dify-rag-pm

dify-rag-pm is a skill for Claude Code, Codex from samzong/agent-brains. It costs 52 tokens per session (466 once invoked), scanned A, original, MIT.

A planning and review guide for Dify datasets and knowledge retrieval. Dify is a platform for building AI applications, while retrieval means finding relevant stored information for an answer.

In plain words
What is it for?
Use it to plan dataset life cycles, document ingestion, indexing, metadata, retrieval settings, and workflow knowledge-retrieval fields. It also supports user stories, feature comparisons, prototypes, and mapping KnowledgeFS concepts to Dify datasets.
Why use it?
It helps turn technical Dify behavior into clear product requirements and user-facing explanations. It also helps distinguish existing behavior from proposed changes and identify invalid combinations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/x/git/lg/dify/api/models/dataset.py.

Good fit Use it to plan dataset life cycles, document ingestion, indexing, metadata, retrieval settings, and workflow knowledge-retrieval fields. It also supports user stories, feature comparisons, prototypes, and mapping KnowledgeFS concepts to Dify datasets.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dify-rag-pm

README.md
[![agentmods](https://agentmods.dev/badge/skills/samzong/agent-brains/dify-rag-pm/github.svg)](https://agentmods.dev/skills/samzong/agent-brains/dify-rag-pm)
Your own site
<a href="https://agentmods.dev/skills/samzong/agent-brains/dify-rag-pm"><img src="https://agentmods.dev/badge/skills/samzong/agent-brains/dify-rag-pm/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dify-rag-pm

Your own site · 80×15
<a href="https://agentmods.dev/skills/samzong/agent-brains/dify-rag-pm"><img src="https://agentmods.dev/badge/skills/samzong/agent-brains/dify-rag-pm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 466 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.00466
Opus 5 $0.00026 $0.00233
Sonnet 5 $0.00010 $0.00093
Haiku 4.5 $0.00005 $0.00047

Measured 9d ago against content hash a2f138fa401a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

dify-rag-pm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/dify-rag-pm/skills/dify-rag-pm/SKILL.md · 54 lines

What it actually says

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
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 54 lines · 52 tokens per session scan A a2f138fa401a

Subscribe to this mod's changes

dify-rag-pm is a skill published in the GitHub repository samzong/agent-brains (6 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 466 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

jetson-inference-mem-tune

Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.

NVIDIA/skills · 50 tokens

kg-builder

Designs and builds knowledge graphs from documents — ontology modeling with domain/range constraints, entity/relation/event extraction, entity resolution, provenance and supersession, and GraphRAG serving. Use when asked to "build a knowledge graph", "design an ontology", "extract entities and relations", "deduplicate…

Mathews-Tom/armory · 100 tokens

rag-auditor

Evaluates RAG pipeline quality across retrieval (precision, recall, MRR) and generation (groundedness, hallucination rate). Triggers on: "audit RAG pipeline", "RAG quality", "hallucination detection", "why is RAG failing", "grounding check". NOT for general architecture audits, use architecture-reviewer.

Mathews-Tom/armory · 76 tokens

rag-implementation

Comprehensive guide to implementing RAG systems including vector database selection, chunking strategies, embedding models, and retrieval optimization. Use when building RAG systems, implementing semantic search, optimizing retrieval quality, or debugging RAG performance issues.

stefan-jansen/claude-code-toolkit · 50 tokens

wshobson-rag-implementation

Skill "wshobson-rag-implementation" from ItamarZand88/awesome-agent-conventions, covering rag implementation, when to use this skill, core components, 1. vector databases and 2. embeddings.

ItamarZand88/awesome-agent-conventions · 0 tokens

ai-product

Expert in shipping production-grade AI-powered features — LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, safety and guardrails, streaming, and cost optimization.

coco-research/coco · 43 tokens