Content Research Writer
Outline, hook options and section-by-section feedback for long-form drafts
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 16, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · d9e6f12
Task: 'create an article outline on why remote onboarding fails, and provide a hook' — ran without skill and with skill. Baseline produced a flat outline and a placeholder hook ('In this article, we'll explore…') — 0 out of 8 criteria; skill version yielded 8 out of 8: Hook/Introduction/Main/Conclusion template, inline [Research needed] annotations, Research To-Do checklist, current hook analysis, three marked variants with 'why it works' justification, built-in counter-argument, and a voice verification question. The structural gain is real and reproducible, but half of the description's promise is not confirmed: the skill consists of exactly one SKILL.md file, with no tool bindings (grep for WebSearch/WebFetch/allowed-tools/browser — empty), so 'conducting research, adding citations' relies solely on the model. Worse, the skill's own examples demonstrate citation format with fabricated numbers and authoritative attribution — 'Gartner: 80% of PMs will use AI tools by 2025', '67% of knowledge workers', 'Dr. Jane Smith, MIT' — meaning they teach citation form without any verification, which directly increases the risk of fabrication; in my run, I instead left a hook variant with an explicit PLACEHOLDER. Stage 0 clean: read the entire file, no exfiltration, hidden instructions, or privilege escalation. Trigger 4 out of 5 — description 'assists in writing high-quality content' is too broad and, in my estimation, would falsely apply to short marketing texts like product descriptions.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 4/5
- Output vs. baseline 7/10
- Docs & honesty 3/5
What Content Research Writer does
A writing-partner skill that structures outlines, marks research gaps, rewrites hooks into labelled alternatives, and gives section-by-section feedback while preserving the writer's voice. Triggers on requests to outline, draft, review, or improve blog posts, articles, newsletters, and thought-leadership pieces.
How to install Content Research Writer
git clone https://github.com/Prat011/awesome-llm-skills.git
mkdir -p ~/.claude/skills && cp -r awesome-llm-skills/content-research-writer ~/.claude/skills/content-research-writer
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Content Research Writer
-
/content-research-writerOutline, hook options and section-by-section feedback for long-form drafts
It also activates on plain-language prompts like these:
-
Outline an article about why remote onboarding fails and give me a hook -
Give me section-by-section feedback on this blog draft without losing my voice -
Rewrite my newsletter's opening line into a few different hook options
Frequently asked questions
- Is the Content Research Writer skill free?
- Yes. The skill itself is free from Prat011/awesome-llm-skills. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Content Research Writer work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. Task: 'create an article outline on why remote onboarding fails, and provide a hook' — ran without skill and with skill. Baseline produced a flat outline and a placeholder hook ('In this article, we'll explore…') — 0 out of 8 criteria; skill version yielded 8 out of 8: Hook/Introduction/Main/Conclusion template, inline [Research needed] annotations, Research To-Do checklist, current hook analysis, three marked variants with 'why it works' justification, built-in counter-argument, and a voice verification question. The structural gain is real and reproducible, but half of the description's promise is not confirmed: the skill consists of exactly one SKILL.md file, with no tool bindings (grep for WebSearch/WebFetch/allowed-tools/browser — empty), so 'conducting research, adding citations' relies solely on the model. Worse, the skill's own examples demonstrate citation format with fabricated numbers and authoritative attribution — 'Gartner: 80% of PMs will use AI tools by 2025', '67% of knowledge workers', 'Dr. Jane Smith, MIT' — meaning they teach citation form without any verification, which directly increases the risk of fabrication; in my run, I instead left a hook variant with an explicit PLACEHOLDER. Stage 0 clean: read the entire file, no exfiltration, hidden instructions, or privilege escalation. Trigger 4 out of 5 — description 'assists in writing high-quality content' is too broad and, in my estimation, would falsely apply to short marketing texts like product descriptions.
- What is the Content Research Writer SkillProof Score?
- 7.6/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 7/10, docs & honesty 3/5.
- How do I install Content Research Writer?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Content Research Writer with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.