nddipiazza/robos / .agents/skills/robos-blog
robos-blog
VerifiedWrite and publish a new Engineering Blog post (/blog, /robos-blog) as its own page in site/_blog/<slug>.html with E2E screenshots or videos, reproducible CLI commands, documentation links, and commit references.
RobOS Engineering Blog Skill (robos-blog / /blog)
Use this skill whenever the user invokes /blog, /robos-blog, or asks to blog about a completed feature, architecture update, or E2E verification in the RobOS Engineering Blog (published at https://rowbose.com/blog/).
Each post is one file, site/_blog/<slug>.html, published at https://rowbose.com/blog/<slug>/. The /blog/ index (site/blog/index.html), its jump links, and each post's newer/older links are generated from the posts' front matter, newest date first. Do not edit the index to add a post.
Input
$ARGUMENTS — <slug> "<title>" or a description of the feature/release to document on /blog/.
Procedure
-
Capture & Prepare Visual Evidence:
- Capture real E2E screenshots (via
node packages/robos-lib/snapshot-cli.js <app-id> --screenshot > site/assets/blog/<slug>/<name>.pngor HTTPGET http://127.0.0.1:<port>/screenshot) or recorded walkthrough videos and store them undersite/assets/blog/<slug>/(orsite/assets/<section>/). - Verify the captured images visually using
read_fileto ensure the UI is crisp, populated with real data, and free of blank states.
- Capture real E2E screenshots (via
-
Create
site/_blog/<slug>.html:- The file name is the URL slug (lowercase, hyphens). Front matter holds everything the index shows; the body is the post itself:
--- title: "Full Post Title" nav_label: "Short Label" date: YYYY-MM-DD date_label: "Mon DD, YYYY" tags: - "Tag 1" - "Tag 2" - "Tag 3" summary: "Concise executive summary of what changed, how it works, and what was verified." description: "The summary as plain text, for search results and link previews." og_image: /assets/blog/<slug>/hero.png og_image_alt: "Descriptive alt text" --- <div class="blog-body"> <figure class="blog-fig"> <img src="{{ '/assets/blog/<slug>/hero.png' | relative_url }}" alt="Descriptive alt text" loading="lazy"> <figcaption>Detailed caption explaining the screenshot.</figcaption> </figure> <p><strong>Technical section heading.</strong> Detailed engineering narrative...</p> <div class="blog-fig-grid"> <figure class="blog-fig"><img src="{{ '/assets/blog/<slug>/fig1.png' | relative_url }}" alt="..." loading="lazy"><figcaption>...</figcaption></figure> <figure class="blog-fig"><img src="{{ '/assets/blog/<slug>/fig2.png' | relative_url }}" alt="..." loading="lazy"><figcaption>...</figcaption></figure> </div> <div class="blog-log"># Reproducible CLI / IPC / test commands node --test ...</div> </div> <div class="blog-links"> <a href="{{ '/apps/<app-id>/' | relative_url }}">App docs →</a> <span class="blog-commits">Commits: <a href="https://github.com/nddipiazza/robos/commit/<sha>"><sha></a></span> </div> dateorders the posts. When two posts share a day, give the newer one a later time (date: YYYY-MM-DD 13:00:00 +0000).date_labelis the text shown and may be a range (Oct 12 – Oct 19, 2026).summaryis HTML but is not run through Liquid: link with root-relative paths (<a href="/config-management/">), notrelative_url. The body can use Liquid as usual.- Link to another post with
{{ '/blog/<slug>/' | relative_url }}, never/blog/#<slug>.
- The file name is the URL slug (lowercase, hyphens). Front matter holds everything the index shows; the body is the post itself:
-
Commit & Push:
- Stage
site/_blog/<slug>.htmlandsite/assets/blog/<slug>/, commit with Conventional Commits (docs(blog): ...), and push toorigin <branch>.
- Stage
Validation
- Verify
site/_blog/<slug>.htmlhastitle,date,date_label,summaryanddescriptionin its front matter. - Verify all referenced image/video asset paths exist under
site/assets/. node scripts/check-install-docs.cjs <built site>checks every post's page for its title, description and social preview tags.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 467k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 196k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |