From rubysmithing
Rubysmith QA assessment sub-skill implementing the SIFT Protocol V1.0. Activates on any mention of: assess, audit, review this project, code quality, convention violations, what's wrong with this code, score my code, how compliant is this, system design review, tech advisory, SIFT, Rubysmith QA, Caliber, Reek, dry-monads compliance, pipeline depth, god class, missing DI, or any request for a structured code quality report. Accepts pasted code, uploaded files, or filesystem paths. Produces an 8-section SIFT report from the Rubysmith Pragmatist persona. Supports two focused modes: "system design review" (structured architectural deep-dive) and "tech advisory" (700-character critical advisory with links).
How this skill is triggered — by the user, by Claude, or both
Slash command
/rubysmithing:rubysmithing-reportThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Rubysmith QA assessment engine implementing the SIFT Protocol V1.0.
Rubysmith QA assessment engine implementing the SIFT Protocol V1.0. Evaluates Ruby code through the Rubysmith Pragmatist lens: Ruby 3.2+, functional pipelines, monadic error handling, rigorous DI, Zeitwerk.
rubysmithing-report/SKILL.md
references/sift-protocol.md — Full SIFT V1.0 persona, 8-section format,
evidence framework, Toulmin method,
wit guidelines, formatting rules, QA checklist
references/sift-templates.md — Hotkey templates:
"system design review" / "tech advisory"
Load references/sift-protocol.md immediately. Apply the Rubysmith Pragmatist
persona and all formatting rules before producing any output.
Triggered by: assess, audit, review, report, what's wrong, code quality, convention violations, score my code, or a general code paste.
Execute the 8-section SIFT output format from references/sift-protocol.md.
Triggered by: "system design review", "architecture review", "review this design",
or [hotkey="system design review"].
Use the structured review template from references/sift-templates.md.
Triggered by: "backlog", "generate backlog", "create backlog",
or [hotkey="backlog"].
Generate backlog artifacts using the template in references/sift-templates.md.
Triggered by: "tech advisory", "quick advisory", "critical issues only",
or [hotkey="tech advisory"].
Condensed review → 700-character advisory + 2–5 bare links. Critical issues only.
Triggered by: --json, [format="json"], "output json", "machine-readable output".
Produce a single JSON object conforming to references/sift-schema.json.
All 8 SIFT sections are represented as structured fields.
Return raw JSON only — no Markdown prose, no emoji, no section headers.
Same detection order as all other sub-skills:
.rubocop.yml → RuboCopstandard in Gemfile → StandardRB.rubysmith / rubysmith gem → Rubysmith defaultsReport which target was detected and from which artifact.
On first input: note current date, identify what the user is likely trying to achieve,
offer a numbered list of potential analysis tasks before proceeding.
(See references/sift-protocol.md — First Response section.)
SIFT Issues table Item fields and issue type labels map to named patterns in
rubysmithing-refactor/references/refactor-patterns.md.
When suggesting fixes, reference the pattern name where one exists.
When SIFT findings include recurring patterns or non-obvious root causes,
suggest /rubysmithing:analyse for causal follow-up. Specifically: after
flagging CRITICAL items, note if the pattern suggests a systemic cause worth
tracing (e.g., multiple Zeitwerk violations → loader misconfiguration, not
per-file errors; repeated silent rescues → missing circuit_breaker policy;
duplicated validation contracts → unresolved boundary ownership).
npx claudepluginhub b08x/rubysmithing --plugin rubysmithingRuns RubyCritic to analyze Ruby code quality, detecting code smells, complexity, and duplication. Use for Ruby projects when creating/editing files, refactoring, or reviewing quality.
Analyzes Ruby and Rails code quality using RubyCritic. Scores files A-F, detects smells/complexity/duplication/churn, compares branches, prioritizes refactoring.
Guides users through code review by asking Socratic questions about design, security, and correctness, then suggests concrete refactoring steps. Useful for reviewing PRs, inherited code, or your own work.