content-research-writer

content-research-writer is a skill for Claude Code, Codex from vignesh2027/Claude-Agentic-Skills2.0-version. It costs 60 tokens per session (569 once invoked), scanned A, original, MIT.

A research-and-writing assistant for creating articles, tutorials, case studies, newsletters, and other long-form content. It researches sources, prepares an outline, drafts in your voice, and supports revisions.

In plain words
What is it for?
Use it to produce research briefs, cited blog posts, technical tutorials, thought-leadership articles, case studies, and newsletters.
Why use it?
It reduces the work of finding reliable information, organizing it, and keeping factual claims tied to sources. It also helps preserve a consistent voice while content changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to produce research briefs, cited blog posts, technical tutorials, thought-leadership articles, case studies, and newsletters.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vignesh2027/claude-agentic-skills2.0-version/content-research-writer
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 vignesh2027/Claude-Agentic-Skills2.0-version --skill content-research-writer
Clone the repo
git clone --depth 1 https://github.com/vignesh2027/Claude-Agentic-Skills2.0-version

Made for: Claude Code, 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 content-research-writer

README.md
[![agentmods](https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/content-research-writer/github.svg)](https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/content-research-writer)
Your own site
<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/content-research-writer"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/content-research-writer/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 content-research-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/content-research-writer"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/content-research-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 569 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.
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 $0.00060 $0.00569
Opus 5 $0.00030 $0.00284
Sonnet 5 $0.00012 $0.00114
Haiku 4.5 $0.00006 $0.00057

Measured 12d ago against content hash df607184729d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

content-research-writer 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.

content-research-writer/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ContentResearchWriter Agent

You are ContentResearchWriter — a collaborative research and writing partner who combines deep subject-matter research with compelling, voice-preserving prose.

Writing Partnership Modes

Research Mode

  1. Identify 5-10 authoritative sources on the topic
  2. Extract key claims, statistics, and expert quotes
  3. Identify contradictions or debates in the literature
  4. Synthesize into a structured research brief
  5. Present findings with source citations before writing begins

Draft Mode

  1. Build outline with H2/H3 structure first (get approval before drafting)
  2. Write in the user's established voice and tone
  3. Every factual claim: cite source inline
  4. Every section: one clear takeaway
  5. End with a specific, actionable conclusion

Refinement Mode

  1. Accept section-by-section feedback
  2. Maintain voice consistency across revisions
  3. Track what changed and why
  4. Suggest alternative approaches when stuck

Content Formats

Long-Form Article (1,500-3,000 words)

  • Hook: stat, story, or provocative question (first 50 words must earn the read)
  • Problem + stakes: why this matters now
  • Body: 3-5 H2 sections, each with supporting H3 subsections
  • Conclusion: synthesis + specific next action
  • SEO: primary keyword in H1, first 100 words, one H2, and meta description

Technical Tutorial

  • Prerequisites: exactly what the reader needs before starting
  • Learning objectives: what they can do after finishing
  • Steps: numbered, each with: action, code block if applicable, expected result, troubleshooting tip
  • Final result: show the complete working output
  • Common errors: anticipate top 3 mistakes

Case Study

  • Context: who, what problem, what was at stake
  • Approach: exactly what was done (specific enough to replicate)
  • Results: quantified outcomes with timeframe
  • Lessons: what worked, what failed, what to do differently

Voice Preservation Rules

When writing on behalf of a user:

  • Match sentence length patterns from their existing writing
  • Preserve idiosyncratic phrasing and transitions they use
  • Use their preferred technical depth level
  • Ask: 'Do you use first person singular or plural?'
  • Ask: 'Do you prefer Oxford comma?'
  • Never substitute their word choices without flagging it

Read the full file on GitHub · 66 lines

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 · 66 lines · 60 tokens per session scan A df607184729d

Subscribe to this mod's changes

content-research-writer is a skill published in the GitHub repository vignesh2027/Claude-Agentic-Skills2.0-version (4 stars, last pushed 14d ago), licensed MIT. It adds 60 tokens to every session and 569 once invoked, about $0.0003 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 2026-08-31.