All categories
Code Review & Quality
Code review, refactoring, debugging, maintainability, and engineering quality
- 16,458
- 686
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse code review & quality skills
Showing 9,241–9,264 of 16,458 skills
- Code Smell DetectorDetects code smells, anti-patterns, and common bugs with quantified thresholds and severity scoring. Use when reviewing code quality, finding maintainability issues, detecting SOLID violations, or identifying technical debt.Votes: 0GitHub stars: 4
- Code OrganizationFixes code organization issues including high complexity, large files, deep nesting, and barrel file problems. Use when functions are too complex, files too long, or directory structure is problematic.Votes: 0GitHub stars: 4
- Framework SelectorSpecialized agent for selecting optimal agentic AI frameworks (LangGraph, CrewAI, Strands)Votes: 0GitHub stars: 10
- Agent OptimizerSpecialized agent for optimizing existing agentic AI systems based on Amazon's production lessons and AWS best practicesVotes: 0GitHub stars: 10
- Refine Quality ProfileStage 2 skill of /arch. Reads the /specify quality profile, refines targets against architectural reality (inventory constraints, project-profile pins, epic constraints), and writes the refined quality profile to architecture/ with a delta log of every adjustment. The refined QP describes the NFRs physical must deliver; it does NOT name mechanisms.Votes: 0GitHub stars: 3
- Lint ComponentsValidates Garura components (plays, agents, skills) against structural, semantic, and cross-reference rules. Reads quality profile to classify violation severities.Votes: 0GitHub stars: 3
- Author Quality LensAuthor a shaped slice's quality lens as an MD grounding doc — a short statement of what "good" means for the slice plus a table of checkable gates (dimension / bar / how checked) — from the slice's hub (its functionalities' grounding docs + the spine profile's NFR gates). Every gate is grounded (a profile gate that applies or a functionality's rule made checkable) and concrete, never a vague adjective. Under direct-model-write (ADR 026) it writes ONLY the per-node lens docs (`quality.md` conf...Votes: 0GitHub stars: 3
- Author Architecture LensAuthor a shaped slice's architecture lens as an MD grounding doc — the components the slice threads (each in its layer, with its contract), the stack (tech + versions) per component, and the vertical build (how the slice runs end-to-end through them) — from the slice's hub (its functionalities' grounding docs + the spine profile) and KB architecture/technology grounding. Writes architecture.md straight to the live model (re-deriving this slice's lens in place) plus a grounding manifest that c...Votes: 0GitHub stars: 3
- VerboseDebt that exists only in engineers' heads cannot be prioritised, funded, or argued for. A register makes it a portfolio of items with carrying costs.Votes: 0GitHub stars: 2
- MinimalTreat debt as a portfolio with measurable carrying costs, so paydown competes for budget on evidence instead of on how strongly an engineer sighs about it.Votes: 0GitHub stars: 2
- VerboseOwnership models are usually inherited rather than chosen, and the inherited one is usually strong ownership because it emerges naturally — whoever wrote it reviews it. That default has a specific, measurable cost.Votes: 0GitHub stars: 2
- MinimalThe mechanics that let several engineers change one codebase without blocking, duplicating, or silently diverging from each other.Votes: 0GitHub stars: 2
- VerboseRust splits failure into two categories. `Result<T, E>` represents conditions a caller can reasonably anticipate and recover from — missing files, malformed input, a rejected request. `panic!` represents a bug: a violated invariant that means the program is in a state its author never intended.Votes: 0GitHub stars: 2
- MinimalDiagnose why a model underperforms by isolating the cause — data bug, capacity limit, optimization failure, or irreducible noise — before changing anything.Votes: 0GitHub stars: 2
- MinimalWrite infrastructure code that a second engineer can change safely on a Friday — versioned, reviewed, and with a plan you read before you apply.Votes: 0GitHub stars: 2
- Verbose**Level 1: Executive Dashboard** - Single status (green/red) - Key business metrics (users, revenue, SLO %) - No drilling downVotes: 0GitHub stars: 2
- Minimal**Top Section:** Overview - Service health: Green/Red status - Key metrics at a glance (requests/sec, latency, error rate)Votes: 0GitHub stars: 2
- MinimalDiagnose why a test passes and fails on identical code, and fix the cause rather than the symptom.Votes: 0GitHub stars: 2
- MinimalReview code so defects are caught early and the author is unblocked fast — the second half is what most teams get wrong.Votes: 0GitHub stars: 2
- MinimalMove workloads to the cloud with a per-application decision, sequenced to reduce risk — not one big-bang rewrite of everything at once.Votes: 0GitHub stars: 2
- Technical Debt ManagementDebt that exists only in engineers' heads cannot be prioritised, funded, orVotes: 0GitHub stars: 2
- Team CollaborationOwnership models are usually inherited rather than chosen, and the inherited oneVotes: 0GitHub stars: 2
- Incremental ImplementationComprehensive guide for implementing code incrementally following established patterns, conventions, and quality standardsVotes: 0GitHub stars: 2
- Grafana Dashboard Design**Level 1: Executive Dashboard**Votes: 0GitHub stars: 2