Keyboard shortcuts

Press ← or → to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

abstract

Meta-skills infrastructure for the plugin ecosystem - skill authoring, hook development, and quality evaluation.

Overview

The abstract plugin provides tools for building, evaluating, and maintaining Claude Code plugins. It’s the toolkit for plugin developers.

Installation

/plugin install abstract@claude-night-market

Skills

SkillDescriptionWhen to Use
skill-authoringTDD methodology with Iron Law enforcementCreating new skills with quality standards
hook-authoringSecurity-first hook developmentBuilding safe, effective hooks
modular-skillsModular design patternsBreaking large skills into modules
skills-evalSkill quality assessmentAuditing skills for token efficiency
hooks-evalHook security scanningVerifying hook safety
escalation-governanceModel escalation decisionsDeciding when to escalate models
makefile-dogfooderMakefile analysisEnsuring Makefile completeness
methodology-curatorExpert framework curationGrounding skills in proven methodologies
shared-patternsPlugin development patternsReusable templates
subagent-testingSubagent test patternsTesting subagent interactions

Commands

CommandDescription
/validate-plugin [path]Check plugin structure against requirements
/create-skillScaffold new skill with best practices
/create-commandScaffold new command
/create-hookScaffold hook with security-first design
/analyze-hookAnalyze hook for security and performance
/analyze-skillGet modularization recommendations
/bulletproof-skillAnti-rationalization workflow for hardening
/context-reportContext optimization report
/estimate-tokensEstimate token usage for skills
/hooks-evaldetailed hook evaluation
/make-dogfoodAnalyze and enhance Makefiles
/skills-evalRun skill quality assessment
/test-skillSkill testing with TDD methodology
/validate-hookValidate hook compliance

Agents

AgentDescription
meta-architectDesigns plugin ecosystem architectures
plugin-validatorValidates plugin structure
skill-auditorAudits skills for quality and compliance

Hooks

HookTypeDescription
homeostatic_monitor.pyPostToolUseReads stability gap metrics, queues degrading skills for auto-improvement
pre_skill_execution.pyPreToolUseSkill execution tracking
skill_execution_logger.pyPostToolUseSkill metrics logging
post-evaluation.jsonConfigQuality scoring and improvement tracking
pre-skill-load.jsonConfigPre-load validation for dependencies

Self-Adapting System

A closed-loop system that monitors skill health and auto-triggers improvements:

  1. homeostatic_monitor.py checks stability gap after each Skill invocation
  2. Skills with gap > 0.3 are queued in improvement_queue.py
  3. After 3+ flags, the skill-improver agent runs automatically
  4. skill_versioning.py tracks changes via YAML frontmatter
  5. rollback_reviewer.py creates GitHub issues if regressions are detected
  6. experience_library.py stores successful trajectories for future context

Cross-plugin dependency: reads stability metrics from memory-palace’s .history.json.

Usage Examples

Create a New Skill

/create-skill

# Claude will:
# 1. Use brainstorming for idea refinement
# 2. Apply TDD methodology
# 3. Generate skill scaffold
# 4. Create tests

Evaluate Skill Quality

Skill(abstract:skills-eval)

# Scores skills on:
# - Token efficiency
# - Documentation quality
# - Trigger clarity
# - Modular structure

Validate Plugin Structure

/validate-plugin /path/to/my-plugin

# Checks:
# - plugin.json structure
# - Required files present
# - Skill format compliance
# - Command syntax

Best Practices

Skill Design

  1. Single Responsibility: Each skill does one thing well
  2. Clear Triggers: Include “Use when…” in descriptions
  3. Token Efficiency: Keep skills under 2000 tokens
  4. TodoWrite Integration: Output actionable items

Hook Security

  1. No Secrets: Never log sensitive data
  2. Fail Safe: Default to allowing operations
  3. Minimal Scope: Request only needed permissions
  4. Audit Trail: Log decisions for review
  5. Agent-Aware (2.1.2+): SessionStart hooks receive agent_type to customize context

Superpowers Integration

When superpowers is installed:

CommandEnhancement
/create-skillUses brainstorming for idea refinement
/create-commandUses brainstorming for concept development
/create-hookUses brainstorming for security design
/test-skillUses test-driven-development for TDD cycles
  • leyline: Infrastructure patterns abstract builds on
  • imbue: Review patterns for skill evaluation