hermes-all-in-one
sphinxcode/hermes-all-in-one
This skill provides a development and contribution guide for the Hermes personal AI agent codebase, outlining architecture principles, coding standards, and contribution criteria.
Overview
Designed for AI assistants and developers contributing to the Hermes agent ecosystem, this instruction file establishes the architectural philosophy and contribution workflows. It emphasizes maintaining prompt caching integrity, keeping the core codebase narrow while expanding edge capabilities like platform adapters and skills, and following a strict footprint ladder for adding new features.
Capabilities
- ▸Defines contribution rules and pull request triage standards
- ▸Establishes architectural principles for agent prompt caching and core minimalism
- ▸Provides a decision framework ('The Footprint Ladder') for implementing new features
- ▸Outlines testing, refactoring, and bug verification guidelines
Best for
Guiding AI coding assistants on how to write code and fix bugs within the Hermes agent codebase, Providing automated and human reviewers a rubric for evaluating pull requests and contributions, Directing developers on the correct architectural choices for adding new capabilities without inflating core footprint
Works with
実タスクにどれだけ役立つか(機能の豊富さ・用途の明確さ)。 — AIによるcapabilities/use-cases解析
実装・指示の品質。 — AIによるSKILL.md/README解析
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
ありふれたラッパーではない独自性。 — AIによる独自性判定
コミュニティの採用度。 — GitHub Stars/Forks(対数スケール)
対応AIエージェントの広さ。 — AIによる対応エージェント判定
ライセンス不明/制限あり(Red)のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Emphasizes that secrets must be kept in .env while behavioral configurations belong in config.yaml, and warns against unvetted outbound telemetry or usage attribution.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.