Engineering
(24 of 46)Coding agents, code review, architecture, testing, and developer workflows.
Corporate Structure for Agents
Build complex projects without token bloat or context loss—organize AI agents like a corporation where fresh workers instantly understand their role, status, and blockers through shared context docume
Sean Lange
Software Engineering Intern at G2
Right-Size Every Claude Task with Token Squirrel 🐿️
Stop overspending on compute by matching each task to the lightest Claude model that solves it well. The skill classifies your work on a five-level complexity scale and shows you the usage savings before you commit.
ClaudeMatt Ryan
Vice President of Global Solutions & Customer Success at G2
Workflow Spec & Design Doc Builder
Transform messy meeting notes into verified workflow specs by automatically validating every Salesforce and Snowflake field exists before documentation is finalized—eliminating costly implementation d
Agentforce Sales (formerly Salesforce Sales Cloud)ClaudeGoogle Docs+3 moreTed S.
GTM Engineer at G2
LLM-as-a-judge to benchmark software platform experience
Benchmark software platform UX across multiple apps using dual LLM-as-judge and synthetic-user scoring passes that validate each other, generating quantified performance comparisons and interactive da
Alexis Z.
CPTO at G2
AI + Speed to production and efficiency were... Playbook
Streamline product development by using AI to reduce communication friction. Designers leverage Claude to iterate on Figma designs and auto-publish refined solutions directly to Git, enabling autonomo
Austin Bedell
Senior Product Designer at G2
Evaluate Skill Quality and Readiness
A skill that scores any AI workflow skill on eight dimensions, applies hard readiness gates, distinguishes guides from runnable skills, and produces a prioritized improvement prompt.
G2
Build and Validate AI Workflow Skills
A two-skill package for creating runnable AI workflow skills from documents and evaluating whether they are shareable.
HubSpot Sales HubAgentforce Sales (formerly Salesforce Sales Cloud)mchen-gtm
AI Pair Programming with Persistent Memory
AI pair programming assistant that builds persistent memory of your codebase, preferences, and decisions—making each session feel like continuing work with an embedded colleague.
Jim Samios
Software Engineer III at G2
PromptFoo LLM Evaluation Pipelines
Ensure LLM applications behave correctly by building deterministic evaluation pipelines that gate deployments on real-world test cases and semantic quality metrics. PromptFoo configs let you test actual application behavior with model-graded rubrics and versioned datasets across your CI workflow.
Vaibhav S.
Machine Learning Engineer at G2
Analyze Finance Anomalies with LLM Grounding
Cut manual review time by uploading your Alteryx financial datasets into an LLM with source citations required, letting you spot anomalies and variance drivers with instant, verifiable references to specific columns and files. Validate findings directly against your original outputs before presenting to stakeholders.
Turn Documents Into Runnable Skills
A skill that extracts incomplete documents, closes gaps through creator interviews, generates complete lifecycle skills, and validates them with simulated runs.
G2
G2 Frontend Guru - Autonomous UI Builder
Convert any UI input, from screenshots to text descriptions, into production-ready, design-system-compliant code in minutes, eliminating the manual rework that slows down product teams. Ship consistent interfaces across G2 without requiring Elevate expertise or design system mastery.
ClaudeWebFetchNext.js+3 moreAustin Bedell
Product Design Manager at G2
Frontend Guru - Autonomous UI Builder
Turn any UI mockup, screenshot, or description into production-ready, design-system-compliant code in minutes—no design expertise needed. Ship consistent interfaces across your entire team.
Austin Bedell
Product Design Manager at G2
Utilities & Integration
Safety guardrails, browser control, multi-AI review, and memory sync
Plan Technical Details
Lock down architecture, data flow, state machines, and test strategy
Plan with Leadership Perspective
Strategic product scope decisions from a CEO or founder's viewpoint
Interrogate Ideas Before Building
Force critical thinking on product assumptions before writing code
Discover Windsurf Resources and Community Prompts
A curated community hub for Windsurf resources, FAQs, tips, and user-contributed prompts.
Deploy Agents with Managed Agents API
Tutorial series for Anthropic's hosted agent runtime, enabling stateful, tool-using agents with persistent sessions and external integrations.