Skip to the rows

agentsclimarketplace

Navigate aie europe 2026

Skill hiteshbandhu/skills-i-use/skills/ai-engineer-talks/navigate-aie-europe-2026

Navigates AI Engineer Europe 2026 keynote themes — MCP and skills, agent orchestration, code mode, application layer shifts, judgment vs automation, replacing large codebases with skills, and platform talks (Vercel, Cloudflare, Anthropic, Cursor, OpenClaw). Use when planning 2026 agent architecture, MCP adoption, or skill-first development; or when the user says "AIE Europe 2026", "future of MCP", "code mode", "end of apps", "12k LOC skill".From its SKILL.md

Install

npx -y skills add hiteshbandhu/skills-i-use --skill navigate-aie-europe-2026

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/navigate-aie-europe-2026 ~/.claude/skills/` and 1 more.

SKILL.md

2.9 KB, 669 tokens by cl100k_base, as published. Nobody here has run it

Navigate AIE Europe 2026

Action playbook from fourteen AIE Europe 2026 keynotes. Do not summarize talks — pick a workflow and execute it.

Supporting files:

workflows.md — workflows A–N
source-index.md — src-NNN → learnings

Optional deliverables: {SKILL_OUTPUT_DIR}/navigate-aie-europe-2026/

Step 0 — Pick workflow

What is the user trying to do?
├─ Agent orchestration / AgentCraft                     → A  [src-001]
├─ Agents beyond chat (legal/work UX)                   → B  [src-002]
├─ Quality bar in slop era (pi / craft)                 → C  [src-003, src-010]
├─ Code mode / code-as-interface                        → D  [src-004]
├─ How AI changes engineering (Pragmatic Engineer)      → E  [src-005]
├─ Gemini / DeepMind research direction                 → F  [src-006]
├─ Replace large code with small skills                 → G  [src-007]
├─ Software fundamentals still matter                   → H  [src-008]
├─ OpenClaw / local agent state                         → I  [src-009]
├─ End of apps / new UX containers                      → J  [src-011]
├─ Judgment vs friction (human in loop)                 → K  [src-012]
├─ MCP roadmap & agent stack                            → L  [src-013]
├─ New application layer (Vercel)                       → M  [src-014]
└─ Skills + subagents in products                       → G  [src-007] + [L]

Open workflows.md.

Install

cp -r skills/navigate-aie-europe-2026 ~/.claude/skills/
cp -r skills/navigate-aie-europe-2026 ~/.cursor/skills/

Source: playlists/aie-europe-2026-keynotes/.

Cross-cutting rules

Rule	Source
2026 agents = skills + MCP + production hardening	[src-013 @ 5:31]
Load prompts/skills only when user invokes	[src-007 @ 8:39]
Code mode: let executable code carry intent	[src-004]
Judgment remains human; friction is signal	[src-012]
Fundamentals (types, tests) still gate quality	[src-008]

Output to user

Name workflow (A–N) and deliverable
Artifacts under ./skill-outputs/navigate-aie-europe-2026/ when requested

Invocation examples

@navigate-aie-europe-2026 MCP adoption plan for our agent
should we replace our rules engine with a 200-line skill?
code mode vs tool-calling for our workflow engine

What ships with it: 3 files

7.6 KB alongside SKILL.md

Gives 0 of the 12 instructions most containers cloud skills give in 669 tokens

Counted across 607 of the 705 authors here whose files we hold, read 2026-09-06

Run as non-root userin 34 of 607, across 27 files
Use multi-stage buildsin 29 of 607
Set resource requests and limitsin 24 of 607, across 20 files
Configure liveness and readiness probesin 18 of 607, across 14 files
Use named volumes for persistent datain 14 of 607, across 9 files
Pin base image versionsin 14 of 607
Set up environment variablesin 14 of 607, across 10 files
Pin provider versionsin 14 of 607
Apply least privilege RBAC permissionsin 10 of 607, across 7 files
Create a dockerignore filein 10 of 607
Use remote state with lockingin 9 of 607
Pin base images by digestin 9 of 607, across 8 files

Said here and by no other author read

Pick a workflow and execute it
Open workflows.md
Load prompts and skills only when user invokes

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 623,215. 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.