LLM judge for plugin quality assessment. Scores skills on triggering accuracy, orchestration fitness, output quality, and scope calibration using anchored rubrics.
Orchestrates plugin quality evaluation. Use PROACTIVELY when evaluating, scoring, or certifying plugin quality.
This repo is a learning experiment by Steven Li based on wshobson/agents.
It is not affiliated with the original project. It records one day's experiment with the codebase.
tools/validate_agent_unique_names.py (+98 lines). Scans all .md files under plugins/, extracts the name field from YAML frontmatter with a lightweight regex-based parser, and reports any name that appears in more than one file. Exits with code 1 if duplicates exist, otherwise 0.tools/tests/test_validate_agent_unique_names.py (+121 lines). Five unit tests covering:
Total: 2 new files, ~219 lines added, 0 lines removed.
This repo is not maintained. Issues filed here will not be addressed. If you want the maintained version of the project, use the upstream repo.
If something here is useful, port it upstream yourself or open an issue on the upstream repo with a link to this work.
The original project workflow files are stored in UPSTREAM_WORKFLOWS_DISABLED/ for reference. They are not active in this snapshot.
The original LICENSE file is preserved verbatim in this repository.
Original project: wshobson/agents Upstream commit at fork time: cbcde3f1f4309f023095181d3e591f983ec7c95d
Uses power tools
Uses Bash, Write, or Edit tools
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.
npx claudepluginhub yo-steven/agents-exploration-20260523 --plugin plugin-evalSelf-contained GEO (Generative Engine Optimization) plugin: 7 slash commands orchestrate the pipeline (/01-intake → /07-reaudit), 7 vendored open-source skills supply commodity capabilities (audit, content writing, schema, internal linking, keyword expansion, quality scoring, frontend design) plus one original skill (geo-review-html) that renders interactive client-review HTML, 8 JSON schemas. Zero external deps, zero API keys for the default flow. Per-client folder convention.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
LLM application development with LangGraph, RAG systems, vector search, and AI agent architectures for Claude 4.6 and GPT-5.4
Self-improving Claude Code plugin — learns from corrections across sessions via reflexio
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.