Guide · Agent skill
How to use the Content Engine agent skill: install and examples
Updated · written with AI from the project's own documentation and checked against our catalogue data
The content-engine skill is a set of written instructions that teaches an AI agent how to draft social posts, threads, short-form video scripts, YouTube outlines and newsletters from material you supply. It is aimed at founders, developers, creators and marketers who want one source asset, such as an article, demo or set of release notes, turned into platform-specific drafts. After this guide you will know what the skill does, how to install it, how to ask for content so the agent uses it, and what limits to keep in mind.
Content Engineaffaan-m/ECC · MIT Download the skill Quick start
- 1Download the ZIP. Download the content-engine ZIP from this page.
- 2Unzip into a skills folder. Unzip it into ~/.claude/skills/ for personal use, or into .claude/skills/ inside a project.
- 3Or upload in the Claude apps. In the Claude apps, open Settings, then Capabilities, then Skills, and upload the ZIP.
- 4Check the files. Confirm the folder contains SKILL.md and agents/openai.yaml.
- 5Give a source and a platform. Paste an article, demo or notes and name the platform you want, such as X or LinkedIn.
- 6Review the drafts and gaps. Read each draft for accuracy and resolve any listed gaps before you publish anywhere.
What the content-engine skill makes the agent do
An agent skill is a folder containing instructions (a SKILL.md file) that an AI agent reads when a request matches the skill's description. Content Engine covers X, LinkedIn, TikTok, YouTube, newsletters and multi-platform campaigns. Its core rule is to start from your real source material rather than generic post formulas, and to adapt the format for each platform rather than rewriting the author's persona.
The skill also sets specific rules per platform. On X it asks for an opening claim or artifact and no padding. On LinkedIn it asks for only enough context for outsiders to follow. For short video it scripts around the visual sequence and proof points, and for newsletters it opens with the point rather than a warm-up paragraph.
- Drafts social posts, threads, short-form scripts, YouTube explainers and newsletters
- Adapts one source into several platform-native versions
- Checks drafts against banned phrases and fake engagement tricks before delivering
- Flags missing proof points as gaps instead of inventing them
- Can hand voice matching to the related brand-voice skill when consistency matters
Install the content-engine skill
You can install the skill in two ways. For a personal setup, download the ZIP from this page and unzip it into ~/.claude/skills/. To scope it to one project, unzip it into the .claude/skills/ folder inside that project. Alternatively, in the Claude apps go to Settings, then Capabilities, then Skills, and upload the ZIP there.
After unzipping, the skill folder should contain the two files listed in the source: SKILL.md and agents/openai.yaml. SKILL.md holds the instructions the agent reads.
- Personal install: unzip into ~/.claude/skills/
- Project install: unzip into .claude/skills/ in your project
- Claude apps: Settings → Capabilities → Skills, then upload the ZIP
Trigger the skill with natural requests
You do not need a special command. The agent uses the skill when your request matches its description: social posts, threads, scripts, content calendars, or one source asset adapted across platforms. Name the platform and attach or paste the source so the agent has material to work from.
The more specific your source, the better the output. The skill's workflow asks the agent to identify published articles, notes, demos, docs, transcripts, screenshots or prior posts before drafting.
- "Turn these release notes into three X posts. Each post should make one claim."
- "Write a LinkedIn post about this demo. Keep it plain and don't add a lesson at the end."
- "Script a 45-second short-form video from this article, opening on the result."
- "Plan a two-week content calendar from these changelogs across X and LinkedIn."
- "Adapt this newsletter draft into a YouTube outline and a LinkedIn post."
Repurpose one asset across platforms
For a multi-platform campaign, the skill follows a fixed flow. It picks an anchor asset, extracts three to seven atomic claims or scenes, ranks them by sharpness, novelty and proof, assigns one strong idea per output, adapts the structure for each platform, strips platform-shaped filler, and runs a quality gate.
When you ask for a campaign, the skill is designed to return a short voice profile if voice matters, the core angle, platform-native drafts, posting order only if it helps execution, and a list of gaps to fill before publishing.
- Pick the anchor asset (article, demo, notes)
- Extract 3 to 7 claims or scenes
- Assign one idea per output
- Review the gaps list before publishing
Safety, requirements and limits
According to the listing, the skill requires nothing beyond itself, runs no scripts and uses no network access. It only drafts text. It does not publish, so you still need your own review step or scheduler. The skill also does not invent facts: if your material lacks proof, the agent should flag the gap.
Engagement bait is excluded by default. The skill says to avoid it unless you explicitly ask, and it treats any call to action as something that must be earned and approved by you.
- Requires: nothing listed
- Runs scripts: no
- Uses network: no
- Does not publish posts; review drafts yourself
- Related skills x-api and crosspost cover sourcing and distribution if you need them, and are separate installs
What people use it for
- Turning release notes or a product demo into a short X thread
- Drafting a LinkedIn launch update from an internal memo, without filler
- Scripting a short-form video from an existing article or explainer
- Planning a content calendar from a set of changelogs
- Adapting one newsletter into a YouTube outline and social posts
Frequently asked questions
Is the content-engine skill free?
The skill is published under the MIT licence, as stated in its SKILL.md. The listing does not state prices for anything else, so check the terms of whatever agent product you run it in.
What do I need to use content-engine?
The listing says it requires nothing beyond the skill itself. You also need an agent environment that supports skills, such as the Claude apps or Claude Code with the skills folders described above.
Where do I install the content-engine skill?
Unzip the ZIP into ~/.claude/skills/ for personal use or into .claude/skills/ in a project. In the Claude apps, upload the ZIP under Settings, Capabilities, Skills.
Does content-engine post to X or LinkedIn for me?
No. The skill only drafts text and does not publish. You need a separate scheduler or your own manual review and posting step.
Does the skill make up stats or quotes?
It is designed not to. It relies on the material you supply, and missing proof points are flagged as gaps rather than invented.
How is content-engine different from brand-voice?
Content Engine handles platform-native drafts and repurposing. The brand-voice skill builds a voice profile from real examples; Content Engine can hand voice matching to it when consistency across outputs matters.
New agent skills, repos and AI tools — every week
The best new skills and open-source projects, the fastest-growing repos, and one free prompt. Five minutes to read. Unsubscribe anytime.
Our verdict
Content Engine suits founders, developers, creators and marketers who already have real material, such as articles, demos or notes, and want platform-specific drafts from it. It is a poor fit if you want fully automated posting or content that must be backed by facts you have not supplied, since it only drafts text and flags gaps.
Download the skill