agentsclimarketplace

Dify rag pm

Skill samzong/agent-brains/agents/dify-rag-pm/skills/dify-rag-pm

Personal agent brain catalog for coding agents: AGENTS.md, SOUL.md, MEMORY.md, skills, workflows, and a bundled loader.

Install
npx -y skills add samzong/agent-brains --skill dify-rag-pm

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Analyze, plan, design, and review Dify Dataset, Knowledge, and RAG product work. Use for Dataset lifecycle, Workflow Knowledge Retrieval nodes, field contracts, user stories, and KnowledgeFS-to-Dify product translation.

SKILL.md

1.9 KB, as published. Nobody here has run it

dify-rag-pm Skill

Use this skill when analyzing, planning, designing, or reviewing Dify Dataset / Knowledge / RAG product work.

Trigger Situations

  • Dataset lifecycle, source ingestion, document management, indexing, retrieval, metadata, or hit testing.
  • Workflow Knowledge Retrieval node fields or runtime behavior.
  • KnowledgeFS to Dify Dataset 2.0 mapping.
  • Product requirements, user stories, feature matrix, or prototype design for Dataset/RAG.

Workflow

  1. Read code first.
  2. Identify the product surface.
  3. Extract fields and runtime rules.
  4. Separate current behavior from proposal.
  5. Translate technical internals into Dify user language.
  6. Produce field contract and user story map.
  7. State non-goals and invalid combinations.

Required Evidence

Prefer these source areas:

  • /Users/x/git/lg/dify/api/models/dataset.py
  • /Users/x/git/lg/dify/api/models/enums.py
  • /Users/x/git/lg/dify/api/services/dataset_service.py
  • /Users/x/git/lg/dify/api/core/rag/retrieval/dataset_retrieval.py
  • /Users/x/git/lg/dify/api/core/workflow/nodes/knowledge_retrieval/
  • /Users/x/git/lg/dify/web/models/datasets.ts
  • /Users/x/git/lg/dify/web/app/components/datasets/
  • /Users/x/git/lg/dify/web/app/components/workflow/nodes/knowledge-retrieval/
  • /Users/x/git/lg/knowledge-fs/packages/core/src/models.ts
  • /Users/x/git/lg/knowledge-fs/packages/api/src/retrieval-types.ts
  • /Users/x/git/lg/knowledge-fs/packages/api/src/gateway-route-schemas.ts

Output Checklist

  • Current behavior
  • Code evidence
  • Product implication
  • Dataset 2.0 proposal
  • Field contract
  • Story map
  • Information flow
  • Non-goals
  • Prototype implications

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.