academic-writing-style

academic-writing-style is a skill for Codex from Rylaispirit/rylai-codex-hermes-skills. It costs 37 tokens per session (865 once invoked), scanned A, original, MIT.

A writing and review process for academic documents such as theses, research papers, literature reviews, methods, results, and discussions. It checks the argument, evidence, structure, citations, and style without making up sources or findings.

In plain words
What is it for?
Use it to plan, draft, revise, restructure, proofread, or audit academic writing.
Why use it?
It helps ensure that each important claim is supported and that the document follows the supplied research and formatting requirements. It also exposes missing information instead of silently guessing.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Good fit Use it to plan, draft, revise, restructure, proofread, or audit academic writing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rylaispirit/rylai-codex-hermes-skills/academic-writing-style
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Rylaispirit/rylai-codex-hermes-skills --skill academic-writing-style
Clone the repo
git clone --depth 1 https://github.com/Rylaispirit/rylai-codex-hermes-skills

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for academic-writing-style

README.md
[![agentmods](https://agentmods.dev/badge/skills/rylaispirit/rylai-codex-hermes-skills/academic-writing-style/github.svg)](https://agentmods.dev/skills/rylaispirit/rylai-codex-hermes-skills/academic-writing-style)
Your own site
<a href="https://agentmods.dev/skills/rylaispirit/rylai-codex-hermes-skills/academic-writing-style"><img src="https://agentmods.dev/badge/skills/rylaispirit/rylai-codex-hermes-skills/academic-writing-style/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for academic-writing-style

Your own site · 80×15
<a href="https://agentmods.dev/skills/rylaispirit/rylai-codex-hermes-skills/academic-writing-style"><img src="https://agentmods.dev/badge/skills/rylaispirit/rylai-codex-hermes-skills/academic-writing-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 865 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.00865
Opus 5 $0.00018 $0.00432
Sonnet 5 $0.00007 $0.00173
Haiku 4.5 $0.00004 $0.00086

Measured 12d ago against content hash c1216b3697bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

academic-writing-style scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/academic-writing-style/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rylai Academic Writing

Produce rigorous academic prose without inventing evidence, citations, findings, or institutional requirements.

Start With The Writing Contract

Before drafting or revising, identify:

  • document type, field, audience, language, and expected length;
  • research question, central claim, and scope;
  • required citation style and institutional template;
  • supplied sources, data, tables, and terminology;
  • whether the task is drafting, restructuring, proofreading, or compliance review.

If a required source or rule is unavailable, state the gap. Do not silently guess.

Core Workflow

  1. Map the argument

    • Express the main claim in one sentence.
    • List the claims each section must establish.
    • Link every substantive claim to evidence, reasoning, or an explicit limitation.
  2. Build the structure

    • Give each section one clear purpose.
    • Order paragraphs so each one prepares the next.
    • Remove sections that repeat a claim without adding evidence or interpretation.
  3. Draft by paragraph function

    • Open with the paragraph's controlling idea.
    • Present evidence or method.
    • Explain why the evidence matters.
    • Close with a consequence, qualification, or transition.
  4. Calibrate claims

    • Match certainty to the study design and evidence.
    • Distinguish correlation, prediction, mechanism, and causation.
    • State population, time, geography, and measurement limits where relevant.
  5. Audit evidence

    • Confirm that every citation supports the nearby statement.
    • Separate the author's interpretation from the source's conclusion.
    • Mark missing bibliographic fields instead of fabricating them.
  6. Revise in passes

    • Pass 1: argument and section order.
    • Pass 2: evidence and citation integrity.
    • Pass 3: paragraph cohesion and transitions.
    • Pass 4: sentence clarity, terminology, and formatting.

Section Guidance

  • Introduction: establish context, define the problem, identify the gap, state the objective, and present the research question.
  • Literature review: synthesize sources by issue or debate; compare positions instead of listing summaries.
  • Methods: describe design, sample, materials, procedure, analysis, ethics, and decisions needed for replication.
  • Results: report findings in the order of the questions or hypotheses; keep interpretation limited.
  • Discussion: answer the research question, connect findings to prior work, explain implications, and acknowledge limitations.
  • Conclusion: state the contribution and boundary of the work without introducing new evidence.

Read the full file on GitHub · 102 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 102 lines · 37 tokens per session scan A c1216b3697bf

Subscribe to this mod's changes

academic-writing-style is a skill published in the GitHub repository Rylaispirit/rylai-codex-hermes-skills (55 stars, last pushed 29d ago), licensed MIT. It adds 37 tokens to every session and 865 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.