juanquy/AI-data-refinery

A high-performance, edge-native Data Refinery Engine built on Cloudflare's serverless AI stack (Workers, Workers AI, D1, KV, Vectorize) designed to continuously ingest unstructured data, refine it into pristine machine-readable structured intelligence, compute semantic diffs, and serve it directly to AI agents via the MCP

0Stars on the repository
51Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
customA LICENSE file GitHub cannot name, so bodies are not copied

juanquy/AI-data-refinery

Skill Claude CodeCodex

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

not rated 0 yesterday A 56 tokens

bmad-agent-analyst

02

juanquy/AI-data-refinery

Skill Claude CodeCodex

Strategic business analyst and requirements expert. Use when the user asks to talk to Mary or requests the business analyst.

not rated 0 yesterday A 30 tokens

juanquy/AI-data-refinery

Skill Claude CodeCodex

System architect and technical design leader. Use when the user asks to talk to Winston or requests the architect.

not rated 0 yesterday A 27 tokens

bmad-agent-dev

04

juanquy/AI-data-refinery

Skill Claude CodeCodex

Senior software engineer for story execution and code implementation. Use when the user asks to talk to Amelia or requests the developer agent.

not rated 0 yesterday A 30 tokens

bmad-agent-pm

05

juanquy/AI-data-refinery

Skill Claude CodeCodex

Product manager for PRD creation and requirements discovery. Use when the user asks to talk to John or requests the product manager.

not rated 0 yesterday A 31 tokens

bmad-architecture

07

juanquy/AI-data-refinery

Skill Claude CodeCodex

Produce the architecture: a lean spine of invariants that keeps everything built from it consistent, projected into whatever format the work needs. Use when the user says "create the architecture", "create technical architecture", "architecture spine", or "create a solution design".

not rated 0 yesterday A 57 tokens

bmad-brainstorming

08

juanquy/AI-data-refinery

Skill Claude CodeCodex

Facilitate a brainstorming session using diverse creative techniques. Use when the user says 'help me brainstorm' or 'help me ideate'.

not rated 0 yesterday A 35 tokens

bmad-build

10

juanquy/AI-data-refinery

Skill Claude CodeCodex

Implements any user intent, requirement, story, bug fix or change request by producing clean working code artifacts that follow the project's existing architecture, patterns and conventions. Use when the user wants to build, fix, tweak, refactor, add or modify any code, component or feature.

not rated 0 yesterday A 61 tokens

juanquy/AI-data-refinery

Skill Claude CodeCodex

LLM-assisted human-in-the-loop review. Make sense of a change, focus attention where it matters, test. Use when the user says "checkpoint", "human review", or "walk me through this change".

not rated 0 yesterday A 49 tokens

bmad-code-review

12

juanquy/AI-data-refinery

Skill Claude CodeCodex

Adversarial code review using parallel review layers and structured triage. Use when the user says "run code review" or "review this code".

not rated 0 yesterday A 35 tokens

bmad-correct-course

13

juanquy/AI-data-refinery

Skill Claude CodeCodex

Manage significant changes during sprint execution. Use when the user says "correct course" or "propose sprint change".

not rated 0 yesterday A 29 tokens

bmad-create-story

17

juanquy/AI-data-refinery

Skill Claude CodeCodex

Deprecated: bmad-build is now the official implementation method. Only use this when explicitly invoked by name.

not rated 0 yesterday A 28 tokens

bmad-customize

18

juanquy/AI-data-refinery

Skill Claude CodeCodex

Authors and updates customization overrides for installed BMad skills. Use when the user says 'customize bmad', 'override a skill', 'change agent behavior', or 'customize a workflow'.

not rated 0 yesterday A 44 tokens

bmad-deep-recon

19

juanquy/AI-data-refinery

Skill Claude CodeCodex

Decision-grade research, three ways: draft a deep-research prompt for the user to run in their own tool (ChatGPT, Gemini, Grok, Perplexity, …), process a finished research report — file it, distill a succinct cited summary with metadata that downstream skills consume without reprocessing — or run the research here…

not rated 0 yesterday A 167 tokens

bmad-dev-auto

20

juanquy/AI-data-refinery

Skill Claude CodeCodex

Deprecated: forwards to bmad-build-auto. Do not use unless invoked by name.

not rated 0 yesterday A 22 tokens

bmad-dev-story

21

juanquy/AI-data-refinery

Skill Claude CodeCodex

Deprecated: bmad-build is now the official implementation method. Only use this when explicitly invoked by name.

not rated 0 yesterday A 28 tokens

juanquy/AI-data-refinery

Skill Claude CodeCodex

Deprecated — forwards to bmad-project-context. Use when the user says "document this project" or "generate project docs".

not rated 0 yesterday A 30 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: