agentsclimarketplace
Sign in

Build aiewf 2024 rag

Skill hiteshbandhu/skills-i-use/skills/ai-engineer-talks/build-aiewf-2024-rag

Runs workflows for AIEWF 2024 RAG talks — layout-aware ingest, GraphRAG, eval-driven tuning, Pydantic structured IO, MongoDB vectors, EMT memory, construction vertical agents, personal-assistant data graphs. Use when the user says "RAG", "GraphRAG", "chunking PDF", "Pydantic RAG", or AIEWF retrieval playlist.From its SKILL.md

Install
npx -y skills add hiteshbandhu/skills-i-use --skill build-aiewf-2024-rag

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

2 things to look at

  • 1 stars1 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.
  • runs commandsInstructs the agent to run 3 commands, including `cp -r skills/build-aiewf-2024-rag ~/.claude/skills/` and 2 more.

SKILL.md

2.4 KB, 572 tokens by cl100k_base, as published. Nobody here has run it

Build AIEWF 2024 RAG stacks

Action playbook from eight AI Engineer / World's Fair talks. Do not summarize talks — pick a workflow and execute it.

Supporting files (read when needed):

  • workflows.md — workflows A–H (steps, deliverables, stop conditions)
  • source-index.md — src-NNN → talk learnings in ingest-into-skills

Optional: {SKILL_OUTPUT_DIR}/build-aiewf-2024-rag/

Step 0 — Pick workflow

Use the decision tree below. Open the matching section in workflows.md.

What is the user trying to do?
├─ Fix PDF/table RAG failures (layout ingest)           → A
├─ Add knowledge graphs (GraphRAG)                        → B
├─ Tune RAG with eval compass                             → C
├─ Harden LLM IO with Pydantic/Instructor                 → D
├─ Unified doc+vector on MongoDB                          → E
├─ Explore beyond RAG (EMT memory tokens)                 → F
├─ Vertical spec-heavy RAG (construction)                 → G
└─ Personal assistant structured data (minimize LLM)    → H

Stop summarizing once a workflow is identified — run its checklist.

Install

cp -r skills/build-aiewf-2024-rag ~/.claude/skills/
cp -r skills/build-aiewf-2024-rag ~/.cursor/skills/
cp -r skills/build-aiewf-2024-rag ~/.codex/skills/

From skills-i-use or ingest-into-skills (playlists/rag-llm-frameworks-aie-world-s-fair-2024/).

Cross-cutting rules

RuleSource
Fix ingest before more retrieval tricks[src-002 @ 1:21]
Eval-driven chunk/rerank changes[src-004 @ 1:48]
Structured outputs via Pydantic[src-005 @ 12:19]

Disputed steps: see source-index.md. Name workflow A–H; save artifacts to ./skill-outputs/build-aiewf-2024-rag/ when requested; do not auto-commit.

Invocation examples

@build-aiewf-2024-rag our RAG fails on tables in PDFs
when should we add GraphRAG?

What ships with it: 3 files

4.3 KB alongside SKILL.md

Gives 0 of the 12 instructions most rag retrieval skills give in 572 tokens

Counted across 199 of the 213 authors here whose files we hold, read 2026-09-06

  • Enable caching for frequent queriesin 14 of 199, across 5 files
  • Enable MMR for diverse resultsin 12 of 199, across 5 files
  • Enable binary quantization to reduce memoryin 11 of 199, across 4 files
  • Initialize the database with dimensions matching the embedding modelin 11 of 199, across 4 files
  • Start the similarity threshold at 0.7in 11 of 199, across 4 files
  • Check database statistics when diagnosing slow searchin 11 of 199, across 4 files
  • Export and import vectors as JSONin 10 of 199, across 3 files
  • Match index dimension to the embedding modelin 10 of 199, across 9 files
  • Order filters cheap before expensivein 9 of 199, across 2 files
  • Generate a runnable scaffold in the user's stackin 9 of 199, across 2 files
  • Recommend multi-action scoring when frequent tuning is expectedin 9 of 199, across 2 files
  • Batch store documents for bulk insertsin 9 of 199, across 2 files

Said here and by no other author read

  • Pick a workflow and execute its checklist
  • Open the matching section in workflows.md
  • Save artifacts when the user wants files
  • use the decision tree to pick a workflow
  • read supporting files when needed
  • fix ingest before adding retrieval tricks

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. 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.