Weekly competitive briefing skill
Hermes Agent ran the same Monday competitive monitoring prompt for six weeks and rewrote its own underlying skill four times.
The same task fell from 20 minutes in week one to 12 in week four and 8 by week six, with better competitor patterns surfaced.
Overview
How it was set up
Hermes Agent from Nous Research, with skills saved as files in ~/.hermes/skills/. It can run on Claude, GPT-4o, Gemini, or local Llama models.
Worth knowing
Full skill files and the rollout plan are behind a paywall, and the timings are the author's own logs.
A prompt to start from
The source does not show the prompt.
Sources 1
History
- Source published
- 2026-05-01
- Added to Agentic Feats
- 2026-10-13
- Pick
- No
- Markdown copy
- /c/weekly-competitive-briefing-skill-hermes-agent.md
More in research
36 featsResultIt created the text file as asked, but after clicking a result it took a screenshot too early and hallucinated the answer.
ResultOperator handled tour search and lesson plan but was slow; adding three grocery items took 15 minutes and an Uber price check took five.
ResultThe draft was usable but weaker than accepted NSF summaries; thinking mode helped, though it began hallucinating and misreading the sources.