abstract

Plugin abstract from marketplace claude-night-market in athola/claude-night-market. Commands read from the repo's manifest — 6 days ago.

Skills (14)

• escalation-governance

  Assess whether to escalate models. Use when evaluating reasoning depth.

• friction-detector

  Detect friction signals; graduate patterns into rules. Use for session retrospectives.

• hook-authoring

  Guide creating Claude Code hooks with security-first design. Use for validation and enforcement.

• hook-scope-guide

  Select hook scope (plugin, project, global) by audience. Use when authoring a hook.

• hooks-eval

  Evaluate hook security, performance, and SDK compliance. Use for audits.

• metacognitive-self-mod

  Analyze and improve the improvement process. Use for detecting regressions and meta-optimization.

• methodology-curator

  Surface expert frameworks. Use when creating or evaluating skills, hooks, or agents.

• modular-skills

  Build composable skill modules with hub-and-spoke loading. Use when token budget is tight.

• plugin-review

  Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.

• rules-eval

  Evaluate Claude Code rules in .claude/rules/. Use for frontmatter, globs, and quality audits.

• skill-authoring

  Guide creating Claude Code skills with TDD and persuasion principles. Use for new skill development.

• skill-graph-audit

  Audit Skill() refs; detect hubs, isolates, and dangling targets. Use when auditing skills.

• skills-eval

  Evaluate Claude skill quality through auditing. Use when reviewing or auditing skills.

• subagent-testing

  Test skills via TDD in fresh subagents. Use when validating behavior or preventing bias.

Slash commands (17)

• /abstract:aggregate-logs

  Generate LEARNINGS.md from skill execution logs over a configurable time window.

• /abstract:analyze-skill

  Analyze skill file complexity metrics and generate modularization recommendations for splitting or progressive loading.

• /abstract:context-report

  Generate context optimization report for skill directories

• /abstract:create-command

  Create slash commands with brainstorming and best practices

• /abstract:create-hook

  Create hooks with brainstorming and security-first design

• /abstract:create-skill

  Scaffold new Claude Code skills with brainstorming, TDD methodology, and proper frontmatter and module structure.

• /abstract:evaluate-skill

  Manually evaluate a recent skill execution to record qualitative feedback.

• /abstract:hooks-eval

  Evaluate all hooks in a plugin for quality and compliance

• /abstract:improve-skills

  Identify and implement skill improvements from execution logs and user evaluations.

• /abstract:make-dogfood

  Analyze and enhance Makefiles for complete functionality coverage with auto-generation capability

• /abstract:plugin-review

  Tiered plugin quality review: branch (quick gates),

• /abstract:promote-discussions

  Check GitHub Discussions for highly voted learnings and promote them to Issues.

• /abstract:rules-eval

  Evaluate Claude Code rules in .claude/rules/ directories for quality

• /abstract:skills-eval

  Audit skill quality, frontmatter compliance, token efficiency, and activation reliability. Recommends improvements.

• /abstract:test-skill

  Test Claude Code skills using RED/GREEN/REFACTOR TDD phases in fresh subagents to prevent priming bias.

• /abstract:validate-hook

  Validate hooks for security, performance, and SDK compliance

• /abstract:validate-plugin

  Validate plugin structure, schema, and naming. Use for plugin creation, debugging, or verification.

Subagents (6)

• insight-engine

  Deep analysis agent that reads codebase patterns, execution logs, and performance data to generate proactive insights about bugs, optimizations, and improvements. Posts findings to GitHub Discussions. - Read - Bash - Glob - Grep - Write

• meta-architect

  Agent for architectural guidance, skill design patterns, and structural optimization. Provides consultation on modularization, token management, and dependency design.

• plugin-validator

  Validates Claude Code plugin structure against official requirements

• skill-auditor

  Agent for detailed skill quality auditing and improvement recommendations. Analyzes skill structure, content quality, token efficiency, activation reliability, and tool integration.

• skill-evaluator

  Records human qualitative feedback on recent skill executions. Use

• skill-improver

  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 c

Hooks (6)

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/pre_skill_execution.py"

• PreToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/agent_dispatch_guard.py"

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/skill_execution_logger.py"

• PostToolUse

  "${CLAUDE_PLUGIN_ROOT}/hooks/homeostatic_monitor.py"

• UserPromptSubmit

  "${CLAUDE_PLUGIN_ROOT}/hooks/aggregate_learnings_daily.py"

• Stop

  "${CLAUDE_PLUGIN_ROOT}/hooks/post_learnings_stop.py"

Similar plugins