Recently updated open-source projects

Solution Architect Workbench helps presales and architecture teams turn customer material and requirements into a bid-ready solution package. It combines guided architecture design, editable diagrams, proposal and presentation templates, and line-by-line RFP support, then carries the work into delivery-runbook preparation. The project is for personal learning, research, and non-commercial use; commercial adoption requires written authorization.

Retail Digital AI Expert is an English international workbench for retail transformation across convenience, grocery, apparel, DTC, e-commerce, franchise, and global chains. It combines format diagnosis with maturity assessment, vendor selection, five-year TCO and ROI analysis, AI-use-case prioritization, and implementation roadmaps. The repository’s license limits use to personal learning, research, and non-commercial work unless the author gives written permission.

Restaurant Digital AI Expert is an English workbench for global food-service transformation. It maps restaurant formats and business chains from supply and central kitchens through front-of-house, POS, delivery, members, finance, and franchising, then applies maturity assessment, vendor scoring, HACCP controls, AI-use-case prioritization, and ROI analysis. It is intended for operators and advisors planning technology choices and rollout, and its license limits use to personal learning, research, and non-commercial work.

IT Consulting Workbench helps consultants and enterprise teams carry an IT or AI transformation engagement from the first conversation to a defensible diagnosis, proposal, business case, and roadmap. It supplies a structured workflow and reusable templates for requirements, technology assessment, architecture, and delivery, with cost-and-return models to support decisions. The project is for personal learning, research, and non-commercial use; commercial adoption requires written authorization.

Business Analysis Workbench helps analysts turn a vague business question into structured analysis and a decision-ready document. It guides work from strategy, market, and customer questions through competition, financial modeling, requirements, and solution evaluation, with reusable frameworks and professional templates. The project is for personal learning, research, and non-commercial use; commercial adoption requires written authorization.

B2B PM Workbench helps product managers turn complex enterprise-product questions into requirements, designs, and delivery-ready documents. Its staged workflow covers research, prioritization, permission, approval, multi-tenant, and AI-product decisions, with outputs such as PRDs, design documents, diagrams, and acceptance criteria. The project is for personal learning, research, and non-commercial use; commercial adoption requires written authorization.

AI PM Workbench helps teams take an AI product from opportunity assessment to a governed launch plan. It guides model and architecture choices, prompt and context design, RAG and agent patterns, evaluation, UX, safety, and pricing while making quality, latency, cost, and risk explicit trade-offs. It also covers red teaming and the EU AI Act. The project is for personal learning, research, and non-commercial use; commercial adoption requires written authorization.

Retail Digital AI Expert is a Chinese-language workbench for retail transformation across convenience stores, supermarkets, apparel, discount retail, DTC, e-commerce, franchises, and large chains. It combines maturity assessment, vendor selection, five-year TCO and ROI analysis, and AI-use-case prioritization, helping teams move from current-state diagnosis to a roadmap and proof-of-concept plan. Its license limits use to personal learning, research, and non-commercial work.

Restaurant Digital AI Expert helps food-service operators and consultants assess digital transformation across restaurant formats and business chains. It combines a five-dimension maturity model with vendor selection, AI-scenario prioritization, ROI analysis, and food-safety frameworks, covering supply, kitchen operations, POS, delivery, members, and franchising. It is a methodology workbench, and its license limits use to personal learning, research, and non-commercial work.

it-consulting-workbench helps consultants run IT strategy or transformation engagements from initial diagnosis through delivery and closeout. Its eight-stage workflows cover strategy, enterprise architecture, technology due diligence, financial cases, cloud migration, data governance, security assessment, and change management, with templates and reference methods for repeatable deliverables.

ba-workbench helps business analysts turn questions about markets, customers, competition, finance, and operations into structured analysis and decision documents. It combines more than 100 frameworks, reusable templates, and eight BA role profiles for industry research, business cases, competitor analysis, and stakeholder planning.

Prediction Markets Skill provides read-only access to public Kalshi and Polymarket data for Claude Code, Codex, and Cursor. Agents can locate markets, inspect order books and price history, estimate implied probability, and match equivalent markets across venues. It uses only the Python standard library and deliberately excludes trading, wallet access, and API keys.

ai-pm-workbench helps AI product teams move from opportunity assessment to a product plan with governance in mind. It brings together methods for data strategy, model and architecture choices, RAG and agent design, evaluation, safety, observability, pricing, and compliance, with more than 60 frameworks and 20 deliverables.

React Native Debugger combines the legacy remote debugger with React Inspector, Redux DevTools, and Apollo Client DevTools in a standalone app. It is intended for older Remote Debugger workflows and does not currently support Hermes, JSI, or React Native's New Architecture.

Catnip creates containerized workspaces with managed Git worktrees so multiple Claude Code sessions can run in parallel. Its web and native mobile interfaces, CLI, and SSH access expose full terminals, while port detection and a built-in proxy let you preview services from the workspace. It can run in Codespaces, devcontainers, or locally, but the current workflow is optimized for Claude Code and broader agent support is still planned.

Give Riffkit a successful TikTok or uploaded clip and it will study the hook, pacing, and emotional beats before generating new footage around your product, character, and story. The hosted service can return voiceover, timed captions, a cover, post copy, and hashtags in English or Spanish without re-uploading the source footage. Generation requires a Riffkit account and is billed by the finished video's duration.

Build import-ready Moodle CodeRunner XML with prompts, starter code, model solutions, and visible or hidden tests. Each question is compiled and executed against a Jobe server before delivery, with support for Java, Python, C, C++, and Node.js. A Jobe server is required for validation, while Moodle CodeRunner is the target environment for the resulting XML.

testfrisk inspects branches added by a diff, such as if, case, catch, and throw paths, and checks that a test actually drives execution through each one. It focuses on per-branch risk instead of an average coverage percentage and can write the missing test when the behavior is clear. The skill works across several coding agents and needs no key, account, or extra dependency.