evals-skills
169Plugin Claude Code
Skills for building LLM evals. Starts with interactive error discovery: build a review app, sample diverse traces, and organize human annotations into failure modes.
5,487 tagged Code review, measured the same way as everything else here.
Browse within: code-quality 105claude-code-skills 59agentic-workflow 46agentic-coding 45claude-plugin 43claude-code-plugins 36claude-code-skill 35claude-code-marketplace 33ai-code-review 32claude-plugins 28claude-ai 27agentic-workflows 26coding-agents 26ai-skills 25
Plugin Claude Code
Skills for building LLM evals. Starts with interactive error discovery: build a review app, sample diverse traces, and organize human annotations into failure modes.
waybarrios/opencode-power-pack
Plugin Claude Code
Portable software-development skills for Claude Code, Codex, OpenCode, and Pi.
waybarrios/opencode-power-pack
Plugin Claude Code
Fifty-four software-development workflows for Claude Code, Codex, OpenCode, and Pi.
Plugin Claude Code
GMGN OpenAPI skills for AI coding assistants — token info, market data, wallet portfolio & copy-trade scoring, and swap execution across sol / bsc / base / eth / robinhood.
Plugin Claude Code
Web app MVP launch readiness checker. Analyzes existing codebases against a battle-tested 10-point checklist (Stripe, mobile, onboarding, AI stability, emails, logging, feedback, auth, domain, database). Identifies gaps, confirms understanding with user, and produces prioritized action items. Philosophy: Don't…
Plugin Claude Code
Survey design framework grounded in proven research methods (Caroline Jarrett's Surveys That Work, Dillman's Tailored Design, Tourangeau's cognitive model). Captures user intent — what people are actually trying to do, what friction they face, what outcomes they want — without leading questions, satisficing bait, or…
Plugin Claude Code
Deep architectural analysis of open-source projects with professional reports.
Plugin Claude Code
Canary browser automation + recorded QA sessions: a sandbox scripting reference, verify/automate/session/review skills, JTBD subagents, and /canary slash commands.
Plugin Claude Code
Memtrace skills for codebase exploration, code search, relationship analysis, temporal evolution, blast radius impact, code quality, graph algorithms, API topology, GitHub PR code review, multi-agent fleet coordination (branch-scoped intents, conflict classification, and agent-judged Class C resolution), and…
yanhua1010/self-media-content-workflow
Plugin Claude Code
A modular toolkit for producing and managing social-media content, with skills for planning, research, writing, short videos, publishing, performance review, and archiving.
Plugin Claude Code
Plugin marketplace listing 7 plugins: brainstorm, review, planning, release-tools, thinking-tools.
Plugin Claude Code
Structured implementation planning, interactive annotation review, and autonomous plan execution.
Plugin Claude Code
Plugin marketplace listing 1 plugin: maestro.
Plugin Claude Code
Multi-agent development orchestration platform — 39 specialists, 4-phase orchestration, native parallel subagents, persistent sessions, and standalone review/debug/security/perf/seo/a11y/compliance commands.
Plugin Claude Code
Plugin marketplace listing 1 plugin: fund-manager-alpha.
Plugin Claude Code
A fund-manager analysis plugin described as an audit engine for examining investment decisions and trading behaviour. It produces a large interactive report about those findings.
Plugin Claude Code
Marketing OS: an entire marketing department as one Claude skill.
Plugin Claude Code
An entire marketing department as one Claude skill. 14 modules: audits scored 0-100, an 18-tactic hook engine, copy graded before you see it, ad diagnosis, GEO, email, launches, pricing. Works in Claude, Codex and Cursor.
Plugin Claude Code
Plugin marketplace listing 1 plugin: recomby-geo.
Plugin Claude Code
Plugin marketplace listing 1 plugin: starter-kit.
Plugin Claude Code
A beginner-friendly desktop-agent workflow: shape rough requests, review plans before acting, and leave handoff notes. Optional second opinions work when Codex or Gemini are already set up.
Plugin Claude Code
Official plugin marketplace for the AI-Driven Development framework.
Plugin Claude Code
Async development orchestration: turn ready issues into pull requests, then iterate on review feedback until a human takes over.
Plugin Claude Code
Cole Medin's agent skills for building software with coding agents.