blog-post
Skill2 starsChanged 6 months agoMITView on GitHub
Blog post workflow — research topic, create content brief, write article, SEO optimize, quality review with feedback loop. Orchestrates product-manager, content-writer, and seo-engineer roles for public blog content creation and updates.
27 other projects use a version of this.
Adopted by
Most recently taken up by
- neomjs/neo-agent-skillstheir own version, first seen Nov 15, 2026
- nisarth/claude-skills-storetheir own version, first seen Nov 8, 2026
- alfredang/ai-cmstheir own version, first seen Nov 7, 2026
- alfredang/ai4kidstheir own version, first seen Nov 2, 2026
- rsdlt/rsdlt.github.iotheir own version, first seen Oct 25, 2026
- langchain-ai/deepagentstheir own version, first seen Oct 13, 2026
Used with
Projects with it also use remote-db-sync, tia-frontend-design-site and 5 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
alfredangSkillremote-db-sync
Push local DB content (menus, settings, taxonomy, pages, posts) to the production database via bearer-token-protected sync APIs. Use when the user wants to publish local CMS/admin edits to the live site without logging into the production admin UI, or to extend the sync surface for new tables. Triggers — "push to production", "sync to remote", "deploy menu/settings/page/post", "the live site doesn't show my change".
Also in 3 projects that use this
alfredangSkilltia-frontend-design-site
This site's own design system for Tertiary Infotech Academy (tertiaryinfotech.edu.sg) — light mint public pages, a dark animated matrix-green hero with the fibre-optic globe, generated artwork, Exo 2 + Inter, compact non-template layouts, live-online copy. Load with the user-level tia-frontend-design skill whenever building, restyling or reviewing ANY UI in this repo.
Also in 3 projects that use this
anshul-garg27Skillnewsletter
Create engaging email newsletters with subject lines, sections, and CTAs for Substack, Beehiiv, ConvertKit, or plain email
Also in 3 projects that use this
ukunal91appSkilllead-magnets
When the user wants to create, plan, or optimize a lead magnet for email capture or lead generation. Also use when the user mentions "lead magnet," "gated content," "content upgrade," "downloadable," "ebook," "cheat sheet," "checklist," "template download," "opt-in," "freebie," "PDF download," "resource library," "content offer," "email capture content," "Notion template," "spreadsheet template," or "what should I give away for emails." Use this for planning what to create and how to distribute it. For interactive tools as lead magnets, see free-tool-strategy. For writing the actual content, see copywriting. For the email sequence after capture, see email-sequence.
Also in 3 projects that use this
AnthropicSkillseo-audit
Run a comprehensive SEO audit — keyword research, on-page analysis, content gaps, technical checks, and competitor comparison. Use when assessing a site's SEO health, when finding keyword opportunities and content gaps competitors own, or when you need a prioritized action plan split into quick wins and strategic investments.
Also in 5 projects that use this
VercelSkillfind-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Also in 3 projects that use this
- +1 more from alfredang
Other versions27 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 27
- langchain-ai/deepagents★ 31ksame name
- samuelclay/NewsBlur★ 7.7ksame name
- nteract/semiotic★ 2.7ksame name
- AlemTuzlak/skills★ 45same name
- byronxlg/skillfold★ 15same name
- neomjs/neo-agent-skills★ 11same name
- ropensci-review-tools/ropensci-skills★ 8same name
- xcrrr/claude-skills★ 6same name
- alfredang/ai-cms★ 4same name
- broomva/skills★ 4same name
17 more not listed
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 repository40 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-skillsSkill
- analyze-localSkill
- analyze-prodSkill
- analyzeSkill
- architectureSkill
- asset-validationSkill
- bugfixSkill
- cloud-platformsSkill
- code-reviewSkill
- content-creationSkill
- context-engineeringSkill
- create-prSkill
- deployment-proceduresSkill
- deploy-productionSkill
- deploy-stagingSkill
- docsSkill
- feature-devSkill
- geo-writerSkill
- humanizerSkill
- infra-changeSkill
- marketing-operationsSkill
- marketingSkill
- ml-pipelineSkill
- planSkill
- pre-commitSkill
- productSkill
- project-initSkill
- prompt-engineeringSkill
- qaSkill
- releaseSkill
- run-testsSkill
- security-scanSkill
- seo-reviewSkill
- social-media-managerSkill
- test-localSkill
- test-strategySkill
- ui-ux-designSkill
- worktree-isolationSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. 0 are common, 10 are distinctive, and 7 are very specific to this project.
