Content Research Writer logo

Content Research Writer

Community
Rylaispirit
content-research-writer

Research, outline, draft, cite, and revise articles, reports, tutorials, newsletters, and case studies with traceable sources and preserved voice.

Overview

PublisherRylaispirit
Repositoryrylai-codex-hermes-skills
Skill namecontent-research-writer
Stars
63
Forks
42
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Rylaispirit on GitHub. Read the source before you install it.

Installation

Install the Content Research Writer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Rylaispirit/rylai-codex-hermes-skills/tree/main/skills/content-research-writer
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Rylaispirit/rylai-codex-hermes-skills.git /tmp/rylai-codex-hermes-skills
mkdir -p .claude/skills
cp -r /tmp/rylai-codex-hermes-skills/skills/content-research-writer .claude/skills/content-research-writer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Content Research Writer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Content Research Writer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Content Research Writer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Content Research Writer

Build useful prose from a traceable research base. Keep verified facts, source interpretation, and the writer's own argument clearly separated.

Runtime Compatibility

  • Use the research and file tools available in the active runtime.
  • Resolve workspace files from the user's stated project path.
  • Confirm network and source access before promising current citations.
  • Preserve existing drafts and user edits unless replacement is explicitly requested.

Establish The Brief

Infer available details, then fill only material gaps:

  • topic and central question;
  • intended audience;
  • purpose and publication format;
  • target length and deadline;
  • voice or writing samples;
  • citation style;
  • required, preferred, or excluded sources.

Record uncertain assumptions before research begins.

Research Workflow

  1. Create research questions

    • Convert the topic into a short list of claims the piece must establish.
    • Add questions for context, counterarguments, examples, and practical impact.
  2. Choose sources

    • Prefer primary material for factual and technical claims.
    • Use reputable synthesis for context and competing interpretations.
    • Check publication date, authorship, methodology, and conflicts of interest.
  3. Build a source ledger

markdown
| ID | Source | Claim Supported | Evidence | Limits | Status |
|---|---|---|---|---|---|
| S1 | [title and locator] | [claim] | [fact or short note] | [caveat] | verified |

Do not put a source in the final reference list unless it was opened and used.

  1. Resolve conflicts

    • Compare definitions, dates, sample populations, and measurement methods.
    • Report meaningful disagreement instead of selecting a convenient number.
  2. Stop when evidence is sufficient

    • Each major factual claim has support.
    • Important counterevidence is represented.
    • Additional searching is unlikely to change the structure or conclusion.

Writing Workflow

  1. Thesis

    • State the article's central answer in one or two sentences.
  2. Outline

    • Give every section a job.
    • Link claims to source IDs.
    • Mark evidence gaps before drafting.
  3. Draft

    • Write from the outline and source ledger.
    • Cite factual claims near the relevant sentence.
    • Use examples to explain, not to substitute for evidence.
    • Keep the user's voice, terminology, and preferred level of formality.
  4. Edit

    • Check argument order, transitions, redundancy, and paragraph purpose.
    • Replace vague claims with evidence or narrower wording.
    • Remove unsupported authority cues and decorative statistics.
  5. Verify

    • Open every citation again when accuracy matters.
    • Confirm names, titles, dates, quotations, quantities, and links.
    • Check that the cited source supports the exact nearby claim.

Collaboration Modes

Outline First

Return:

  • thesis options;
  • proposed section order;
  • claim-to-source map;
  • research gaps;
  • questions that require the user's judgment.

Section Review

Lead with the highest-impact feedback:

  • argument or evidence issue;
  • structure and flow;
  • audience or voice mismatch;
  • concrete revision;
  • citations still needed.

Do not rewrite the whole section when a focused edit would preserve more of the writer's voice.

Full Draft

Deliver the requested article and a short verification note containing:

  • citation style used;
  • claims still awaiting evidence;
  • assumptions or source limitations;
  • optional editorial alternatives.

Citation Rules

  • Follow the user's requested citation format.
  • Never invent a source, author, title, date, URL, quotation, or page number.
  • Prefer direct links or identifiers to vague publication names.
  • Quote only when exact wording is necessary; otherwise paraphrase accurately.
  • Keep source notes long enough to audit but do not reproduce large passages.
  • For current or changing facts, research them at the time of writing.

Voice Preservation

  • Study supplied writing samples before making broad stylistic changes.
  • Preserve intentional vocabulary, rhythm, and point of view.
  • Distinguish correctness edits from optional stylistic suggestions.
  • Avoid flattening personal prose into generic professional language.
  • Ask for confirmation only when a voice choice changes meaning or audience fit.

Final Check

  • The thesis answers the stated question.
  • Each section advances the piece.
  • Important factual claims have traceable support.
  • Sources are represented fairly, including limitations and disagreement.
  • Citations and reference entries agree.
  • The final voice belongs to the user, not to a generic template.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Content Research Writer AI skill do?

Research, outline, draft, cite, and revise articles, reports, tutorials, newsletters, and case studies with traceable sources and preserved voice.

Why use Content Research Writer on TypingMind?

Because you install it once and use it with any model. Content Research Writer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Content Research Writer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Rylaispirit/rylai-codex-hermes-skills/tree/main/skills/content-research-writer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Content Research Writer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Content Research Writer?

As many as you like. As long as a model supports skills, you can use Content Research Writer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Content Research Writer AI skill free?

Yes. It is published on GitHub by Rylaispirit under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