the progress checkpoint and advancing — turns the prose doctrine into an enforced gate. | | references/orchestration-doctrine.md | Subagents that need orchestration rules without pulling the whole CLAUDE.md | Cacheable mirror of CLAUDE.md §"Orchestration Mode (Subagent Strategy)". | | references/skill-composition-strategy.md | framework-development, every workflow skill | T1-T4 tier model + SDD boundary + composition contract. | | references/skill-resolver.md | Skills that resolve composable skills at runtime via the registry | Skill Resolver Protocol used by sub-agent launches. Companion: scripts/build-skill-registry.ts → .claude/skills/REGISTRY.md. | | references/preflight-gate.md | shift-left-testing, sprint-testing, test-documentation, test-automation, regression-testing, framework-development | Readiness Preflight Gate doctrine — probe tools/MCPs/CLIs/credentials and surface a user checklist BEFORE a skill starts its real work. Owns the secret/token handling + OpenAPI api-login → RESTART flow. | | references/adr-doctrine.md | project-discovery, framework-development, sprint-testing, test-automation | When a test-architecture decision earns an ADR (two-gate test: architectural AND hard-to-reverse) + the detect → draft → record procedure. Test architecture = runner/framework choice, Page-Object vs Screenplay, fixture/data strategy, isolation & parallelization, auth-in-tests, selector contract, exploratory-vs-scripted boundary, reporting/CI sharding, flake-retry policy. |

When a skill cites one of these, it includes a Dependencies block at the top so the AI knows to load agentic-qa-core before continuing.

---

The Naming Codex (visual reference deck)

agentic-qa-core hosts the canonical naming-conventions presentation — a self-contained, dark-themed html-ppt deck that documents every test-artifact title format across the seven layers (CASE · GROUP · CONTAINER · CODE · JIRA · GIT · FILESYSTEM), plus a coverage audit of the open naming gaps.

| File | Language | |------|----------| | naming-conventions.html | English | | naming-conventions.es.html | Spanish |

It is the human-facing mirror of the naming rules that live in prose across the workflow skills' references/*.md (TC titles, @atc decorator, describe()/Test Set grouping, KATA components, tags, branch/commit/PR shapes, the PBI tree). Open it in a browser (arrow keys navigate; O = overview; F = fullscreen). Offer to open it when a user asks how artifacts are named or wants to review the conventions visually.

Keep it canonical: when a naming rule changes, edit the owning skill's references/*.md, regenerate REGISTRY.md (bun run skills:registry), then refresh BOTH decks so the codex never drifts from the prose source.

---

Dependency declaration for downstream skills

Every workflow skill that cites agentic-qa-core/references/*.md should declare it explicitly so the AI knows what to load on demand. Example block to add near the top of the skill's SKILL.md:

## Dependencies
Requires `agentic-qa-core`. Loads on demand:
- agentic-qa-core/references/briefing-template.md
- agentic-qa-core/references/dispatch-patterns.md

The block is documentation — the AI reads it and pulls the cited files. There is no automated wiring: skills are markdown, not code.

---

Install model

This boilerplate is designed to be cloned in full. The workflow skills under .claude/skills/ depend on foundation files that live at the repo root (CLAUDE.md, .agents/, scripts/, package.json, tests/) and on shared references under agentic-qa-core/references/. Installing only a subset of skills (e.g. copying one skill directory in isolation) leaves those skills without their dependencies and they will not function.

If a downstream user has only the skills and not the rest of the repo, the supported path is to clone the full boilerplate repository and integrate it as a single unit. No per-skill scaffolding action is provided by this skill — the skill set is intentionally inseparable from the foundation.

---

Out of scope

agentic-qa-core does not:

• Create or modify any files. It is a passive reference library.
• Create or modify .context/ files (that belongs to /project-discovery).
• Generate or scaffold tests, fixtures, or KATA components (that belongs to /adapt-framework and /test-automation).
• Adapt the framework to a specific stack (that belongs to /adapt-framework).
• Sync AI-critical documents or project-specific facts in CLAUDE.md (that belongs to /sync-ai-memory).
• Sync OpenAPI / API schemas (that's bun run api:sync).

For framework evolution (changes to KATA bases, fixtures, cli/, scripts/, api/schemas/ pipeline), see /framework-development.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: upex-galaxy
• Source: upex-galaxy/agentic-qa-boilerplate
• License: MIT

Install and usage instructions live in the source repository linked above.