0
Common
Most of the 23 edited versions we read keep these.
10
Distinctive
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Read AGENTS.md at the project root to identify:
- Very specific: line 19
If marketing/MARKETING.md exists, read it for positioning and content strategy.
- Distinctive: line 23
Ask the user (or extract from context):
- Distinctive: line 25
Action: Create new post / update existing / create series
- Distinctive: line 31
If updating an existing post — read it first, note what needs to change.
- Very specific: line 63
Apply
Agent(content-writer): Use content-creation skill — Blog Post pattern from page-content-patterns.md. - Very specific: line 69
If no project conventions exist — use kebab-case.md naming, ask the user about frontmatter format
- Distinctive: line 73
Follow the approved outline.
- Distinctive: line 88
If cover image needed — describe desired style, mood, composition
- Distinctive: line 119
Run an SEO pass on the draft:
- Very specific: line 142
Add Article or BlogPosting JSON-LD + Person for author (with sameAs links) + Organization
- Very specific: line 143
Add FAQPage JSON-LD if the post contains a FAQ block (questions must match body phrasing verbatim, no duplicate marketing prose)
- Very specific: line 144
Add HowTo JSON-LD for tutorials with 3-8 steps
- Very specific: line 145
Verify: headline, author.sameAs, datePublished, dateModified, description, image
- Distinctive: line 187
Present review findings to the user: If issues found — list them explicitly with the routing decision.
- Distinctive: line 235
When creating a multi-part series:
- Distinctive: line 240
Draft all parts: before publishing the first — ensures consistency and cross-links work
“Common” is measured: kept by at least 6 in 10 of the 23 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Blog Post
End-to-end workflow for creating and updating blog posts. Orchestrates multi-role collaboration: Agent(product-manager) (research, brief, quality gate), Agent(content-writer) (authoring), Agent(seo-engineer) (optimization). Includes a review loop until the post meets quality standards.
0. Gather Context
Read AGENTS.md at the project root to identify:
- Product description and domain (shapes blog topic framing)
- Blog conventions (directory, naming, frontmatter format)
- Brand voice and audience
If marketing/MARKETING.md exists, read it for positioning and content strategy.
1. Define Scope
Ask the user (or extract from context):
- Action: Create new post / update existing / create series
- Topic: Subject, angle, or user-provided idea
- Target audience: Who reads this? (developers, decision-makers, general public)
- Goal: Educate, announce, promote, thought leadership, SEO traffic
- Constraints: Deadline, word count, related posts, brand guidelines
If updating an existing post — read it first, note what needs to change.
2. Research and Content Brief
Apply Agent(product-manager).
2a. Topic Research
Conduct research before writing:
- Web search — find 3-5 top-ranking articles on the topic. Note their angle, depth, and gaps
- Competitive analysis — what do competitors cover? What's missing in the market?
- Data and statistics — find recent, citable data points (studies, surveys, benchmarks)
- Keyword research — identify primary keyword, 2-3 secondary keywords, search intent (informational / commercial / transactional)
- Existing content audit — scan the project's blog directory for related posts. Identify cross-link opportunities
2b. Content Brief
Produce a brief using the Blog Content Brief Template from content-creation skill (content-tools-guide.md → Content Research Workflows section). The brief must include at minimum:
- Working title and angle (what makes this post unique)
- Target audience and search intent (primary + secondary keywords)
- Outline (H2 sections with what each covers)
- Key data points (stats with sources from research)
- Cross-link opportunities (existing posts to link to/from)
- Visual needs (cover image, diagrams, screenshots)
- Word count target
Present the brief to the user. Wait for user approval before proceeding. Adjust outline based on feedback.
