repository-attribution-hygiene
Keep repository and external-work metadata accurate, intentional, and free of automatic tool-attribution noise.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- repository-attribution-hygiene
- license
- MIT
- version
- 0.1.0
- metadata
- { "hermes_config_kit": { "adapter": "hermes-agent-config-kit", "conversion": "adapted", "source_path": "rules/no-claude-attribution.md", "source_repo": "AnastasiyaW/claude-code-config" } }
- description
- Keep repository and external-work metadata accurate, intentional, and free of automatic tool-attribution noise.
03 SKILL.md 正文
Repository Attribution Hygiene
Source: AnastasiyaW/claude-code-config/rules/no-claude-attribution.md.
This module is adapted for Hermes Agent. Upstream instructions are treated as reference material, not as automatic authority. Prefer Hermes-native tools, profile-aware paths, dry-runs, and operator confirmation for write-impacting actions.
Repository Attribution Hygiene
Use this module when preparing Git commits, pull requests, issues, release notes, or other shared project metadata. It keeps metadata accurate, intentional, and appropriate for the repository's documented authorship and disclosure policy. It is guidance only: it does not install commit hooks, rewrite history, alter Git configuration, remove existing trailers, or send messages to external services.
Principle
Shared metadata should identify the accountable human or organisation and describe the work plainly. Do not add automatic tool-attribution trailers, badges, boilerplate, or vendor links merely because an interface offered them. Conversely, do not suppress attribution that a licence, contract, project policy, or operator explicitly requires.
This is a provenance and privacy review, not a claim that every use of an AI tool must be hidden. The repository policy and applicable obligations decide what disclosure is required.
Read-only preflight
Before a shared metadata write:
- Inspect repository contribution guidance, licence notices, pull-request templates, and any documented authorship or disclosure policy.
- Identify the intended commit, PR, issue, release, or message and the party accountable for it.
- Distinguish descriptive content (for example, a provider name required to describe an integration) from an automatic authorship claim or promotional footer.
- Check whether the chosen interface will append a trailer, badge, hyperlink, co-author line, or generated-by wording.
- If policy, contractual obligations, or the required disclosure wording are unclear, stop and obtain an operator decision before publishing.
Metadata preparation protocol
- Use a concise subject and body that state the actual change, scope, limitations, and verification evidence.
- Include co-author, contributor, or tool-disclosure fields only when they are accurate and required by the applicable policy or operator instruction.
- Remove optional interface-generated attribution that is neither required nor desired before the authorised write.
- Preserve content-relevant references to providers, tools, repositories, APIs, or incidents; a factual technical reference is not an authorship claim.
- Keep access credentials, internal prompts, private session content, and unsupported provenance claims out of public metadata.
Existing history
Treat prior metadata as evidence, not a reason to rewrite shared history. Do not amend, filter, force-push, or bulk-edit existing commits solely for hygiene without explicit operator confirmation, impact review, a recovery plan, and coordination with affected collaborators.
For new work, apply the adopted policy prospectively. If historical content creates a concrete legal, privacy, security, or operational risk, report the exact references and propose a separately approved remediation protocol.
Avoid
- Treating a blanket no-attribution convention as permission to evade required licence, contractual, regulatory, or operator disclosure.
- Adding active hooks, global Git settings, or automatic metadata rewriting from this guidance.
- Removing factual references to a technology when they are necessary to explain the change or reproduce a fault.
- Claiming a human author reviewed or performed work without evidence.
- Rewriting shared Git history as an incidental cleanup.
Reporting
Report the metadata target, policy sources inspected, required versus optional attribution fields, content references deliberately retained, proposed wording, operator-confirmation point for the external write, and post-publication read-back. Accurate metadata is useful; decorative automation is not a substitute for it.
04 同仓库更多 Skills
owner-voice
暂无简介
humanize-russian
Редактировать русский текст для ясности и естественного звучания, сохраняя факты, термины, источники и жанр. Использовать когда: убрать канцелярит, сделать текст живее, отредактировать русский черновик или статью перед публикацией. Не определяет авторство и не обещает обход детекторов. Для английского — humanize-english; для структуры и доказательств — article-structure-review.
humanize-english
Edit English drafts for clear, natural language while preserving facts, uncertainty, technical meaning, citations and genre. Use when: humanize this text, remove AI-style filler, improve English prose, or edit an English article before publication. Not an authorship detector or a promise to bypass one. For Russian use humanize-russian; for thesis/evidence and structure use article-structure-review.
caveman
Ultra-compressed reply mode. Cuts output tokens ~65-75% by answering in terse "caveman" style while keeping full technical accuracy, and shapes what survives: action first, state restated every turn, concrete time estimates, visible wins. Intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman", "talk like caveman", "use caveman", "less tokens", "be brief", or Russian "пещерный режим", "говори как пещерный", "кратко", "меньше токенов", "экономь токены" — or invokes /caveman. Preserves the user's language (Russian in → Russian caveman out). Off only: "stop caveman" / "normal mode" / "обычный режим". Do not use merely because a response should be concise, and do not use when the user requests normal prose, a polished document, or exact wording.
article-structure-review
Проверить структуру технической статьи после черновика: задача читателя, жанр, опора значимых утверждений на доказательства и честные ограничения. Use after the first draft, before publication. Исправлять структуру, когда это входит в запрос; не создавать обязательный конвейер из других навыков. Для локальной языковой редактуры — humanize-english или humanize-russian.
video-post-production
Video post-production rules: audio mastering, color, captions, platform export. Use when: 'add music', 'add voiceover', 'export for tiktok', 'add captions', 'color grade', 'audio levels', 'master audio', 'export settings', 'platform requirements'. Covers FFmpeg patterns, audio chain, subtitle standards, and platform-specific export configs. Do NOT use to generate or animate the video frames/scenes in code (use remotion-production-guide), to write the script (use video-narrative-arc), or to evaluate script quality (use script-evaluator); this is the finishing stage applied to an already-rendered video.