Dossier May Hermes: Les skills (Episode 4)

Dossier May Hermes: Les skills (Episode 4)

May’s Files Hermes: Skills (Episode 4)

Title history
  • Dossier May Hermes: Les skills (Episode 4) — observed on 20261111-1954 UTC (YouTube)

by Max Oro · View the channel on PSI

Applied Sciences & Engineering Video Games UDDigital Lifestyle and online world: consumer and user guidesUDXComputer games
🎙 Max Oro 👥 264 📅 June 22, 2026 ⏱ 11 min 👁 93 📄 tutorial 🧭 2026-11-11
Available in: English (current) Français

Keywords

skillagent IAworkflowmémoireprocédure

Summary

In this fourth episode of the ‘May Hermes Dossier’, Max Oro explains the concept of ‘skills’ within the Hermes AI agent. He distinguishes skills from simple prompts and memory, emphasizing that skills are reusable procedures that the agent loads on demand. The video covers the definition, storage location (in Hermes folders), and demonstration of writing a skill. He introduces the idea of a ‘curator skill’ that periodically optimizes existing skills. The author illustrates with examples from his own agency, showing how skills are organized into bundles to handle complex workflows like creating YouTube videos. The episode includes a live demo where Hermes invokes multiple skills to generate a video outline, slides, and thumbnail prompt. He concludes with advice on writing effective skills: clear triggers, concrete steps, pitfalls, and verifiable checklists. The presentation targets users of the Hermes agent, aiming to make them more efficient by converting their methods into reusable workflows.

151 words

Critical Evaluation

Value of the Information & Strength of the Argument

The video provides practical, hands-on value for users of the Hermes agent, demonstrating a concrete workflow for creating and using skills. The argumentation is coherent, relying on the author’s professional experience and clear analogies (SOPs, memory vs. skills). The main claims are supported by live examples, which increases credibility. However, the video offers limited critical analysis or comparison with alternative approaches, and the technical depth is moderate. The author’s enthusiasm for the product is evident, but arguments are more illustrative than systematically evidenced.

Scientific Rigor, Source Quality, Title Accuracy

The scientific rigor is moderate; the content is based on the author’s expertise and product-specific knowledge rather than peer-reviewed sources. The description provides links to the author’s booking page and official website, which serve as practical references but not as scientific evidence. The title accurately reflects the content, and the video is well-structured with clear chapters. No external sources are cited, which is typical for tutorial content. The public reception appears positive (7 likes on 93 views), but no comment analysis is possible due to absence of data.

186 words

Title / Content Match

Title accurately reflects the video content, which focuses on defining and using skills in the Hermes agent.

Quality & Reliability

6/10

Clear explanation with practical demonstration; relies on the author's experience, not on external scientific references.

Chapters

Cited Sources

  • Appel de découverte – May — L'auteur invite à réserver un appel découverte pour en savoir plus sur les skills.
  • Site de May — Présentation de l'agent Hermes et de la société May.

Contribution & Novelties

This episode offers a pragmatic introduction to the concept of ‘skills’ in a specific AI agent, showing how procedural knowledge can be structured and reused. The originality lies in the concrete demonstration and the emphasis on treating skills as SOPs for AI. It bridges the gap between abstract ‘memory’ and executable workflows, providing a clear mental model.

Pour aller plus loin :

102 words

Radar Profile

The radar shows a balanced profile: high on information quantity and quality, moderate on technical level and reliability. This reflects a tutorial that is informative and accessible but lacks deep technicals or external validation.

Reliability 6/10