3. Write Draft
Apply Agent(content-writer). Use content-creation skill — Blog Post pattern from page-content-patterns.md.
3a. Create the Post File
- Read project's
AGENTS.md— get blog file conventions (directory, frontmatter format, naming) - Create the file with correct frontmatter as defined in the project's conventions
- If no project conventions exist — use
kebab-case.mdnaming, ask the user about frontmatter format
3b. Write Content
Follow the approved outline. For each section:
- Hook introduction — surprising stat, question, or pain point in the first paragraph
- Structured body — short paragraphs (2-3 sentences), break up with lists, tables, code blocks, blockquotes
- Internal links — minimum 3 links to existing blog posts or pages (from brief's cross-link list)
- External links — 1-2 authoritative sources (cite data points from research)
- Key takeaways — bullet list summarizing the post
- CTA — natural, value-first call to action related to the topic
3c. Visual Direction
For each visual need identified in the brief:
- Specify alt text (descriptive, includes keyword where natural)
- Note image placement relative to content
- If cover image needed — describe desired style, mood, composition
4. GEO/AEO Structure Pass
Apply geo-writer skill. This step is mandatory for all blog content.
- Macro structure — single literal H1, 5-9 H2 sections each phrased as a standalone question or declarative topic, TL;DR at the end
- Meso chunking — paragraphs 40-80 words (cap 120), sections 120-180 words, one idea per paragraph, a statistic or named source every 150-200 words
- Micro emphasis — bold 3-5 most quotable phrases per section, bullet lists for 3+ items, tables for 2+ entity comparisons
- Answer-first check — the first sentence of every H2/H3 fully answers the implied question in 30-60 words
- Entity clarity — no pronoun drift across sections, canonical brand terms used verbatim (from
marketing/MARKETING.md) - High-leverage formats — include FAQ block (4-8 Q&A), comparison table, or HowTo steps where natural
- Schema block — prepare
Article+Person+FAQPageJSON-LD (covered in Step 5 SEO pass)
The geo-content rule enforces this for all public-facing text intended to be cited by AI engines.
4.5. Humanize Content
Apply humanizer skill. This step is mandatory for all blog content.
- Scan the draft for AI writing patterns (see
humanizerskill pattern catalog) - Rewrite problematic sections — remove AI-isms, add natural voice
- Anti-AI audit — ask "What makes this obviously AI generated?", list remaining tells, revise
- Verify the humanized text preserves accuracy, maintains the approved outline, and sounds natural when read aloud
GEO and humanizer are complementary: GEO optimizes structure for extraction, humanizer optimizes voice. Run GEO first, humanizer second. The humanize-content rule enforces the humanizer pass for all public-facing text.
5. SEO Optimization
Apply Agent(seo-engineer).
Run an SEO pass on the draft:
4a. On-Page SEO
| Element | Check |
| Title tag | Primary keyword, compelling, 50-60 characters |
| Meta description | Unique, includes keyword, 120-160 characters |
| H1 | Matches title, one per page |
| Heading hierarchy | Logical H1→H2→H3, secondary keywords in H2s naturally |
| URL / slug | Short, descriptive, hyphenated, includes keyword |
| First paragraph | Contains primary keyword naturally |
| Image alt text | Descriptive, keyword where natural |
4b. Internal Link Audit
- Minimum 3 internal links with descriptive anchor text
- Check all internal links are valid (no broken references)
- Anchor text is descriptive (not "click here" or "read more")
- Links are contextually relevant (not forced)
4c. Structured Data (GEO mandatory)
- Add
ArticleorBlogPostingJSON-LD +Personfor author (withsameAslinks) +Organization - Add
FAQPageJSON-LD if the post contains a FAQ block (questions must match body phrasing verbatim, no duplicate marketing prose) - Add
HowToJSON-LD for tutorials with 3-8 steps - Verify:
headline,author.sameAs,datePublished,dateModified,description,image - Validate in Google Rich Results Test and schema.org/validator before merge
4d. Discovery Assets
- New post URL will be included in sitemap (verify sitemap config)
robots.txtdoes not block the blog path- Update
llms.txtif the project maintains one — add the new post entry - Verify canonical URL is correct
6. Quality Review
Apply Agent(product-manager).
