Command
Build a Requirement Traceability Matrix (RTM) — link each requirement to its test cases and bugs, then surface coverage gaps (Gap / No-test / Partial / Covered). Reads the analyze-spec output (requirements), the feature xlsx / plan (test cases), and the Lark board (bugs) — read-only. Writes results/ /traceability.md.…
Command
Triage a list of bugs/incidents — classify Severity (P1–P4) + Type, score each by RICE for an objective processing order, derive SLA deadlines, analyze cross-feature impact + regression scope from the sitemap, and emit an ordered action plan. Reads a sheet/file/pasted list or the Lark board (read-only). Writes…
Command
Install-helper for the local UI-vision engine used by /qa:exploratory-ui — creates a dedicated Python venv under .claude/qa-claude/ui-engine/ and installs the CV stack (opencv-python-headless + scikit-image + Pillow + imagehash + numpy), then writes the engine config (interpreter path + comparison thresholds).…
Command
Add/switch the active Lark bug board and refresh field/option/dev-pic mappings in .claude/qa-claude/log-bug.config.yml from a board URL or alias (so /qa:log-bug knows where to write).
Skill Claude CodeCodex
Reusable logic to deep-analyze a bug/ticket board (ANY board by URL) over a time range. Reads every record via scripts/larkbitable.py --url (range-filtered by createdtime), ADAPTIVELY classifies the board's own status names into readiness groups (not-ready-to-test = New/Rework/Reopen/Fixing/DevDone-style vs…
Skill Claude CodeCodex
Import bugs from an exploratory report (results/ /dev-bug-report-.md, produced by /qa:exploratory) into Lark Bitable. Resolve & parse the report into structured bug drafts, map report fields → board fields (title→Name, Màn→Feature, Hiện tượng+steps+Actual→Input/Action, Kỳ vọng→Expected, severity 🔴/🟡/ℹ️→Priority…
Skill Claude CodeCodex
Reusable logic acting as a "green gate" — clean compile/build (auto-detects the project's build system) and (optionally) a quick run of the just-touched feature's tests. Use before finishing cook/fix/exploratory and before committing in push-code/merge-request. Do not raise timeouts / add workarounds just to "pass the…
Skill Claude CodeCodex
Reusable logic to check for a duplicate bug on the Lark Bitable board before logging a new one. Parses free text or a structured payload (name/feature/platform/keywords...), extracts 2–3 meaningful keywords, searches the board via scripts/larkbitable.py --search, drops closed records + keyword-only false positives…
Skill Claude CodeCodex
Reusable logic to commit & push safely — never push directly to main/master (auto-creates a feat/ branch), commit per Conventional Commits with a Co-Authored-By trailer, push -u without force. Used by push-code and merge-request after the code is clean + build is green. Runs only when the user requests it.
Skill Claude CodeCodex
Engine that writes mobile test code (Appium Java + TestNG + POM), used by the cook command when the platform is android/ios. Covers 3-layer element lookup, Screen declaration (via the declare-screen skill), writing atomic/flow Tests, TestNG XML (GoToHomeTest first), Utils.passCap/failCap with the [APP-BUG] triage…
Skill Claude CodeCodex
Reusable logic to write/maintain a Playwright Java Page Object (Screen) + Tests class + smoke/regression runner following the 3-layer POM, with correct locator priority and isDisplayed(), and NO assert in the Screen. Used by the cook/plan-tests command (creating a new feature or extending one). Hooks the missing-ids…