AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Write Bilingual Blog

skill-rubenmarcus-portfolio-write-bilingual-blog · by rubenmarcus

Write, translate, revise, or publish paired Portuguese and English Markdown articles for rubenmarcus.dev. Use for new portfolio blog posts, bilingual article pairs, PT/EN synchronization, frontmatter preparation, internal-link planning, article updates, and editorial QA in src/content/blog-pt and src/content/blog.

No reviews yet
0 installs
0 views
view→install

Install

$ agentstack add skill-rubenmarcus-portfolio-write-bilingual-blog

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-rubenmarcus-portfolio-write-bilingual-blog)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
today

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Write Bilingual Blog? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Write Bilingual Blog

Produce two native-sounding versions of one evidence-backed article while keeping facts, structure, links, and frontmatter synchronized.

Workflow

  1. Read .claude/skills/blog-voice/SKILL.md completely before drafting.
  2. Read references/publishing-contract.md completely.
  3. Inspect at least two recent paired posts with related subject matter. Reuse facts and links, not sentences.
  4. Build a fact sheet from user statements, repository evidence, commands, measurements, and existing articles. Mark missing evidence instead of inventing it.
  5. Choose the language closest to the source material as the first draft. For Ruben's personal experience, default to PT-BR first.
  6. Open with a concrete event, number, command, failure, or decision. Do not open with a definition or trend claim.
  7. Write the second language from the fact sheet and argument, not by translating sentence by sentence.
  8. Keep the same internal translation key (the shared filename), date, cover, core headings, claims, examples, and destination URLs across both files. Register a natural PT-BR public slug in src/lib/blog-routes.ts. Localize title, description, prose, link labels, and the Portuguese public URL.
  9. Add internal links only where they advance the argument. Prefer the matching language route when it exists.
  10. Run pnpm text:gate, pnpm check, and pnpm build. Fix every failure caused by the article.

Editorial rules

  • Separate concepts by observable behavior. Do not create labels that differ only rhetorically.
  • Use Ruben's projects as evidence: show the command, loop, file, failure, cost, or measured output.
  • Treat Ralph Starter as a concrete implementation when discussing spec-driven loops, validation feedback, worktrees, provider choice, or pull requests.
  • Distinguish exploration from production. State what changes when code needs users, maintenance, security, or repeatability.
  • Explain jargon on first use without flattening it.
  • Include at least one failed attempt or operating constraint.
  • End with a decision rule the reader can apply.
  • Never manufacture usage numbers, costs, benchmark results, dates, quotes, or implementation details.

Completion gate

Finish only when both Markdown files exist, their frontmatter is paired, their claims agree, the PT slug and redirect are covered by blog-routes, every referenced local route exists, the shared cover path exists, and all three repository checks pass.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.