AGENT SKILL

article-structure-review

Review a completed article's macro-structure, evidence balance, genre fit, stated limitations, section load, and appropriate use of visuals without rewriting prose or publishing content.

License 许可
MIT
最近更新
2026-11-14
Stars
★ 1
Forks
0

01 前言 Front Matter

name
article-structure-review
license
MIT
version
0.1.0
metadata
{ "hermes_config_kit": { "adapter": "hermes-agent-config-kit", "conversion": "adapted", "source_path": "skills/writing/article-structure-review/SKILL.md", "source_repo": "AnastasiyaW/claude-code-config" } }
description
Review a completed article's macro-structure, evidence balance, genre fit, stated limitations, section load, and appropriate use of visuals without rewriting prose or publishing content.

03 SKILL.md 正文

Article Structure Review

Source: AnastasiyaW/claude-code-config/skills/writing/article-structure-review/SKILL.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.

Article structure review

Use this module after a complete draft exists and before sentence-level editing or publication. It is a read-only editorial protocol for macro-structure: the relation between claims and their support, genre and reader expectations, declared limitations, section load, and whether a visual would communicate structure more clearly than prose.

Boundary and overlap

Use humanize-russian for Russian-language phrasing, register, cadence, and factual preservation. Use the installed humanizer module for a general scan of generic AI-writing patterns. This module does not prescribe wording, simulate a human voice, conceal authorship, invent evidence, or bypass publication, disclosure, or editorial review requirements.

Treat numerical ratios and paragraph-count heuristics as optional diagnostic signals, not publication gates. A claim may be supported by a concrete example, a sourced fact, a reproducible method, a clearly bounded case, or an explicit uncertainty; the appropriate balance depends on the article's genre and audience.

Read-only review protocol

  1. Set the editorial brief. Identify the intended audience, primary genre, publication context, central question, factual constraints, and any required disclosure. If the article is stored in a file, inspect it before proposing changes.
  2. Check claim and support balance. For each major section, mark its important claims and the evidence or reasoning that supports them. Flag unsupported assertions, evidence that arrives too late, and sections that accumulate conclusions without showing how the reader can assess them. Propose the smallest repair: qualify a claim, add available evidence, move support nearer to the claim, or narrow scope.
  3. Check genre and narrative contract. Confirm that the title, opening, section sequence, and conclusion serve one primary genre such as analysis, tutorial, reference, opinion, or experience report. A deliberate genre shift is acceptable when it is signposted and has a clear purpose; an accidental one should be clarified or separated.
  4. Make limitations visible. For articles that present a tool, approach, result, or recommendation, locate where assumptions, trade-offs, untested conditions, and known failure modes are stated. Recommend a bounded limitations section when their absence could cause readers to overgeneralise. Do not manufacture caveats or personal experience that the author cannot support.
  5. Review section load. Compare the conceptual load of opening, middle, and final sections. Flag a dense section that introduces many new ideas without transitions, examples, or staging. Suggest splitting, reordering, summarising, or moving detail to a separately scoped article only when it improves the reader's path.
  6. Choose visual or prose deliberately. When a section explains relationships, hierarchy, architecture, comparison, categories, or a timeline, ask whether a table, diagram, or other visual would make the structure clearer. Use prose for reasoning, sequence, nuance, and narrative. A visual is a proposal, not a required deliverable.
  7. Read back the structure. Read the title, opening, headings, first paragraphs, transitions, and conclusion as a reader would. Record the supported thesis, genre, limitations, structural risks, and proposed edits separately from any actual write.

Output shape

Return a compact structural review with: editorial brief; claim/support observations; genre and reader-path assessment; limitations and uncertainty; section-load and visual/prose recommendations; retained facts; and any operator confirmation required before changing a file or publishing. Preserve the author's evidence and make the scope of uncertainty visible rather than polishing it away.

04 同仓库更多 Skills

hermes-jarvis-bot
hermes-jarvis-bot/hermes-agent-config-kit

owner-voice

暂无简介

★ 1
hermes-jarvis-bot
hermes-jarvis-bot/hermes-agent-config-kit

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.

★ 1
hermes-jarvis-bot
hermes-jarvis-bot/hermes-agent-config-kit

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.

★ 1
hermes-jarvis-bot
hermes-jarvis-bot/hermes-agent-config-kit

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.

★ 1
hermes-jarvis-bot
hermes-jarvis-bot/hermes-agent-config-kit

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.

★ 1
hermes-jarvis-bot
hermes-jarvis-bot/hermes-agent-config-kit

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.

★ 1