From QA My App
Print a one-shot health + inventory snapshot of the QA catalog in this project — browser-agent install status, catalog framework/route/task counts, configured issue-tracker integrations, drift vs. source, and the most recent run's pass/fail/blocked totals. Read-only; never modifies the catalog. Use to verify an install or get your bearings before a run.
How this skill is triggered — by the user, by Claude, or both
Slash command
/qa-catalog:statusWhen to use
Use to confirm the plugin is wired up correctly, to see how many routes and tasks exist, to check whether the catalog has drifted from source, or to recall the last run's results without opening files. Trigger phrases include "qa status", "is qa set up", "catalog status", "show qa health", "how many tests", and "did the catalog drift".
This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
- Inventory: !`node "${CLAUDE_PLUGIN_ROOT}/scripts/status.mjs"`
node "${CLAUDE_PLUGIN_ROOT}/scripts/status.mjs"node "${CLAUDE_PLUGIN_ROOT}/scripts/catalog-diff.mjs" --notifyThis skill is read-only — it never writes to QA-tests/. Present the two snapshots above to the user as a concise status report, then suggest the single most relevant next command:
QA-tests/catalog.json is absent → recommend /qa-catalog:init.⚠ N route(s) drifted) → recommend /qa-catalog:sync.✗ <role>: … missing <ENV_VAR>) → tell the user to export that env var (or fill auth.local.json) before running that role's protected tasks./qa-catalog:run-all (or /qa-catalog:run <task> for a single task).Do not spawn subagents and do not run a browser. Keep the report to what the two snapshot commands returned.
npx claudepluginhub elwizard33/qa-my-app --plugin qa-catalogCreates bite-sized, testable implementation plans from specs or requirements, with file structure and task decomposition. Activates before coding multi-step tasks.