common-architecture-di…
Draw architecture diagrams as editable draw.io files with a fixed house style, C4 levels, and evidence-tagged shapes. Use when producing a system context,…
Turn acceptance criteria into an executable test plan (scenarios, seed, selector gaps) before generating E2E code. Use when ACs exist but no runnable test plan does yet.
$ npx -y skills add hoangnguyen0403/agent-skills-standard --skill quality-engineering-test-plan-authoring --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/quality-engineering-test-plan-authoringContext preview
The summary Claude sees to decide when to auto-load this skill.
Turn acceptance criteria into an executable test plan (scenarios, seed, selector gaps) before generating E2E code. Use when ACs exist but no runnable test plan does yet.
name: quality-engineering-test-plan-authoring
description: Turn acceptance criteria into an executable test plan (scenarios, seed, selector gaps) before generating E2E code. Use when ACs exist but no runnable test plan does yet.
guardrail: true
metadata:
triggers:
files:
- "specs/**/*.md"
- "tests/seed.spec.*"
keywords:
- test plan
- executable test plan
- seed spec
- scenario matrix
- ac to scenario
- planner`AC-*` IDs and SRS lanes (unit/integration/E2E-web/E2E-mobile/API) from the approved PRD/SRS. Never derive scenarios from reading the code — code shows what exists, not what the acceptance criteria require.
`docs/srs/test-plan-[slug].md` (and `specs/[slug].md` once Playwright Test Agents are initialised on the target repo). Each scenario block: `Steps`, `Expected`, `@AC-n` tag, `priority`, exactly one `lane` (web|ios|android|api). One scenario covers one AC condition — do not fold multiple conditions into one scenario.
`tests/seed.spec.ts` (or platform equivalent) carries only shared prerequisites: auth and navigation to the starting screen. No assertions.
`Selector Gaps` (elements the plan needs that have no stable id yet — feeds `specialist-testid-inserter`) and `Data & Reset` (fixtures needed, how state resets between scenarios). Gaps must follow the `<screen>-<element>-<role>` naming convention defined in `quality-engineering-selector-stability`.
Each AC condition expands to `P` (positive), `N` (negative: a stated condition violated), and `E` (edge: boundary of a stated condition). Classes must differ by precondition or input, never by phrasing. Every `Expected` cites its AC or business rule, or is tagged `ASSUMED` and surfaced under an `Assumed Results` header. On a HALT trigger (ultra-short AC, no expected behavior, bundled ACs, contradiction, undefined state) stop and ask; return `HALT: <trigger>` in autonomous mode.
Manual Zephyr TCs stay the system of record for business sign-off (`quality-engineering-zephyr-test-generation`); this skill's scenarios carry a bidirectional TC-key reference where one exists, and are additive, not a replacement.
The portable SDLC standards layer for AI coding agents. Sync once, then work in your own runtime.
Repo: hoangnguyen0403/agent-skills-standard
Draw architecture diagrams as editable draw.io files with a fixed house style, C4 levels, and evidence-tagged shapes. Use when producing a system context,…
Enforce SOLID principles, guard-clause style, function size limits, and intention-revealing naming across all languages. Use when refactoring for readability,…
Standardize BRD and BRD-lite discovery for business goals, stakeholder impact, current-to-future state, and measurable value outcomes. Use when creating BRD,…
Conduct high-quality, persona-driven code reviews. Use when reviewing PRs, critiquing code quality, or analyzing changes for team feedback.
Maximize context window efficiency, reduce latency, and prevent lost-in-middle issues through strategic masking and compaction. Use when token budgets are…
Standardize dynamic application security testing for backend APIs, frontend web apps, and mobile clients. Covers ZAP, Nuclei, Nikto, sqlmap, ffuf, browser…