Skill Claude Code
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation.
not rated 620
+4 1mo ago A SkillSpector: warn 26 tokens
original MIT
620Stars on the repository
201Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Skill Claude Code
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation.
not rated 620
+4 1mo ago A 27 tokens
copy · 92% MIT
Skill Claude Code
Review dimensions for acceptance test quality - happy path bias, GWT compliance, business language purity, coverage completeness, walking skeleton user-centricity, priority validation, observable behavior assertions, traceability coverage, and walking skeleton boundary proof.
not rated 620
+4 1mo ago A SkillSpector: pass 53 tokens
original MIT
Skill Claude Code
Detailed 5-phase workflow for creating agents - from requirements analysis through validation and iterative refinement.
not rated 620
+4 1mo ago A SkillSpector: warn 24 tokens
original MIT
Skill Claude Code
5-layer testing approach for agent validation including adversarial testing, security validation, and prompt injection resistance.
not rated 620
+4 1mo ago A SkillSpector: pass 23 tokens
original MIT
Skill Claude Code
Architectural style selection decision matrices, trade-off analysis, structural enforcement rules, and combination patterns. Load when choosing or evaluating architecture styles.
not rated 620
+4 1mo ago A SkillSpector: pass 37 tokens
original MIT
Skill Claude Code
Comprehensive architecture patterns, methodologies, quality frameworks, and evaluation methods for solution architects. Load when designing system architecture or selecting patterns.
not rated 620
+4 1mo ago A SkillSpector: pass 32 tokens
original MIT
Skill Claude Code
Canonical AT completeness gate — research-anchored 7-category taxonomy (C1-C7) + 15-item mechanical checklist. Paradigm-neutral. Drives acceptance-designer reviewer verdict deterministically.
not rated 620
+4 1mo ago A SkillSpector: pass 46 tokens
original MIT
Skill Claude Code
Domain-specific authoritative source databases, search strategies by topic category, and source freshness rules.
not rated 620
+4 1mo ago A SkillSpector: pass 22 tokens
original MIT
Skill Claude Code needs its repo
BDD patterns for acceptance test design - Given-When-Then structure, scenario writing rules, pytest-bdd implementation, anti-patterns, and living documentation.
not rated 620
+4 1mo ago A SkillSpector: pass 36 tokens
original MIT
Skill Claude Code
BDD requirements discovery methodology - Example Mapping, Three Amigos, conversational patterns, Given-When-Then translation, and collaborative specification.
not rated 620
+4 1mo ago A SkillSpector: pass 31 tokens
original MIT
Skill Claude Code
Structured divergent thinking techniques — HMW framing, SCAMPER, Crazy 8s mechanics, and option diversity guarantees. Enforces strict separation of generation and evaluation phases.
not rated 620
+4 1mo ago A SkillSpector: pass 40 tokens
original MIT
Skill Claude Code
All /nw- commands — what they do, when to use them, which agent they invoke. For the buddy agent to help users pick the right command.
not rated 620
+4 1mo ago A SkillSpector: pass 39 tokens
original MIT
Skill Claude CodeCodex
How the nWave buddy agent reads a project to answer questions — detection, order of inspection, and citation discipline.
not rated 620
+4 1mo ago A SkillSpector: pass 29 tokens
original MIT
Skill Claude CodeCodex
Single Source of Truth detection — where truth lives in an nWave repo and how to avoid contradicting it.
not rated 620
+4 1mo ago A SkillSpector: pass 31 tokens
original MIT
Skill Claude CodeCodex
Wave methodology knowledge for the buddy agent — what each wave does, its inputs and outputs, and how to route questions.
not rated 620
+4 1mo ago A SkillSpector: pass 31 tokens
original MIT
nw-buddy
17Skill Claude Code
Wave: CROSSWAVE | Agent: Guide (nw-nwave-buddy) | Command: /nw-buddy.
not rated 620
+4 1mo ago A SkillSpector: pass 30 tokens
original MIT
nw-bugfix
18Skill Claude Code
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.
not rated 620
+4 1mo ago A SkillSpector: warn 23 tokens
original MIT
nw-canary
19Skill Claude Code
Canary skill for auto-injection detection.
not rated 620
+4 1mo ago A SkillSpector: pass 12 tokens
original MIT
Skill Claude Code
CI/CD pipeline design methodology, deployment strategies, GitHub Actions patterns, and branch/release strategies. Load when designing pipelines or deployment workflows.
not rated 620
+4 1mo ago A SkillSpector: pass 36 tokens
original MIT
Skill Claude Code
Cross-agent collaboration protocols, workflow handoff patterns, and commit message formats for TDD/Mikado/refactoring workflows.
not rated 620
+4 1mo ago A SkillSpector: pass 32 tokens
original MIT
Skill Claude Code
Documentation collapse anti-patterns - detection rules, bad examples, and remediation strategies for type-mixing violations.
not rated 620
+4 1mo ago A SkillSpector: pass 25 tokens
original MIT
Skill Claude Code
Best practices for command definition files - size targets, declarative template, anti-patterns, and canonical examples based on research evidence.
not rated 620
+4 1mo ago A SkillSpector: warn 31 tokens
original MIT
Skill Claude Code
Step-by-step workflow for converting bloated command files to lean declarative definitions.
not rated 620
+4 1mo ago A SkillSpector: pass 22 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: