By malston
Encode and demonstrate heuristics for Claude Code plugin design decisions -- skill vs. agent vs. command vs. hook.
Audits a Claude Code plugin's structure for misclassified components. Analyzes agents, skills, commands, and hooks against design heuristics.
Extracts architectural constraints from a feature description to determine parallelism, isolation, tiering, context budget, and I/O contract needs.
Classifies a feature description by task type, trigger mode, context needs, and reusability to inform plugin mechanism selection.
Interactive decision tree that guides you through choosing the right Claude Code plugin mechanism. Use when asked "help me choose", "decision tree", "I'm not sure whether to use", "skill or agent", or "command or hook".
Heuristics for choosing the right Claude Code plugin mechanism -- skill, agent, command, or hook. Use when designing, reviewing, or refactoring plugin architecture.
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A self-demonstrating Claude Code plugin that encodes heuristics for plugin design decisions. The plugin's own architecture enacts the rules it teaches -- skill vs. agent vs. command vs. hook.
Skills inject knowledge into context. Agents spawn isolated Claude instances.
This single sentence resolves most ambiguous cases. If you're building something to teach Claude how to do X correctly, it's a skill. If you need separate context, tool permissions, or a different model, it's an agent.
| Component | Purpose |
|---|---|
skills/plugin-design-advisor/ | Core heuristics for choosing the right plugin mechanism |
agents/architecture-validator.md | Audits existing plugin structure for misclassifications |
agents/requirements-analyzer.md | Classifies task characteristics |
agents/constraint-extractor.md | Identifies parallelism/isolation/tiering needs |
commands/design.md | Multi-phase design workflow with parallel analysis |
commands/validate.md | Run architecture-validator against a plugin directory |
hooks/hooks.json | PreToolUse guard on Write/Edit to agents/ and skills/ |
skills/decision-explorer/ | Interactive decision tree for learners (Phase 4) |
The skill and architecture-validator identify these misclassifications:
See docs/DESIGN.md for the full design specification.
npx claudepluginhub malston/plugin-design-advisorGenerate OpenAPI/Swagger documentation from Go API code
Interactive tutor for Claude Code workshop attendees. Teaches via wiki content and Anki flashcards with progressive topic unlocking.
VMware vSphere architecture, design, and troubleshooting expertise. Covers capacity planning, resource management, performance tuning, HA/DRS design, storage architecture, and infrastructure design for enterprise virtualization environments.
Complete plugin development toolkit for creating, refactoring, and validating Claude Code plugins and agents. Use when creating new plugins/skills/agents, refactoring existing plugins/skills, validating frontmatter, or restructuring plugin components. Includes specialized agents for assessment, planning, execution, and validation workflows.
Create and manage Claude Code skills, plugins, subagents, and hooks. Use when building new skills, validating existing skills, testing skills empirically, creating plugins, converting projects to plugins, creating hooks, or managing plugin automation. Includes /skills-toolkit:skill-composer, /skills-toolkit:skill-refiner, /skills-toolkit:skill-tester, /skills-toolkit:plugin-creator, /skills-toolkit:subagent-creator, /skills-toolkit:hook-creator, and /skills-toolkit:ask-user-question skills.
Plugin development toolkit with skills for creating agents, commands, hooks, MCP integrations, and comprehensive plugin structure guidance
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.