Cursor rule Cursor
Collaboration preferences and AI interaction style.
not rated 60
+1 28d ago A 473 tokens
original MIT
development
02Cursor rule Cursor needs its repo
Cursor rule "development" from kanyun-inc/reskill, covering reskill development rules, project overview, tech stack, code style guidelines and language requirements.
not rated 60
+1 28d ago A 2,822 tokens
original MIT
testing
03Cursor rule Cursor needs its repo
Cursor rule "testing" from kanyun-inc/reskill, covering testing rules, testing philosophy, spec-driven tdd workflow, benefits of test-first approach and example: adding --dry-run option.
not rated 60
+1 28d ago A 2,287 tokens
original MIT
Skill Claude CodeCodex
Assesses code comprehensibility and maintainability risk. Use when the user asks about code confidence, risk, maintainability, tech debt, code health, or whether code is safe to change. Also use when the user asks to analyze code quality, scan for risks, check if code is messy or complex, audit code, do a code…
not rated 60
+1 28d ago A SkillSpector: warn 104 tokens
original MIT
find-skills
05Skill Claude CodeCodex
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. Uses reskill as the package manager.
not rated 60
+1 28d ago A SkillSpector: warn 54 tokens
original MIT
Skill Claude CodeCodex
Teaches AI agents how to use reskill — a Git-based package manager for AI agent skills. Covers CLI commands, install formats, configuration, publishing, and common workflows.
not rated 60
+1 28d ago A SkillSpector: warn 40 tokens
original MIT
Skill Claude CodeCodex
Detects content drift between skill files and their source documents. Helps maintain skills that are derived from other documentation by comparing content and flagging outdated sections.
not rated 60
+1 28d ago A SkillSpector: warn 35 tokens
original MIT
Skill Claude CodeCodex
Behavioral modifier for AI coding assistants working with non-developers. Adapts AI behavior by risk level — fast for small changes, cautious for risky ones. Prevents debug death spirals, translates errors to plain language, auto-checkpoints with git, and runs periodic health checks. Always active, zero manual trigger…
not rated 60
+1 28d ago A SkillSpector: warn 73 tokens
original MIT
kanyun-inc/ai-explore-review-loop-plugin
Plugin Claude Code
Bundles 5 skills, 3 hooks, 1 MCP server · 115 tokens together
Durable Hermes review/fix loop for Pilot and Rush pull requests.
not rated 0 1mo ago A
tokens not measured
original Apache-2.0
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: