# Agent skills A pack of 9 talks from the AI Engineer YouTube channel, in the order to watch them. 5h 10m of video. Page: https://aietalks.com/packs/skills An API tells an agent what it can call, but not how your team gets a job right. Skills package that missing procedure in a folder whose details load only when needed. The format becomes practical by choosing reliable triggers, separating steps from reference material, preferring constraints to a procedural novel, and using scripts when a step should be deterministic. Cursor's worktree rewrite tests the provocative case for moving product behavior from thousands of lines of code into instructions, including the isolation failures that follow. Langfuse and Supabase make maintenance concrete: product documentation has to keep pace with the product, and an eval can be wrong even when the skill is right. Regression tests come next, followed by retrieval, ownership and versioning when one useful folder grows into shared infrastructure. ## This pack is for you if - You keep giving an agent the same procedural guidance in prompts or review comments. - Your product has an API or MCP server, but agents still use it in the wrong sequence. - Your team shares skills and now needs tests, versioning, ownership and a way to retire them. ## The talks, in order ### 1. Skills are the New SDKs Elvin Aghammadzada, DataRobot | 26:40 | AI Engineer World's Fair 2026 Video: https://www.youtube.com/watch?v=LC3-P7v3yoI Summary: https://aietalks.com/talks/skills-are-the-new-sdks.md Why first: Aghammadzada explains why APIs, tools and human documentation still leave an agent without the workflow knowledge needed to use a platform well. Skills fill that gap through progressive loading. Pocock follows with the practical question: what makes one of those folders good enough for the model to find and follow? ### 2. Building Great Agent Skills: The Missing Manual Matt Pocock, AI Hero | 20:43 | AI Engineer World's Fair 2026 Video: https://www.youtube.com/watch?v=UNzCG3lw6O0 Summary: https://aietalks.com/talks/building-great-agent-skills-the-missing-manual.md Why here: Aghammadzada defines the gap and the progressive-loading pattern. Pocock turns that pattern into an editing checklist for triggers, structure, steering and pruning, then Nisi and Proser put the same choices into a complete build-and-test walkthrough. ### 3. Full Walkthrough: Writing & Using Skills Nick Nisi & Zack Proser, WorkOS | 1:21:03 | AI Engineer Europe 2026 Video: https://www.youtube.com/watch?v=pFsfax19yOM Summary: https://aietalks.com/talks/full-walkthrough-writing-using-skills.md Why here: Pocock supplies compact rules for a skill file. Nisi and Proser show the surrounding work: package references and scripts, share the folder across agents, and compare runs with and without it. Gomes then tests a more radical use for the format, replacing a large implemented feature with instructions. ### 4. Replacing 12K LoC with a 200 LoC Skill David Gomes, Cursor | 19:22 | AI Engineer Europe 2026 Video: https://www.youtube.com/watch?v=WE_Gnowy3uw Summary: https://aietalks.com/talks/replacing-12k-loc-with-a-200-loc-skill.md Why here: Nisi and Proser treat skills as portable additions to an agent. Gomes moves product behavior into them, deleting thousands of lines while accepting that prompt-based isolation is weaker than code-enforced boundaries. Klingen follows with a less dramatic but more common maintenance problem: product knowledge goes stale. ### 5. Skill issue: Lessons from skilling up coding agents to use Langfuse Marc Klingen, ClickHouse | 24:09 | AI Engineer Europe 2026 Video: https://www.youtube.com/watch?v=vNCY9kXXyDQ Summary: https://aietalks.com/talks/skill-issue-lessons-from-skilling-up-coding-agents-to-use-langfuse.md Why here: Gomes shows the leverage and the new failure modes that appear when behavior moves into a skill. Klingen shows how to maintain one against a changing product: inspect traces, point to living documentation, and resist an optimizer that rewards short runs at the expense of current information. Rodrigues then tests the same approach against a product rule whose absence can expose data. ### 6. Skill Issue: How We Used AI to Make Agents Actually Good at Supabase Pedro Rodrigues, Supabase | 1:18:41 | AI Engineer Europe 2026 Video: https://www.youtube.com/watch?v=GmAQKINjv1E Summary: https://aietalks.com/talks/skill-issue-how-we-used-ai-to-make-agents-actually-good-at-supabase.md Why here: Klingen keeps changing product knowledge outside the skill and measures whether the agent fetches it. Rodrigues adds a rule that cannot be missed, then catches his own evaluator checking the wrong database metadata. Schmid follows by turning those hard-won lessons into a smaller, repeatable test discipline. ### 7. Don't Ship Skills Without Evals Philipp Schmid, Google DeepMind | 21:46 | AI Engineer World's Fair 2026 Video: https://www.youtube.com/watch?v=0vphxNt4wyk Summary: https://aietalks.com/talks/dont-ship-skills-without-evals.md Why here: Rodrigues shows both a skill changing agent behavior and a grader misreading the result. Schmid generalizes the method into positive and negative trigger cases, isolated trials, cheap assertions and ablation tests. Miraje then asks what changes when skills become the main feature layer of a harness. ### 8. Skills are New Features: Building a Skill-Centric Harness Yogendra Miraje, FactSet | 17:24 | AI Engineer World's Fair 2026 Video: https://www.youtube.com/watch?v=7jjudsEhBtM Summary: https://aietalks.com/talks/skills-are-new-features-building-a-skill-centric-harness.md Why here: Schmid gives one skill a lifecycle through evaluation and retirement. Miraje scales that discipline to a skill-centric harness, where descriptions route tasks and a growing registry needs retrieval and governance. Touil widens the same argument from one harness to an organization with many teams and workflows. ### 9. AI-Native Organisations Run on Skills: How to Structure and Scale Them Imad Touil, QuantumBlack | 20:31 | AI Engineer World's Fair 2026 Video: https://www.youtube.com/watch?v=M05vON8i0aI Summary: https://aietalks.com/talks/ai-native-organisations-run-on-skills-how-to-structure-and-scale-them.md Why last: Miraje explains why a skill-centric harness needs retrieval and governance. Touil shows what that demand becomes across many teams: a searchable catalog, dependencies, versions, access controls, evaluation, observability and named owners. The pack ends where a useful personal technique becomes shared infrastructure with a maintenance bill. ## Editor's note Gomes checks both the assigned worktree and the primary checkout, while Klingen and Schmid compare behavior before and after a skill changes. Those tests need more than the agent's final answer. Kitaru records the inputs, outputs and tool calls from a run, then replays the same task so a team can see whether a revised skill changed the route as well as the result. Written by the AIE Talks editors (the Kitaru team), not by any of the speakers.