Plugins

12 plugins

Run Agent Evaluation

Sets up evaluation framework, runs benchmarks, and produces comparative analysis of agent performance.

9 skills · plugin

Microsoft 365 Agents Toolkit

Toolkit for building and evaluating Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, capability configuration, and eval workflows.

6 skills · plugin

ML Model Lifecycle

Train, evaluate, and deploy a production ML system with monitoring.

10 skills · plugin

Design Pricing Strategy

Design a pricing strategy by analyzing market, evaluating financial impact, and recommending pricing models.

6 skills · plugin

Monetization to Billing Pipeline

For product managers and finance ops: brainstorm strategies, evaluate financial impact, then execute billing workflows.

4 skills · plugin

Analyze and Prioritize Feature Requests

Install this pack to categorize, evaluate, and prioritize customer feature requests against product goals.

3 skills · plugin

Prototyping Testing

Prototyping and testing skills: wireframe specs, usability heuristics, heuristic evaluations, accessibility audits, A/B test design, and benchmark analysis.

8 skills · plugin

Google Cloud Well-Architected

For architects evaluating Google Cloud workloads against the Well-Architected Framework pillars: reliability, cost optimization, and operational excellence.

6 skills · plugin

Visual Critique

Visual critique skills: hierarchy analysis, brand consistency checks against mood/voice/tokens, composition evaluation, and typography audits — with a /critique-screen command that compiles a prioritised fix list.

7 skills · plugin

@alirezarezvani

14 regulatory affairs & quality management skills for HealthTech/MedTech: ISO 13485 QMS, MDR 2017/745, FDA 510(k)/PMA, GDPR/DSGVO, ISO 27001 ISMS, CAPA management, risk management, clinical evaluation, SOC 2 compliance.

10 skills · plugin

@alirezarezvani

Multi-agent collaboration — spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any task that benefits from diverse solutions. 7 slash commands (/hub:init, /hub:spawn, /hub:status, /hub:eval, /hub:merge, /hub:board, /hub:run), agent templates, DAG-based orchestration, LLM judge mode, message board coordination.

8 skills · plugin

@alirezarezvani

Engineering Team

32 engineering skills: architecture, frontend, backend, fullstack, QA, DevOps, security, AI/ML, data engineering, Playwright (9 sub-skills), self-improving agent, Stripe integration, TDD guide, tech stack evaluator, Google Workspace CLI, a11y audit (WCAG 2.2), Azure cloud architect, GCP cloud architect, security pen testing, Snowflake development, adversarial-reviewer, ai-security, cloud-security,

16 skills · plugin

Results for “eval”

202 skills

Novel Evaluator

严格细致判断与评分故事文本，从市场潜力、创新属性、内容亮点维度分析质量。适用于小说初筛选、多维度评估打分

Nemotron Retrieval Recipes

Plan, debug, tune, evaluate, export, or deploy public Nemotron embedding and reranking retrieval recipes using the current checkout.

Guides users through creating, editing, and optimizing agent skills, including drafting, testing, evaluating, and improving skill descriptions for better triggering.

AI QA and evaluation specialist for quality gates. Use when the user asks to talk to Moody, requests AI evaluation, or needs regression tests for AI systems.

Aeon Skill Evals

Validate skill outputs against assertion manifests to detect regressions, enforce quality gates, and bootstrap starter manifests from historical runs.

Create new skills, modify and improve existing skills, and measure skill performance through iterative evaluation and benchmarking.

construct-ai-primary

Innovation Evaluation

Use when assessing new ideas, technologies, or approaches before committing resources to them. This skill provides a framework for evaluating innovation opportunities systematically, separating genuine breakthroughs from hype.

Story Outline Evaluator

专业评估故事大纲，从市场潜力、创新属性、内容亮点维度判断评分。适用于故事大纲质量评估、IP改编潜力判断、项目立项决策

Create Skill Test

Scaffolds eval.yaml test files for agent skills in the dotnet/skills repository, including scenario writing, assertion definition, and rubric creation.

Set up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator. Use when the user runs /ar:setup or asks to start optimizing a file with the autoresearch loop.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Agentic Engineering

Guides AI agents through engineering workflows with eval-first execution, task decomposition, cost-aware model routing, and review focus for generated code.

Evaluate the codebase and suggest ideas to explore with $feature-interview

Guides the creation of high-quality MCP servers that let LLMs interact with external services through well-designed tools, covering planning, implementation, testing, and evaluation.

Expo Skill Eval

Evaluates Expo skills end-to-end: trigger accuracy, generated code quality, and runtime screenshots on iOS simulator and Android emulator via Expo Go.

Ata Gnrh Testing Against

Recommends against performing dynamic GnRH stimulation testing in the evaluation of hypogonadism, as it provides no additional diagnostic information beyond baseline gonadotropins and sex steroids. Consider this recommendation when evaluating hypogonadism and contemplating GnRH testing.

Offers, compensation framing, and negotiation planning. Use when evaluating offers or raises.

Analyzes evaluation patterns across completed plans and evolves the superpowers checklists accordingly.

sakamoto-family-smile

Skill Stocktake

Audits Claude skills and commands for quality, offering Quick Scan for changed skills and Full Stocktake modes with sequential subagent batch evaluation.

Gan Style Harness

Uses a multi-agent generator-evaluator feedback loop to build high-quality applications from a single prompt, inspired by GANs and Anthropic's harness design.

Evaluate a raw app, startup, SaaS, internal tool, marketplace, or AI product idea before planning features. Use when the user shares a vague concept and needs pain analysis, market realism, feasibility, differentiation, risks, or a build/no-build recommendation.

Evaluate codebase against ICP to identify gaps blocking first sales and retention

Deliberative consultation with Codex CLI. Ask, evaluate, critique, iterate until workable agreement.

Deliberative consultation with Gemini CLI. Ask, evaluate, critique, iterate until workable agreement.

Run a single experiment iteration. Edit the target file, evaluate, keep or discard.

Deliberative consultation with Codex CLI. Ask, evaluate, critique, iterate until workable agreement.

Testing Quality Assurance

Coordinates quality assurance workflows by routing testing tasks to specialized sub-skills for API testing, performance benchmarking, test analysis, tool evaluation, and process optimization.

Property Patterns

Provides canonical MSBuild property definition patterns including conditional defaults, composition, path normalization, target framework detection, and evaluation order for diagnosing and fixing property issues in .props and .csproj files.

Understand blockchain technology, interact with smart contracts, and evaluate when distributed ledgers solve real problems.

One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation.

Speckit Review Tests

Test coverage quality analysis — behavioral coverage, critical gap identification, test resilience evaluation.

matteobortolazzo

Address PR review comments by fetching, evaluating, fixing, replying, pushing, and re-requesting review.

One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation.

One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation.

Deobfuscating Javascript Malware

Deobfuscates malicious JavaScript code used in web-based attacks, phishing pages, and dropper scripts by reversing encoding layers, eval chains, string manipulation, and control flow obfuscation to reveal the original malicious logic.

24.6k · bundle

编写评估FastText文本分类模型的Python函数，计算accuracy、F1、recall和precision指标，并处理特定格式的标签文本分割。