Skills by risk · page 384
Highest-trust agent skills
9,826 skills rated SAFE with grade A or B, best score first. All are grade B today: grade A needs a sandboxed run we do not do for skills yet. Ties are broken by stars, so a repository with many skills can fill a page.
Cite
Cite this page
ModelsAtlas. “Highest-trust agent skills”. Retrieved 30 Oct 2026. https://modelsatlas.com/skills/trusted/page/384
nWave-ai/nWave
Requirements quality critique dimensions for peer review - confirmation bias detection, completeness validation, clarity checks, testability assessment, and priority validation
nWave-ai/nWave
Review dimensions and bug patterns for journey artifact reviews
nWave-ai/nWave
Blameless post-mortem structure, incident timeline reconstruction, response evaluation, and organizational learning
nWave-ai/nWave
Monitoring, observability, operational procedures, CI/CD lessons learned, and quality gate definitions. Load when assessing production readiness or validating operational excellence.
nWave-ai/nWave
Agent safety boundaries - input validation, output filtering, scope constraints, and document creation policy
nWave-ai/nWave
Progressive L1-L6 refactoring hierarchy, 22 code smell taxonomy, atomic transformations, test code smells, and Fowler refactoring catalog
nWave-ai/nWave
Property-based testing strategies, mutation testing, shrinking, and combined PBT+mutation workflow for test quality validation
nWave-ai/nWave
Quality gates - 11 commit readiness gates, build/test protocol, validation checkpoints, and quality metrics
nWave-ai/nWave
Type-specific validation checklists, six quality characteristics, and quality gate thresholds for documentation assessment
nWave-ai/nWave
SQL and NoSQL query optimization techniques, indexing strategies, execution plan analysis, JOIN algorithms, cardinality estimation, and database-specific query patterns
nWave-ai/nWave
Applies the Refactoring Priority Premise (RPP) levels L1-L6 for systematic code refactoring. Use when improving code quality through structured refactoring passes.
nWave-ai/nWave
Gathers knowledge from web and files, cross-references across multiple sources, and produces cited research documents. Use when investigating technologies, patterns, or decisions that need evidence backing.
nWave-ai/nWave
Research output templates, distillation workflow, and quality standards for evidence-driven research
nWave-ai/nWave
Dispatches an expert reviewer agent to critique workflow artifacts. Use when a roadmap, implementation, or step needs quality review before proceeding.
nWave-ai/nWave
YAML output format and approval criteria for platform design reviews. Load when generating review feedback.
nWave-ai/nWave
Detailed review process, v2 validation checklist, and scoring methodology for agent definition reviews
nWave-ai/nWave
Selects a quality-vs-token-consumption profile (lean, standard, thorough, exhaustive, custom, inherit) and persists it globally (~/.nwave/global-config.json) or per-project (.nwave/des-config.json). Use when tuning how…
nWave-ai/nWave
Creates a phased roadmap.json for a feature goal with acceptance criteria and TDD steps. Use when planning implementation steps before execution.
nWave-ai/nWave
Roadmap-specific validation checks for architecture reviews. Load when reviewing roadmaps for implementation readiness.
nWave-ai/nWave
Root cause analysis and debugging
nWave-ai/nWave
Critique dimensions and scoring for research document reviews
nWave-ai/nWave
Architecture quality critique dimensions for peer review. Load when invoking solution-architect-reviewer or performing self-review of architecture documents.
nWave-ai/nWave
Architecture quality critique dimensions for peer review. Load when performing architecture document reviews.
nWave-ai/nWave
Reviewer critique dimensions for peer review - implementation bias detection, test quality validation, completeness checks, and priority validation