Engineering
(24 of 80)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
Claude
Agentforce Sales (formerly Salesforce Sales Cloud)Google 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
ClaudeTrustpilotAlexis 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
ClaudeGitHubFigma+2 moreAustin Bedell
Senior Product Designer at G2
Technical Software Evaluation with AI
Cut through scattered documentation to build a structured technical evaluation that maps software capabilities against your actual requirements and surfaces unvalidated assumptions before purchase. The workflow identifies integration risks, trade-offs, and critical open questions so your team can make informed adoption decisions.
ChatGPTMistral
Jira+3 moreJayesh Wankhede
Software Engineer II at Uber
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.
Build and Validate AI Workflow Skills
A two-skill package for creating runnable AI workflow skills from documents and evaluating whether they are shareable.
ClaudeChatGPTCursor+5 moremchen-gtm
Ship AI-Built Code With Documentation and Audits
2 skills and 5 commands for documenting vibe-coded apps, auditing security/performance, mapping test coverage, and producing shipping packets.
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.
ClaudeSuperWhisperJim Samios
Software Engineer III at G2
Business Technology & Digital Solutions Workflow
Avoid costly, fragmented digital projects with a plan that connects business goals to practical tools, implementation steps, and measurable results. It also flags performance, security, accessibility, and SEO checks before launch.
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.
ChatGPTNode.jsGitHub Actions+1 moreVaibhav S.
Machine Learning Engineer at G2
AI-Assisted Incident Root Cause Analysis
Rapidly synthesize fragmented incident evidence into a structured root-cause diagnosis, distinguishing correlation from causation and confidence levels. The workflow builds a validated timeline, evaluates competing hypotheses, and produces remediation steps without inventing conclusions when evidence remains incomplete.
Jayesh Wankhede
Software Engineer II at Uber
AI-Assisted Requirements to Technical Specification
Clarify ambiguous requirements and surface missing edge cases before engineering starts, turning vague briefs into testable specifications with acceptance criteria and identified risks. This workflow extracts functional and technical context, flags unresolved decisions, and produces a structured handoff document that aligns product and engineering on scope and dependencies.
NotionClaudeChatGPT+1 moreJayesh Wankhede
Software Engineer II at Uber
AI-Assisted API & SDK Evaluation
Skip weeks of manual API documentation review and immediately spot integration blockers, security gaps, and architectural mismatches. This workflow maps your technical requirements against API capabilities and surfaces assumptions worth testing before you commit to implementation.
Jayesh Wankhede
Software Engineer II at Uber
Two-Way Sync Between Your CRM and a System That Cannot Send Webhooks
Eliminate manual data entry between your CRM and operational system by automating two-way syncing even when the latter cannot send webhooks. Daily change detection captures edits made directly in your system of record and pushes them to your CRM, keeping both platforms current and your team working with trusted data.
HubSpot BreezeARIVETurn 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 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
Interview Your Code Requirements Like a Senior Architect
Conducts a rigorous pre-code interview using interactive questioning and codebase analysis.
Use Scripts to Extract or Analyze Prompts
Python and shell scripts for reverse engineering GPTs, extracting prompts, and testing LLM behavior.
Protect Your GPTs With Security Prompt Techniques
Instruction-level protections against prompt injection, jailbreaking, and custom instruction extraction.
Capture Learnings and Run Retrospectives
Persistent memory and process reflection that compounds across sessions.