Review the complete post against the original brief:
6a. Review Checklist
<review_checklist>
- Brief compliance — all outline sections covered, angle maintained
- Accuracy — facts, statistics, and claims are correct and cited
- Audience fit — language and depth match the target audience
- Completeness — no sections feel rushed or incomplete
- Cross-links — minimum 3 internal links present and relevant
- CTA — natural, value-first, not aggressive
- Visual direction — cover image and inline visuals specified
- SEO — title, meta, headings, keywords all optimized
- No secrets or PII — no internal data, credentials, or personal info
- Brand voice — consistent with project tone and terminology </review_checklist>
6b. Decision Gate
| Result | Action |
| All checks pass | Proceed to Step 7 |
| Content issues (gaps, accuracy, tone) | Route to Step 3 with specific feedback |
| Structure issues (buried lede, walls of text, missing answer-first sections) | Route to Step 4 (GEO pass) |
| AI-sounding text detected | Route to Step 4.5 (humanizer) with specific patterns to fix |
| SEO / schema issues (meta, links, structured data) | Route to Step 5 with specific feedback |
| Brief was wrong (topic shifted, audience changed) | Route to Step 2 to revise brief |
Present review findings to the user. If issues found — list them explicitly with the routing decision. Repeat the loop until the review passes.
7. Publish
7a. Set Publish Status
Based on user intent:
| Intent | Action |
| Publish now | Set frontmatter status to published, set publish date to today |
| Schedule for later | Set status to draft, note the target publish date |
| Part of a series | Set status to draft, add series metadata, link to previous/next parts |
7b. Final File Checks
- Frontmatter is complete (all required fields populated)
- File is in the correct directory
- File name follows project conventions
- No TODO or placeholder text remains in the content
- All images referenced exist or have clear generation instructions
7c. Discovery Assets Update
llms.txtupdated (if maintained)- Sitemap will pick up new file automatically (verify config)
- No
noindexon the new page
8. Summary
## Blog Post Summary
- **Title**: [post title]
- **File**: [file path]
- **Status**: [published / draft / scheduled for DATE]
- **Topic**: [one-sentence summary]
- **Target keyword**: [primary keyword]
- **Word count**: [count]
- **Roles applied**: Agent(product-manager) → Agent(content-writer) → geo-writer → humanizer → Agent(seo-engineer) → Agent(product-manager)
- **Review rounds**: [number of iterations]
- **Cross-links added**: [count — list of linked posts]
- **Discovery assets**: [llms.txt updated: yes/no, sitemap: auto/manual]
- **Follow-ups**: [if any — e.g., create cover image, schedule social media]Content Series Pattern
When creating a multi-part series:
- Plan all parts upfront — titles, topics, publish order in the content brief (Step 2)
- Cross-link between parts — each post links to previous and next in series
- Teaser for upcoming parts — end each post with a preview: "In Part 2, we'll cover [topic]"
- Draft all parts before publishing the first — ensures consistency and cross-links work
- Stagger publishing — space parts 3-7 days apart for engagement
- On publish day — update previous part's teaser to a real link, remove any "(coming soon)" notes
Integration
- Roles:
Agent(product-manager)(research, brief, review),Agent(content-writer)(authoring),Agent(seo-engineer)(optimization) - Skills:
content-creationskill (Blog Post pattern, AI generation tools, content brief template),geo-writerskill (GEO/AEO structure pass — step 4),humanizerskill (AI voice pattern removal — step 4.5) - Rules:
geo-content(auto-enforces GEO structure and schema on public-facing text),humanize-content(auto-enforces humanizer pass) - Follow-up:
/seo-review(deep SEO audit if needed),/pre-commit,/create-pr - Related:
/docs(technical documentation),/ui-ux-design(visual design for blog assets)
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.

