From armory
Conducts gate-oriented safety audit on code changes before landing using two-pass checklist triage for critical risks like SQL safety, race conditions, and trust boundaries.
npx claudepluginhub mathews-tom/armory --plugin armoryThis skill uses the workspace's default tool permissions.
Gate-oriented safety audit for code changes before landing. Uses a structured checklist with two-pass severity triage and blocking/non-blocking classification.
Implements Playwright E2E testing patterns: Page Object Model, test organization, configuration, reporters, artifacts, and CI/CD integration for stable suites.
Guides Next.js 16+ Turbopack for faster dev via incremental bundling, FS caching, and HMR; covers webpack comparison, bundle analysis, and production builds.
Discovers and evaluates Laravel packages via LaraPlugins.io MCP. Searches by keyword/feature, filters by health score, Laravel/PHP compatibility; fetches details, metrics, and version history.
Gate-oriented safety audit for code changes before landing. Uses a structured checklist with two-pass severity triage and blocking/non-blocking classification.
Distinct from pr-review: pr-review is a multi-dimension code quality review. This skill is a gate-oriented safety audit — it uses an external checklist with two-pass severity triage and a blocking/non-blocking classification.
Native alternative: Claude Code's
/ultrareviewruns a dedicated native review session optimized for bug-finding (Anthropic ships three free per month on Pro/Max plans at Opus 4.7's launch). Use this skill for checklist-driven, gate-oriented blocking classification with a documented triage protocol; use/ultrareviewfor lightweight bug-hunting on a single change.
Identify the changes to review:
git symbolic-ref refs/remotes/origin/HEAD)Read references/checklist.md. This is mandatory — if the checklist is unreadable, STOP and report the error.
Review the diff against critical safety categories. These are potential ship-blockers.
For each CRITICAL finding:
AskUserQuestion with exactly three options: Fix now / Acknowledge risk / False positiveReview against remaining categories:
Conditional Side Effects — side effects hidden in conditional branches, callbacks triggered by state changes, error handlers silently swallowing failures.
Magic Numbers — unexplained numeric literals, hardcoded thresholds without constants, timeout values without rationale.
Dead Code — unreachable branches, unused imports, commented-out code without explanation.
Test Gaps — new code paths without test coverage, modified behavior without updated tests, missing edge case and error path tests.
Crypto & Entropy — weak random sources for security contexts, hardcoded secrets, missing TLS/encryption for sensitive data in transit.
Time Window Safety — timezone-naive comparisons, daylight saving edge cases, cron expressions not accounting for clock skew.
Type Coercion — implicit type conversions that could lose data, numeric precision loss across boundaries, implicit string encoding at I/O boundaries.
Present all informational findings in a single summary table (file, line, category, description).
Do NOT flag:
Gate verdict (CLEAR TO LAND / BLOCKED), critical issues summary with resolution status, informational findings table.
This skill is read-only by default — only modifies code when user explicitly chooses "Fix now" on a critical issue.