agentsclimarketplace
Sign in

Learn summit 2023 remote

Skill hiteshbandhu/skills-i-use/skills/ai-engineer-talks/learn-summit-2023-remote

Applies AI Engineer Summit 2023 remote-talk playbooks for evals, hybrid RAG grounding, model selection, fine-tuning, prompt ops, multimodal apps, coding-agent maturity, and career transition from fullstack. Use when reproducing summit remote lessons, comparing LLM eval tools, or scoping hybrid retrieval; or when the user says "summit 2023 remote", "llmeval", "hybrid context query", "AI maturity model".From its SKILL.md

Install
npx -y skills add hiteshbandhu/skills-i-use --skill learn-summit-2023-remote

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 2 commands, including `cp -r skills/learn-summit-2023-remote ~/.claude/skills/` and 1 more.

SKILL.md

2.8 KB, 664 tokens by cl100k_base, as published. Nobody here has run it

Learn Summit 2023 remote talks

Action playbook from eleven remote sessions at AI Engineer Summit 2023. Do not summarize talks — pick a workflow and execute it.

Supporting files:

Optional deliverables: {SKILL_OUTPUT_DIR}/learn-summit-2023-remote/

Step 0 — Pick workflow

What is the user trying to do?
├─ Ship LLM evals in production (LLMeval)                    → A  [src-001]
├─ Hybrid context query / RAG grounding                    → B  [src-002]
├─ Viral AI app / codegen product (10k apps)               → C  [src-003]
├─ Career path: fullstack → AI engineer                    → D  [src-004]
├─ Pick the right model for a use case                     → E  [src-005]
├─ No-code / low-friction fine-tuning                        → F  [src-006]
├─ Prompt engineering tactics + prompt management            → G  [src-007]
├─ Multimodal TS apps (ModelFusion)                          → H  [src-008]
├─ Code AI maturity model (SAE levels)                       → I  [src-009]
├─ AI software engineer stack (embeddings, retrieval)        → J  [src-010]
└─ Generative infinite game / creative AI loops              → K  [src-011]

Open the matching section in workflows.md.

Install

cp -r skills/learn-summit-2023-remote ~/.claude/skills/
cp -r skills/learn-summit-2023-remote ~/.cursor/skills/

Source: playlists/ai-engineer-summit-2023-remote-talks/.

Cross-cutting rules

RuleSource
Store prompts/configs; eval before fine-tune[src-001 @ 0:00:53]
RAG needs deliberate pipeline, not naive retrieval[src-002 @ 0:01:26]
Model choice is use-case specific, not one-size[src-005 @ 0:00:45]
Prompt engineering ≠ prompt hoarding — use tooling[src-007 @ 0:00:18]
Maturity model: partial → supervised agent autonomy[src-009 @ 0:04:04]

Output to user

  1. Name workflow (A–K) and deliverable
  2. Artifacts under ./skill-outputs/learn-summit-2023-remote/ when requested

Invocation examples

@learn-summit-2023-remote set up evals like the LLMeval talk
hybrid grounding query design for our copilot
which workshop path for fullstack → AI engineer?

What ships with it: 3 files

7.5 KB alongside SKILL.md

Gives 0 of the 12 instructions most learn study skills give in 664 tokens

Counted across 545 of the 593 authors here whose files we hold, read 2026-09-06

  • Treat the current directory as a teaching workspacein 20 of 545, across 17 files
  • Teach knowledge first then practice skillsin 19 of 545, across 16 files
  • Design lessons which build long-term retentionin 15 of 545, across 12 files
  • Save each lesson as a self-contained HTML filein 15 of 545, across 12 files
  • Question the user on why they want to learn thisin 15 of 545, across 12 files
  • Reuse components from the assets directoryin 14 of 545, across 11 files
  • Never trust your parametric knowledgein 13 of 545, across 10 files
  • Record user preferences in NOTES.mdin 11 of 545, across 8 files
  • Ground all teaching in the MISSION.md documentin 11 of 545, across 8 files
  • Save each lesson to the lessons directoryin 8 of 545
  • Question the user if the mission is unclearin 7 of 545
  • Gather primary sources onlyin 7 of 545, across 4 files

Said here and by no other author read

  • Pick a workflow and execute it
  • Open the matching section in workflows.md
  • Store prompts and configs
  • Eval before fine-tune
  • Build a deliberate RAG pipeline

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.