agentsclimarketplace

Run summit 2023 workshops

Skill hiteshbandhu/skills-i-use/skills/ai-engineer-talks/run-summit-2023-workshops

Drop-in skills and plugins for your AI development workflows

Install
npx -y skills add hiteshbandhu/skills-i-use --skill run-summit-2023-workshops

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

  • 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.

What its author says it does

Copied from the file, not written here

Runs AI Engineer Summit 2023 workshop playbooks — foundations (101), inference (201), product patterns beyond inference (Rest of the Owl), and Anthropic prompt engineering principles. Use when onboarding to AI engineering, designing inference stacks, or improving task prompts; or when the user says "summit 2023 workshop", "AI engineering 101", "inference workshop", "prompt principles Karina".

SKILL.md

2.7 KB, as published. Nobody here has run it

Run Summit 2023 workshops

Action playbook from four AI Engineer Summit 2023 workshops. Do not summarize talks — pick a workflow and execute it.

Supporting files (read when needed):

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

Optional deliverables: {SKILL_OUTPUT_DIR}/run-summit-2023-workshops/ — see skills-i-use OUTPUT.md.


Step 0 — Pick workflow

What is the user trying to do?
├─ Baseline AI engineering literacy (models, APIs, apps)     → A  [src-003]
├─ Inference serving, latency, cost, deployment              → B  [src-004]
├─ Product architecture beyond the model (LUI, eval, ops)  → C  [src-001]
└─ Task prompt design (Claude / API best practices)          → D  [src-002]

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


Install

cp -r skills/run-summit-2023-workshops ~/.claude/skills/
cp -r skills/run-summit-2023-workshops ~/.cursor/skills/
cp -r skills/run-summit-2023-workshops ~/.codex/skills/

Source corpus: ingest-into-skills playlists/ai-engineer-summit-2023-workshops/.


Cross-cutting rules

RuleSource
AI engineering = systems around models, not prompting alone[src-003 @ 7:17]
Inference is necessary but not sufficient for product value[src-001 @ 0:25]
Prompts steer attention; use task keywords, context, examples[src-002 @ 0:01:33]
Structure: context first, clear task, coherent logical flow[src-002 @ 6:43]
Prefer inference-time compute over retraining when possible[src-002 @ 1:53]

Output to user

  1. Name the workflow (A–D) and deliverable
  2. Save artifacts under ./skill-outputs/run-summit-2023-workshops/ when requested
  3. Do not auto-commit

Invocation examples

@run-summit-2023-workshops walk me through AI engineering 101 topics
design our inference layer using the 201 workshop
improve task prompts using Anthropic principles

Gives 0 of the 12 instructions most prompt engineering skills give

Counted across 563 of the 626 authors here whose files we hold, read 2026-08-06

  • ask at most three clarifying questionsin 22 of 563, across 15 files
  • respond in the user input languagein 14 of 563, across 9 files
  • preserve the original intentin 13 of 563, across 11 files
  • Establish baseline metrics and collect representative examplesin 12 of 563, across 2 files
  • Identify failure modes and prioritize high-impact fixesin 12 of 563, across 2 files
  • Apply prompt and workflow improvements with measurable goalsin 12 of 563, across 2 files
  • Roll back quickly if quality or safety metrics regressin 12 of 563, across 2 files
  • validate changes with tests and roll out in controlled stagesin 12 of 563, across 2 files
  • generate quantitative baseline performance reportsin 12 of 563, across 2 files
  • create representative test scenariosin 12 of 563, across 2 files
  • treat prompts as codein 12 of 563, across 5 files
  • test prompts on diverse inputsin 12 of 563, across 8 files

Said here and by no other author read

  • pick one workflow and execute it
  • read workflows file when needed
  • read source index file when needed
  • save artifacts under skill outputs directory when requested
  • name the workflow and deliverable to the user

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

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.