writing-blog-posts
Skill21 starsChanged 3 months agoApache-2.0View on GitHub
Create or improve English Kivgraph blog posts with search-intent research, SEO/AEO metadata, authoritative sources and verified landing builds.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- rundesk-ai/skillstheir own version, first seen Nov 15, 2026
- dork-labs/dorkostheir own version, first seen Sep 26, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- dork-labs/dorkos★ 11same name
- rundesk-ai/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- benchmarks/AGENTS.mdAGENTS.md
- internal/AGENTS.mdAGENTS.md
- landing/AGENTS.mdAGENTS.md
- ts-worker/AGENTS.mdAGENTS.md
- web/AGENTS.mdAGENTS.md
- benchmarks/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- internal/CLAUDE.mdCLAUDE.md
- landing/CLAUDE.mdCLAUDE.md
- ts-worker/CLAUDE.mdCLAUDE.md
- web/CLAUDE.mdCLAUDE.md
- adding-a-languageSkill
- autofixSkill
- code-reviewSkill
- merging-pull-requestsSkill
- opening-pull-requestsSkill
- publishing-releasesSkill
- running-testsSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 4 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Very specific: line 8
Use this skill when creating or substantially editing an article under landing/src/content/blog/, or when improving the Kivgraph blog's …
- Very specific: line 21
Read landing/AGENTS.md and inspect the existing blog components, content schema and related articles.
- Distinctive: line 33
Every published article is English and uses the existing collection frontmatter:
- Distinctive: line 57
Use question-style H2s when they match real follow-up searches.
- Very specific: line 63
Add relevant internal links to the closest Kivgraph guide, tool reference, quickstart or related article.
- Distinctive: line 65
Add one or two authoritative external sources when the post makes protocol, platform, language or tool claims.
- Distinctive: line 67
Do not add links solely to satisfy a count or link to competitors without a clear reader benefit.
- Very specific: line 109
Do not edit generated directories such as landing/dist or landing/.astro.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Writing Blog Posts
Use this skill when creating or substantially editing an article under
landing/src/content/blog/, or when improving the Kivgraph blog's search
visibility. It does not apply to product documentation, release notes or
generic copy outside the landing blog.
Goal
Produce a useful article that answers one search intent clearly, earns a click with an accurate title and description, and gives both search crawlers and AI answer engines enough structure and evidence to quote it safely.
Before writing
- Read
landing/AGENTS.mdand inspect the existing blog components, content schema and related articles. Reuse the current route and metadata system. - Identify one primary question or task and the supporting questions that naturally follow it. Use current SERP research when the user asks for search intent, competition or recommendations. SERP patterns are evidence of intent, not monthly search volume; never invent volume or difficulty numbers.
- Choose an angle Kivgraph can support with product behavior, documentation, benchmarks or an authoritative external source. Do not pad a post with generic AI or SEO claims.
Article contract
Every published article is English and uses the existing collection frontmatter:
title: A clear search-facing title
description: A direct 120–160 character answer or promise
pubDate: 2026-08-31
author: Kivgraph
category: One useful topic label
tags:
- primary topic
featured: falseAim for a natural title of roughly 45–60 characters. Put the primary topic in
the title when it reads naturally; avoid repeated brand suffixes, keyword
lists and clickbait. The description is also shown immediately below the
generated H1, so it must answer or frame the query directly rather than merely
describe the company.
The first one or two sentences of the body must answer the primary question in plain text. State the definition, command, decision or result before the background. Do not make the answer depend on bold text, a graphic, a code block or a link being opened.
Use question-style H2s when they match real follow-up searches. Keep paragraphs short, use ordered lists for procedures, and use fenced code blocks for exact commands. Do not add another H1: the blog route renders the article title.
Link deliberately:
- Add relevant internal links to the closest Kivgraph guide, tool reference, quickstart or related article.
- Add one or two authoritative external sources when the post makes protocol, platform, language or tool claims. Verify unfamiliar URLs before publishing.
- Do not add links solely to satisfy a count or link to competitors without a clear reader benefit.
FAQs and structured data
The blog route emits BlogPosting and breadcrumbs automatically. When an
article contains a visible FAQ section, declare the exact same questions and
plain-text answers in the optional faq frontmatter field:
faq:
- question: Does this change the indexed code?
answer: No. Registration and indexing are separate operations.The route turns that field into FAQPage JSON-LD. Keep the frontmatter answers
aligned with the visible Markdown answers; never publish FAQ schema for
questions that the page does not visibly answer. Do not hand-write canonical,
Open Graph, sitemap, RSS or llms.txt markup in an article.
Verification
From landing/, run:
pnpm check
pnpm test
pnpm buildAlso run git diff --check. Confirm the generated article has one H1, a
120–160 character description, a canonical URL, BlogPosting JSON-LD, valid
FAQ JSON-LD when applicable, internal links and a raw Markdown alternate. If a
preview server is available, request the article as HTML and check it returns
200; preview canonical URLs should still point at the production origin.
BabyLoveGrowth's public readability checker can be used as a spot check, one URL at a time. Its public endpoint is rate-limited per IP and its H1/source checks can disagree with the actual HTML, so treat it as feedback rather than the sole acceptance gate. Inspect the page source and the build output before changing correct markup to satisfy a false positive.
Do not edit generated directories such as landing/dist or landing/.astro.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

