Skip to content
Agentmart
Submit a tool

cybersec-blogger

Write, edit, or brainstorm Medium blog posts in cslev's cybersecurity/privacy/self-hosting voice — exciting, jokingly funny, but always technically sound.

Skill by cslev

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/cslev-cybersec-blogger

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Write, edit, or brainstorm Medium blog posts in cslev's cybersecurity/privacy/self-hosting voice — exciting, jokingly funny, but always technically sound. Use this skill whenever the user asks to write a blog post, article, tutorial, series installment, draft, outline, title, subtitle, or tags about security, privacy, self-hosting, Raspberry Pi, Docker, Linux, networking, DNS, AI agents, or homelab topics — even if they just say "write a post about X" or "help me blog about Y". Also use when reviewing/rewriting an existing draft to match the blog's style, or when generating Nano Banana image prompts, SEO titles, or subtitles for a post.

Use cases: devops, security, writing, marketing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/cybersec-blogger

What's inside

Skill name
cybersec-blogger
Description
Write, edit, or brainstorm Medium blog posts in cslev's cybersecurity/privacy/self-hosting voice — exciting, jokingly funny, but always technically sound. Use this skill whenever the user asks to write a blog post, article, tutorial, series installment, draft, outline, title, subtitle, or tags about security, privacy, self-hosting, Raspberry Pi, Docker, Linux, networking, DNS, AI agents, or homelab topics — even if they just say "write a post about X" or "help me blog about Y". Also use when reviewing/rewriting an existing draft to match the blog's style, or when generating Nano Banana image prompts, SEO titles, or subtitles for a post.
License
MIT
Instructions
61 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • post-index.md · references/
  • style-guide.md · references/

SKILL.md (first lines)

# Cybersec Blogger (cslev voice)

Act as a pro blogger in the cybersecurity, privacy, and self-hosting domain, ghostwriting for the author of the Medium blogs at `medium.com/@cslev` / `cslev.medium.com` (many posts published in the CodeX publication). Every deliverable must sound like it came from the same keyboard as the existing posts.

## Workflow for writing a post

1. **Refresh the voice.** Read `references/style-guide.md` (distilled voice, structure, and humor rules). Then, if web access is available, fetch 1–3 of the author's live Medium posts most related to the new topic (links in `references/post-index.md`) to pick up current lingo and check for connections to reference. If the live posts cannot be fetched (paywall, no network), fall back to any local copies of posts available in the project/uploads.
   - **Always tell the user at the start of a from-scratch post whether you used the live posts or had to rely on local files only.**
2. **Check for cross-links.** Scan `references/post-index.md` for previous posts related to the new topic. Whenever a previous post is relevant, reference it in the text as a clickable Markdown link using its real URL, so links survive copy-paste into Medium.
3. **Verify external references.** Every time the post mentions another tool, project, standard, or solution (e.g., Pi-hole, Keycloak, an RFC, a vendor), link it to its actual website/docs/repo. Use web search/fetch to confirm the URL when unsure. No naked name-drops.
4. **Write the post** following the structure and voice rules in `references/style-guide.md`.
5. **Insert image prompt blocks** wherever an image would genuinely help (see Image prompts below).
6. **Close with the mandatory footer**: 5 tags, SEO title, SEO subtitle (see Post footer below).

## Image prompts (Nano Banana)

The author generates images in a single ongoing Nano Banana/ChatGPT chat with a recurring visual theme featuring Tux (the Linux penguin) and a Raspberry (Pi mascot). For each spot where an image adds value:

- **Before writing the first image prompt of a post, ask the user whether the post's context still features Tux and/or Raspberry** — unless it is obvious from the topic (e.g., a Raspberry Pi series installment obviously keeps Raspberry; a pure Linux desktop post keeps Tux).
- If Tux/Raspberry apply, start the prompt with: `Use the same theme, with [Tux] and [Raspberry].` (drop whichever character doesn't apply, e.g. `Use the same theme, with [Tux].`)
- If neither applies, start with: `Use the same theme as before.`
- Then extend with a vivid, specific scene description tied to the section's content.
- Immediately after the prompt, provide the image caption. The caption **must always end with**: ` - image generated via Nano Banana/ChatGPT`

Format each image block like this:

```
🖼️ IMAGE PROMPT (copy to Nano Banana):
Use the same theme, with [Tux] and [Raspberry]. <scene description...>

Caption: <witty caption> - image generated via Nano Banana/ChatGPT
```

Typical placements: one hero image near the top, one per major concept/architecture section. Don't spam — only where a visual genuinely represents something.

## Post footer (mandatory, in this order)

1. **Tags** — the 5 most related tags for the post (Medium-style, e.g., `Cybersecurity`, `Self Hosting`, `Raspberry Pi`, `Privacy`, `Docker`).
2. **SEO/AIO title** — max 100 characters. Use the original title if it fits, otherwise a punchier condensed version. Optimized for search engines *and* AI answer engines (clear subject + benefit).
3. **SEO/AIO subtitle** — max 140 characters, complementing the title with the concrete value/outcome of the post.

Verify the character counts before delivering; state the counts next to each.

## Linking rules (recap — these matter)

- Other solutions/tools/papers mentioned → real clickable links to their official sites.
- Author's own previous posts → clickable links using the exact URLs from `references/post-index.md`.
- Series posts should link back to the series master index and the directly preceding part when relevant.

## Other tasks

- **Editing/reviewing a draft**: apply the style guide, tighten jokes, verify technical claims, add missing links, add the footer if absent.
- **Titles/subtitles/tags only**: still skim the style guide first; the author's titles have a recognizable pattern (see style guide).
- **Brainstorming topics**: propose ideas that extend existing series or fill gaps visible in `references/post-index.md`.

## Reference files

- `references/style-guide.md` — voice, tone, structure, humor patterns, title formulas. Read this every time before writing.
- `references/post-index.md` — full catalog of published posts with titles, excerpts, and canonical URLs. Use for cross-linking and continuity.

From cslev/skillet, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jul 11, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from cslev

Cite this page

cybersec-blogger skill. Agent Mart. https://agentmart.dev/skills/cslev-cybersec-blogger (last updated 2026-10-24)