에λ₯΄λ©”μŠ€ μ—μ΄μ „νŠΈ μŠ€ν‚¬ β€” 에λ₯΄λ©”μŠ€ μ—μ΄μ „νŠΈλ₯Ό μœ„ν•œ 자기 μ§„ν™”, 페λ₯΄μ†Œλ‚˜ 인식 μŠ€ν‚¬ μ»¬λ ‰μ…˜

μž‘μ„±μž

μΉ΄ν…Œκ³ λ¦¬:

← ν”Όλ“œλ‘œ
DEV Community · Ow1onp · 2026-06-20 개발(SW)

Ow1onp

Body:

Hey everyone πŸ‘‹

I’ve been building hermes-agent-skills β€” a production-grade skill collection for Hermes Agent that does three things no other skill pack does:

1. Self-Evolving Skills

Skills aren’t static YAML. The built-in EvolutionEngine tracks 5 health dimensions (usage frequency, success rate, user corrections, freshness, command validity), assigns a health score, and tells you which skills are rotting. Think of it as npm audit for your AI assistant’s capabilities.

2. SOUL.md Persona Awareness

Drop a SOUL.md in your Hermes config β€” naming conventions, comment density, architecture preferences, commit style β€” and every skill that touches code output adapts to it. hermes-skill soul generate bootstraps one in one command. The persona-aware-coding skill reads it at runtime so your agent writes code that actually looks like you wrote it.

3. CLI Toolchain

hermes-skill create my-workflow     # scaffold a standards-compliant SKILL.md
hermes-skill validate skills/       # validate against the Agent Skills Standard
hermes-skill list skills/ -f json   # enumerate with health metadata
hermes-skill soul generate          # bootstrap a persona file

Enter fullscreen mode Exit fullscreen mode

What’s in the box (v1.1.0):
| Skill | Phase | Hermes-only Feature |
|—|—|—|
| requirement-analyzer | Define | Persistent memory across sessions |
| spec-driven-dev | Spec | /skills chain forming workflows |
| test-driven-dev | Build | delegate_task parallel test execution |
| debugger-coordinator | Verify | browser + terminal + vision tri-tool |
| code-quality-guardian | Review | patch auto-fix + /curator tracking |
| cicd-orchestrator | Ship | cronjob scheduling + webhook triggers |
| skill-curator | Evolve | Direct /curator integration |
| persona-aware-coding | Identity | Native SOUL.md persona system |

Why this is different: Most agent skill collections are portable but shallow β€” they can’t use any platform’s unique superpowers. These skills go deep on Hermes specifically: slash commands, delegate_task, persistent memory, vision+browser+terminal coordination, cron jobs, webhooks. But the format follows the open Agent Skills Standard β€” anyone can fork, remix, or build their own.

Install:

pip install hermes-agent-skills
hermes skills tap add Ow1onp/hermes-agent-skills

Enter fullscreen mode Exit fullscreen mode

Repo: https://github.com/Ow1onp/hermes-agent-skills
46 tests, MIT license, Python 3.10+.

Would love feedback β€” especially from people who’ve tried building their own skills. What’s the friction point you hit first?

μ›λ¬Έμ—μ„œ 계속 β†—

μ½”λ©˜νŠΈ

λ‹΅κΈ€ 남기기

이메일 μ£Όμ†ŒλŠ” κ³΅κ°œλ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. ν•„μˆ˜ ν•„λ“œλŠ” *둜 ν‘œμ‹œλ©λ‹ˆλ‹€