AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Quality

skill-igmarin-rails-agent-skills-quality · by igmarin

>

No reviews yet
0 installs
37 views
0.0% view→install

Install

$ agentstack add skill-igmarin-rails-agent-skills-quality

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-igmarin-rails-agent-skills-quality)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Quality? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Quality Persona

Orchestrates systematic code quality checks, safe refactoring, and documentation updates across three phases. Use this instead of individual refactoring or documentation skills when full production-readiness is required end-to-end. If unsure which skill applies, use skill-router.

Complexity Thresholds

| Metric | Threshold | Action | |---|---|---| | Cyclomatic Complexity | > 10 | Extract method | | Method Length | > 20 lines | Extract method | | Parameter Count | > 4 | Parameter object | | Nesting Depth | > 3 levels | Extract method | | Duplication | > 3 similar blocks | DRY violation | | Class Length | > 300 lines | Extract class |

Agent Phases

Phase 1: Conventions Review

Check code against Rails standards via skills/code-quality/apply-code-conventions (DRY/YAGNI/PORO/CoC/KISS compliance, linter as style source of truth, structured logging) and skills/code-quality/apply-stack-conventions (Rails + PostgreSQL patterns, Hotwire + Tailwind conventions, security best practices).

Key file patterns to review: app/controllers, app/models, app/services, app/jobs, spec/.

Tool Integration:

# Complexity and duplication
bundle exec rubocop --only Metrics/CyclomaticComplexity,Metrics/MethodLength,Metrics/ParameterLists,Metrics/AbcSize,Metrics/PerceivedComplexity

# Security
bundle exec brakeman --no-pager
bundle exec bundle-audit check --update

Phase 2: Refactoring (Optional)

Decision Gate — Proceed if any threshold from the table above is exceeded; otherwise skip to Phase 3.

If refactoring is needed, follow TDD discipline:

TDD Enforcement for Refactoring

Before any code change:

  1. testing/plan-tests — Choose the best characterization test to document current behavior
  2. testing/write-tests — Write characterization test and verify it PASSES (documents current behavior)
  3. Refactoring Checkpoint — Propose specific refactoring (e.g., "Extract calculate_discount method to DiscountCalculator class")
  4. User Approval — Wait for explicit confirmation
  5. Implement Refactoring — Make the structural change only
  6. Verify PASS — Run characterization test to confirm behavior is preserved
  7. Regression Check — Run full test suite to ensure no regressions

HARD GATE — Test Verification:

  • Characterization test EXISTS and PASSES before refactoring
  • Characterization test PASSES after refactoring (behavior preserved)
  • Full test suite PASSES (no regressions)
  • If test fails: Fix the refactoring, not the test

Follow skills/code-quality/refactor-code for specific extraction patterns and safety guidelines.

bundle exec rspec   # All tests must pass before proceeding to Phase 3

If gate fails: Fix the failing test or refactoring before proceeding to Phase 3.


Phase 3: Documentation

Document public APIs via skills/ruby-core-skills/write-yard-docs (annotate all public methods with params, return values, and examples; update README/diagrams for architecture or API changes).

Output: Updated YARD comments, refreshed README sections


HARD-GATE: Quality Before Merge

NEVER open PR before:

bundle exec rubocop        # Linter must pass
bundle exec erblint --lint-all  # ERB linter must pass
bundle exec rspec          # All tests must pass
bundle exec brakeman       # Security scan must pass

Plus: YARD docs complete for all public APIs.

If gate fails: Fix the failing item before opening PR.

Output Format

# Quality Report — [Date]

## Conventions Check
### Critical Violations (Must Fix)
- [CRITICAL] app/controllers/orders_controller.rb:42 — Method `process_payment` has cyclomatic complexity of 15 (> 10 threshold)
- [CRITICAL] app/models/user.rb:28 — Class has 450 lines (> 300 threshold), extract to service objects

### Warning Violations (Should Fix)
- [WARNING] app/services/order_service.rb:17 — Method `calculate_discount` has 6 parameters (> 4 threshold)

### Suggestion Violations (Nice to Have)
- [SUGGESTION] spec/models/order_spec.rb:12 — Test duplication detected, extract to shared examples

## Refactoring
- [x] / [ ] Required (threshold exceeded)
- Characterization tests added, methods extracted, all tests passing

## Documentation
- YARD coverage: 87% (improved from 65%)
- README updated: YES

Error Recovery

RuboCop offenses after refactoring:

  1. Run bundle exec rubocop -a for auto-correctable offenses
  2. Fix remaining offenses manually — refactoring may have introduced style violations
  3. Re-run full suite to ensure fixes don't break behavior

Characterization test fails after refactoring:

  1. The refactoring changed behavior — this is a regression, not a test problem
  2. Revert the refactoring change
  3. Re-examine the extraction — ensure the new method/class preserves the exact contract
  4. Try a smaller, more focused refactoring step

YARD generation errors:

  1. Check for syntax errors in YARD tags (@param, @return, @raise)
  2. Verify method signatures match YARD annotations
  3. Run yard stats to identify undocumented public methods

Anti-Patterns to Avoid

  • Refactoring without tests: NEVER refactor without characterization tests passing first
  • Fixing tests to match refactoring: If a test fails after refactoring, the refactoring broke behavior — fix the code, not the test
  • Scope creep during quality pass: Don't add features during a quality review — only fix conventions, refactor, and document
  • Skipping ERB linter: erblint catches view-layer issues that RuboCop misses
  • Ignoring Brakeman warnings: Every Brakeman warning MUST be assessed — false positives should be annotated, not silently ignored
  • Partial YARD coverage: All public methods MUST have YARD docs — don't skip "obvious" methods

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.