Skill Claude CodeCodex
This repo uses a continuous dogfood + QA loop for frontend changes.
not rated 15
+1 today A 0 tokens
original MIT
Skill Claude Code
Use this skill to generate well-branded interfaces and assets for NodeBench AI, either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.
not rated 15
+1 today A 53 tokens
original MIT
nodebench
27Skill Claude CodeCodex
Entity intelligence and founder clarity inside Claude Code. Search any company, run banker-grade deep diligence, get actionable remediation steps, and inject company truth into your session. Delegates implementation tasks to Codex when available.
not rated 15
+1 today A SkillSpector: warn 45 tokens
original MIT
Plugin Claude Code
Bundles 2 skills, 2 hooks · 86 tokens together
NodeBench MCP — 244-tool development methodology server with context sandbox, progressive discovery, agent-as-a-graph embeddings, and toolset gating presets.
not rated 15
+1 today A
tokens not measured
original MIT
Cursor rule Cursor
8-point reliability checklist for agent-facing infrastructure.
not rated 15
+1 today A 0 tokens
original MIT
Cursor rule Cursor
Root-cause diagnosis before any fix — 5-whys trace upstream.
not rated 15
+1 today A 209 tokens
original MIT
Cursor rule Cursor
Auto-QA after code changes using NodeBench MCP tools.
not rated 15
+1 today A 0 tokens
original MIT
Skill Claude CodeCodex
Use this capability for source-grounded questions about companies, markets, competitive position, diligence, and changes over time. The expected result is an evidence-backed answer or reusable run artifact, not an unsupported chat response.
not rated 15
+1 today A 0 tokens
original MIT
convexRules
33Cursor rule
Cursor rule "convexRules" from HomenShum/NodeBenchAI, covering convex guidelines, function guidelines, new function syntax, http endpoint syntax and validators.
not rated 15
+1 today A 0 tokens
copy · 94% MIT
nodebench
34Cursor rule
Cursor rule "nodebench" from HomenShum/NodeBenchAI, covering implementation guidelines, 1. code reuse & existing components, 2. architecture & file organization, 3. documentation & api verification and 4. the standard development cycle (request → ship).
not rated 15
+1 today A 0 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: