Agent
Agent for architectural guidance, skill design patterns, and structural optimization. Provides consultation on modularization, token management, and dependency design.
332 6d ago A 32 tokens
original MIT
Agent
Validates Claude Code plugin structure against official requirements - checks plugin.json schema, verifies referenced paths exist, validates kebab-case naming, and validates skill frontmatter is complete.
332 6d ago A 37 tokens
original MIT
Agent
Agent for detailed skill quality auditing and improvement recommendations. Analyzes skill structure, content quality, token efficiency, activation reliability, and tool integration.
332 6d ago A 36 tokens
original MIT
Agent
Facilitates human-in-loop qualitative evaluation of skill executions.
332 6d ago A 3 tokens
original MIT
Agent
Implements skill improvements based on observability data from LEARNINGS.md. Prioritizes by frequency × impact / ease, generates proposals, validates changes. Enhanced with Hyperagents patterns: consults PerformanceTracker for trend data and ImprovementMemory for causal hypotheses before proposing changes.
332 6d ago A 60 tokens
original MIT
Command
Generate LEARNINGS.md from skill execution logs over a configurable time window.
332 6d ago A 19 tokens
original MIT
Command
Analyze skill file complexity metrics and generate modularization recommendations for splitting or progressive loading.
332 6d ago A 21 tokens
original MIT
Command
Generate context optimization report for skill directories.
332 6d ago A 10 tokens
original MIT
Command
Create slash commands with brainstorming and best practices.
332 6d ago A 11 tokens
original MIT
create-hook
34Command
Create hooks with brainstorming and security-first design.
332 6d ago A 11 tokens
original MIT
create-skill
35Command
Scaffold new Claude Code skills with brainstorming, TDD methodology, and proper frontmatter and module structure.
332 6d ago A 25 tokens
original MIT
Command
Manually evaluate a recent skill execution to record qualitative feedback.
332 6d ago A 16 tokens
original MIT
hooks-eval
37Command
Evaluate all hooks in a plugin for quality and compliance.
332 6d ago A 14 tokens
original MIT
Command
Identify and implement skill improvements from execution logs and user evaluations.
332 6d ago A 17 tokens
original MIT
make-dogfood
39Command
Analyze and enhance Makefiles for complete functionality coverage with auto-generation capability.
332 6d ago A 18 tokens
original MIT
Command
Tiered plugin quality review: branch (quick gates), pr (quality scoring), release (full ecosystem audit). Detects affected plugins from git diff and reviews related plugins for side effects.
332 6d ago A 40 tokens
original MIT
Command
Check GitHub Discussions for highly voted learnings and promote them to Issues.
332 6d ago A 20 tokens
original MIT
rules-eval
42Command
Evaluate Claude Code rules in .claude/rules/ directories for quality.
332 6d ago A 18 tokens
original MIT
skills-eval
43Command
Audit skill quality, frontmatter compliance, token efficiency, and activation reliability. Recommends improvements.
332 6d ago A 24 tokens
original MIT
test-skill
44Command
Test Claude Code skills using RED/GREEN/REFACTOR TDD phases in fresh subagents to prevent priming bias.
332 6d ago A 29 tokens
original MIT
Command
Validate hooks for security, performance, and SDK compliance.
332 6d ago A 13 tokens
original MIT
Command
Validate plugin structure, schema, and naming. Use for plugin creation, debugging, or verification.
332 6d ago A 22 tokens
original MIT
Skill Claude CodeCodex
Detailed development workflow with modular patterns for git, review, testing, and deployment.
332 6d ago A 20 tokens
original MIT
PreToolUse
48Hook
Runs before the agent uses a tool for Skill, Agent and Task tool calls, executing pre_skill_execution.py and agent_dispatch_guard.py (2 commands). From athola/claude-night-market.
332 6d ago A
tokens not measured
original MIT