claude

meta

Evaluation layer for Claude Code plugins — scored skill and plugin audits, hook and rules evals, and context-footprint reports against bundled checklists

0 on GitHubby meaganewallerv1.1.3BlueOak-1.0.0updated 5 days ago

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin meta in meaganewaller/marketplace. Commands read from the repo's manifest — 5 days ago.

What it installs

Skills (1)

  • modular-skill-framework

    This skill should be used when the user asks about "modular skills", "composable skills", "skill composition", "split a skill", "skill boundaries", "skill interfaces", "token-efficient skills", "single responsibility for skills", or needs design patterns and implementation guidelines for reusable sk

Slash commands (9)

  • /meta:audit-skill

    Audit a Claude Code skill for structure, triggers, and quality best practices

  • /meta:context-optimization-report

    Generate a context window optimization report for all skills in a directory

  • /meta:create-command

    Scaffold a new slash command in a Claude Code plugin using meta conventions

  • /meta:hooks-eval

    Evaluate plugin hooks statically and run companion test scripts when present

  • /meta:rules-eval

    Evaluate Cursor rules and agent instruction files for clarity and enforceability

  • /meta:skills-eval

    Batch-evaluate all skills in a plugin or directory for quality and compliance

  • /meta:test-skill

    Run behavioral scenarios against a single skill to test trigger and rule compliance

  • /meta:validate-hook

    Validate plugin hook configuration, scripts, and portable path usage

  • /meta:validate-plugin

    Validate a Claude Code plugin against structure and marketplace checklist rules

Subagents (2)

  • plugin-auditor

    Scores Claude Code plugins for layout, manifest quality, component inventory, marketplace registration, and hook/MCP conventions. Use when the user asks to "audit a plugin", "score this plugin", "marketplace registration check", "plugin compliance review", or needs a scored plugin assessment with an

  • skill-auditor

    Performs detailed quality audits of Claude Code skills and generates improvement recommendations. Use when the user asks to "audit a skill", "skill quality review", "evaluate skills in a plugin", "skill standards compliance", "token efficiency audit", or needs structure, content, activation, and too

View source on GitHub

Problems found in this repo's manifests

  • .claude-plugin/marketplace.json is not valid JSON

More from meaganewaller/marketplace

All 12 plugins →

ruby-rails

claude

Ruby 4+ and Rails 8+ expert skills: mise toolchain, Ruby LSP, RBS/Sorbet type signatures, Active Record, Hotwire, testing, security, performance, and Kamal deployment

28 skills · hooks · LSP

0

dotfiles

claude

Chezmoi-managed dotfiles workflow: source-only edits, templates, run_onchange scripts, BATS tests, ADRs, and mise/Homebrew package routing

9 skills · 4 commands · 2 agents · hooks

0

mise

claude

mise dev environment management — tool versions, environment variables, tasks, and project configuration

3 skills · 3 commands · 1 agent · hooks

0

example-plugin

claude

Complete example plugin demonstrating all plugin features

1 skill · 2 commands · 1 agent · 1 MCP server · hooks

0

git-workflow

claude

Git and GitHub workflow skills — commits, pull requests, issues, and PR splitting, sharing one set of conventional-commit and issue-linking rules

4 skills

0

Similar plugins

plugin-dev

claude

Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.

7 skills · 1 command · 3 agents

anthropics/claude-code 155,476

impeccable

claude

Design fluency for frontend development. 1 skill with 24 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.

1 skill · 4 agents · hooks

pbakaus/impeccable 109,099

ruflo-plugin-creator

claude

Scaffold, validate, and publish new Claude Code plugins with proper structure

3 skills · 1 command · 1 agent

ruvnet/ruflo 81,589

academic-research-skills

claude

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

ifixai

claudecodex

Independent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).

1 skill · hooks

ifixai-ai/iFixAi 45,158

llm-finetuning

claudecodex

Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.

10 skills · 2 commands · 3 agents

wshobson/agents 42,461

Maintain meta?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins12 plugins