Аудитория: инженеры, уже развернувшие Hermes (install runbook), но упирающиеся в routing Skills, Bundles или GEPA pipeline.Результат: полная спецификация SKILL.md, Progressive Disclosure (Level 0–2), Conditional Activation, Tap publish, GEPA+DSPy evolution, plugin namespace и authoring patterns.Структура: шесть bottlenecks, матрица Skills/Memory/Prompts, bundles, hub, 8 шагов Tap, GEPA, case study, FAQ, ресурсы.
В начале 2026 Hermes Agent превысил 160 000 GitHub stars. Тезис the agent that grows with you реализован через Skills — стандартизированный procedural memory layer, а не через размер модели. Механизмы загрузки и персистентности определяют, сработает ли compounding.
MEMORY.md хранит факты (declarative); Skills — процедуры с on-demand load и нулевым token cost до activation./skill вместо atomic /backend-dev workflow load.| Измерение | Prompt | Memory | Skill |
|---|---|---|---|
| Персистентность | текущая session | cross-session | cross-session |
| Load trigger | always in context | inject each session | on-demand (Progressive Disclosure) |
| Token до activation | full cost | small, stable | zero (только metadata L0) |
| Тип данных | произвольная инструкция | факты, preferences | procedure (step-by-step) |
| Sharing | сложно | private | publishable as Tap |
Memory architecture (3 layers): MEMORY.md + SQLite FTS5 + Provider.
Стандарт agentskills.io обеспечивает portability между Hermes, Claude Code, Cursor. Путь: ~/.hermes/skills/<category>/<name>/SKILL.md.
| Level | Payload | Trigger | Tokens |
|---|---|---|---|
| 0 | name + description |
session init | ~3000 total |
| 1 | full SKILL.md body | /skill or LLM match |
file size |
| 2 | references/, scripts/ |
runtime execution | per file; script stdout only in context |
---
name: github-code-review
description: |
Use when reviewing PRs, checking security or style.
Do NOT use for writing new code.
metadata:
hermes:
requires_toolsets: [terminal]
fallback_for_tools: [web_search]
---
# GitHub Code Review
## Procedure
1. `gh pr diff`
2. Security checklist
3. Structured comment
## Common Pitfalls
- 403 rate limit: `--rate-limit 100`
- Large diff: load references/chunking.md
YAML в ~/.hermes/skill-bundles/<slug>.yaml. Команда /mlops-deploy загружает vllm, llama-cpp, github-pr-workflow, systematic-debugging одновременно.
Priority rules: bundle > single skill с тем же name; missing skills skip silently с warning; bundle не модифицирует system prompt — Prompt Cache остаётся valid.
name: mlops-deploy description: Model deployment pipeline with monitoring. skills: - vllm - llama-cpp - github-pr-workflow - systematic-debugging instruction: | Run inference benchmarks before and after deploy. Document quantization in PR description.
Четыре поля в metadata.hermes управляют visibility skill в runtime tool registry:
web_search.При наличии FIRECRAWL_KEY fallback skill исчезает из Level-0 metadata — measurable token savings без manual toggle. TUI hermes skills позволяет per-platform enable (CLI, Telegram, Discord).
hermes skills install official/research/arxiv hermes skills install github:openai/skills/k8s hermes skills tap add github:your-org/your-skills-tap hermes skills tap update hermes skills tap list
| Repo | Focus | Notes |
|---|---|---|
| hermes-agent | Official skills | Source of truth |
| hermeshub | Community registry | Prompt injection scan |
| awesome-hermes-skills | Production skills | MLOps, Deep Research |
| ai-agent-skills | 191 skills, 28 categories | Hermes/Claude/Cursor |
mlops/, research/).skills-ref validate ./my-skill.hermes skills tap add github:org/repo; private: --token $GH_TOKEN.hermes skills tap update; после changes — /reset или --now (cache invalidation).GEPA (Genetic-Pareto Prompt Evolution) — ICLR 2026 Oral. Optimizer анализирует execution trajectories в SQLite, генерирует SKILL.md variants, оценивает Pareto frontier (success rate × token efficiency × latency). Repo: hermes-agent-self-evolution. Cost: $2–10 per run (API only, no GPU).
5 stages: trajectory collection → reflective failure analysis → targeted mutation (10–20 variants) → multi-objective Pareto eval → human-reviewed PR.
export HERMES_AGENT_PATH=~/.hermes
python -m evolution.skills.evolve_skill \
--skill github-code-review \
--iterations 10 \
--eval-source sessiondb
# Cross-agent traces (experimental):
# --trace-dirs ~/.claude/traces,~/.hermes/sessions
4 guardrails: pytest 100%, skill ≤15KB, prompt cache compatibility, semantic drift check. Roadmap: Phase 1 Skills (live), Phases 2–5 tool descriptions, system prompts, tool code, full automation (planned).
Namespace plugin:skill — opt-in load via skill_view("superpowers:writing-plans"); не pollute default skills_list.
references/.agent_writes_require_approval: true в config.yaml.name: blog-workflow skills: - seo-keyword-research - outline-generator - code-example-validator - bilingual-checker instruction: | Research SEO keywords before writing. All code examples must be runnable.
description fields.~/.hermes/ on Apple Silicon UMA.SKILL.md + Bundles + Conditional Activation + GEPA формируют closed learning loop без weight fine-tuning. Limits альтернатив: (a) ephemeral prompts; (b) shared VPS без isolated ~/.hermes/; (c) laptop sleep прерывает Gateway и trajectory accumulation.
Для GEPA runs, team Taps и launchd Gateway на Apple Silicon UMA с FileVault-at-rest — выделенный Mac Mini M4 через MACCOME. Цены: тарифы аренды; поддержка: центр помощи.
FAQ
Skills vs MCP в Hermes?
Skills — procedural docs; MCP — tool interfaces. Skill описывает когда и как вызывать MCP tools — complementary layers.
Почему старая версия Skill?
/reset или install --now после edit. Production: Git tag + documented rollout window.
GEPA-safe для production?
4 guardrails + manual PR review. SessionDB с PII требует purge policy перед GEPA run.
24/7 hosting для Skills?
Compounding и Tap sync требуют persistent disk. Сравните регионы на странице тарифов; FAQ: центр помощи.