Plugin Ecosystem
abstract
Meta-skills infrastructure — skill authoring, hook development, modular design patterns, and evaluation frameworks.
New
Meta-skills infrastructure for the Claude Code plugin ecosystem — skill authoring, hook development, modular design patterns, and evaluation frameworks.
Source: claude-night-market marketplace Version: 1.4.3 Author: Alex Thola
Key Commands
| Command | Description | When to Use |
|---|---|---|
/create-skill | Author a new Claude Code skill | When building a new skill from scratch |
/create-command | Create a new slash command | When adding a command to a plugin |
/create-hook | Develop a new hook | When adding lifecycle hooks |
/test-skill | Test a skill in isolation | After creating or modifying a skill |
/bulletproof-skill | Harden a skill against edge cases | When preparing a skill for production |
/evaluate-skill | Evaluate skill quality | When assessing a single skill |
/skills-eval | Evaluate all skills in a plugin | When auditing a plugin's skill quality |
/hooks-eval | Evaluate all hooks in a plugin | When auditing hook quality |
/analyze-skill | Deep analysis of a skill | When investigating skill behavior |
/analyze-hook | Deep analysis of a hook | When investigating hook behavior |
/validate-plugin | Validate plugin structure | When checking plugin.json and structure |
/validate-hook | Validate hook configuration | When checking hook config |
/plugin-review | Full plugin quality review | When reviewing an entire plugin |
/improve-skills | Suggest skill improvements | When looking for skill optimization opportunities |
/make-dogfood | Generate dogfooding scenarios | When creating test scenarios for skills |
/aggregate-logs | Aggregate skill execution logs | When analyzing skill usage patterns |
/context-report | Report on context usage | When analyzing context window usage |
/estimate-tokens | Estimate token consumption | When planning token budgets |
Skills
| Skill | When It Activates |
|---|---|
| escalation-governance | When escalation decisions arise that need governance |
| hook-authoring | When creating or modifying hooks |
| hooks-eval | During hook evaluation and quality assessment |
| makefile-dogfooder | When dogfooding Makefile-based workflows |
| methodology-curator | When curating and organizing methodologies |
| modular-skills | When designing skills with modular architecture |
| performance-optimization | During performance optimization of skills |
| shared-patterns | When applying cross-plugin shared patterns |
| skill-authoring | When creating or modifying skills |
| skills-eval | During skill evaluation and quality assessment |
| subagent-testing | When testing subagent behavior |
Agents
| Agent | Purpose |
|---|---|
| meta-architect | Design plugin architecture and skill organization |
| plugin-validator | Validate plugin quality against best practices |
| skill-auditor | Audit skill implementations for issues |
| skill-evaluator | Evaluate skill effectiveness with metrics |
| skill-improver | Suggest and apply skill improvements |
Common Workflows
Build a New Skill
The standard flow for creating a production-quality skill:
- Create — Run
/create-skilland describe what the skill should do. Abstract scaffolds the skill file with the correct structure and metadata. - Test — Run
/test-skillto test the skill in isolation, verifying it activates correctly and produces expected results. - Harden — Run
/bulletproof-skillto test edge cases, add defensive guards, and ensure the skill handles unexpected inputs gracefully. - Evaluate — Run
/evaluate-skillto get a quality score and improvement suggestions.
Plugin Quality Check
When auditing an entire plugin for quality:
- Review — Run
/plugin-reviewfor a comprehensive quality assessment covering structure, skills, commands, hooks, and agents. - Evaluate skills — Run
/skills-evalto evaluate every skill in the plugin, producing a report with scores and improvement priorities. - Improve — Run
/improve-skillsto get specific, actionable improvement suggestions for each skill that scored below threshold.
Tips
- Abstract is a meta-plugin — it is used to build and improve other plugins, not for day-to-day development work.
- The skill-authoring skill activates automatically when you are editing SKILL.md files, even without running a command.
/estimate-tokensis useful for keeping skills within token budgets. Large skills consume context window space.- The modular-skills pattern encourages breaking large skills into composable pieces.
See Also
- Contributing — How to add skills to the ontopix plugin
- Available Tools — Full command reference