npx agentspec-cli install 859c2cf4-34fb-4ad6-839c-373b62304f0f --framework ClaudeCode→ .claude/skills/qa/SKILL.md
# QA Verification Harness Run the appropriate verification tier based on `$ARGUMENTS`. If `$ARGUMENTS` is empty, run **standard**. --- ## Tier 1 — quick Minimum check. Run from the repository root — do NOT `cd` into subdirectories, because this is a Pub Workspaces project and `fvm dart analyze` at the root inspects all packages in one pass. ```bash fvm dart analyze ``` Expected output: `No issues found!` If issues are found, fix them and re-run before proceeding. --- ## Tier 2 — standard (default when $ARGUMENTS is empty) Pre-PR baseline. Run all three steps in sequence; stop and fix before continuing if any step fails. ```bash # Step 1 — static analysis across all packages fvm dart analyze # Step 2 — format check (read-only, does NOT modify files) fvm dart run melos run format:ci --no-select ``` Expected output for each: `No issues found!` (analyze) or a clean exit (format:ci). If `format:ci` reports a diff, fix formatting with: ```bash fvm dart format packages/ ``` Then re-run `fvm dart run melos run format:ci --no-select` to confirm the diff is gone. --- ## Tier 3 — full Heavy verification including tests. Run standard first, then add: ```bash # All packages fvm dart run melos run test:ci --no-select # Or, for a specific package only fvm dart run melos exec --scope=<package_name> -- flutter test ``` All tests must pass. Do not declare the task complete while any test is red. --- ## Code-generation prerequisite If the change touches any of the following, run `fvm dart run melos run gen` **before** running any QA tier: - Riverpod providers annotated with `@riverpod` - Drift database table definitions - i18n YAML files (`app_en.yaml` / `app_ja.yaml`) - Freezed data classes ```bash fvm dart run melos run gen ``` For i18n changes only: ```bash fvm dart run melos run slang ``` --- ## Completion criteria Do NOT declare the task complete until **all** of the following are true for the chosen tier: - `fvm dart analyze` → `No issues found!` - `fvm dart run melos run format:ci --no-select` → clean (standard / full) - `fvm dart run melos run test:ci --no-select` → all tests pass (full only)
Built on the Agent Skills standard
qa
Verify that code changes are correct, safe, and ready to ship. Use this skill after implementing changes, before pushing or creating a PR. Also use when the user says "check", "verify", "review", "QA", "is this ready", or when you want to validate work done by the developer skill. Runs build, lint, and structural checks.
by AgentHub Crawler
Building and running
Before submitting any changes, it is crucial to validate them by running the full preflight check. This command will build the repository, run all tests, check for type errors, and lint the code. To run the full suite of checks, execute the following command:
by AgentHub Crawler
qa
Run automated QA checks on Grafema VS Code extension via Playwright + MCP cross-validation. Use when: (1) user says "/qa" to start or resume QA session, (2) user wants to validate extension panels against graph data, (3) user wants to re-check previously found bugs after a fix, (4) user wants to run a custom QA task. Requires Docker code-server running.
Sign in to leave a comment.
by AgentHub Crawler