blog-writer
Skill4 starsChanged 19 days agoMITView on GitHub
Use when the user asks for a blog article, blog post, or publishable long-form website content. Use content-writing for general copy and blog-writer for a complete article.
33 other projects use a version of this.
Adopted by
Most recently taken up by
- chaitanyapantheor/claude-skillstheir own version, first seen Oct 25, 2026
- maroffo/claude-forgetheir own version, first seen Oct 25, 2026
- peterbamuhigire/proposal-skillstheir own version, first seen Oct 17, 2026
- google/adk-samplestheir own version, first seen Oct 13, 2026
- google/adk-recipestheir own version, first seen Oct 13, 2026
- TheArchitectit/awesome-cline-skillstheir own version, first seen Oct 13, 2026
Used with
Projects with it also use aminer-data-search, auto-target-tracker and 10 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.
dav-niu474Skillaminer-data-search
使用 AMiner 开放平台 API 进行学术数据查询与分析。当用户需要查询学者信息、论文详情、机构数据、期刊内容或专利信息时使用此 skill。 触发场景:提到 AMiner、学术数据查询、查论文/学者/机构/期刊/专利、学术问答搜索、引用分析、科研机构分析、学者画像、论文引用链、期刊投稿分析等。 支持 6 大组合工作流(学者全景分析、论文深度挖掘、机构研究力分析、期刊论文监控、学术智能问答、专利链分析)以及 28 个独立 API 的直接调用。 即使用户只说"帮我查一下 XXX 学者"或"找找关于 XXX 的论文",也应主动使用此 skill。
Also in 4 projects that use this
dav-niu474Skillauto-target-tracker
自动目标进度追踪器。在对话中检测到目标相关图片(笔记、进度、截图、记录)时,自动调用 VLM 识别关键信息并记录到目标日记。适用于学习管理、健身追踪、工作进度、习惯养成、创作记录等所有目标管理场景。
Also in 4 projects that use this
Liang-MHSkillstock_analysis
获取 A 股、基金和港股的实时行情和技术分析数据
Also in 4 projects that use this
- +9 more from dav-niu474
Other versions33 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 33
- google/adk-recipes★ 11ksame name
- google/adk-samples★ 11ksame name
- microsoft/vscode-docs★ 6.7ksame name
- cosZone/astro-koharu★ 470same name
- KonghaYao/peri★ 252same name
- eunomia-bpf/eunomia.dev★ 244same name
- getnao/sylph★ 195same name
- travsteward/openwriter★ 36same name
- nimbalyst/skills★ 28same name
- maroffo/claude-forge★ 17same name
23 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 repository105 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- finance-policy-and-manualSkill
- governance-and-board-charterSkill
- grants-management-manualSkill
- hr-policy-manualSkill
- internal-controls-and-risk-frameworkSkill
- me-framework-documentSkill
- procurement-policy-and-manualSkill
- ecommerce-business-model-diagnosticSkill
- ecommerce-unit-economics-and-cross-border-margin-modelSkill
- ict-product-company-business-planSkill
- ict-services-firm-business-planSkill
- hospitality-hotel-restaurantSkill
- industry-guidesSkill
- east-african-englishSkill
- language-standardsSkill
- writing-qualitySkill
- demand-forecastingSkill
- digital-marketing-strategySkill
- entrepreneurial-demand-generationSkill
- marketing-plan-orchestratorSkill
- meta-accounting-finance-reviewSkill
- meta-agent-bankability-and-investor-readinessSkill
- meta-agent-revenue-recognition-policySkill
- meta-agent-sla-financial-controlsSkill
- meta-agent-valuation-adjustmentsSkill
- meta-agent-valuation-overlay-for-slaSkill
- meta-ai-bankability-and-investor-readinessSkill
- meta-ai-valuation-adjustmentsSkill
- meta-bankability-scoringSkill
- meta-financial-stress-testSkill
- meta-investment-committee-red-teamSkill
- meta-valuationSkill
- meta-pitch-preparationSkill
- meta-presentation-designSkill
- pitch-deckSkill
- meta-premium-go-to-marketSkill
- meta-pricing-strategySkill
- meta-website-investment-planningSkill
- meta-agent-board-and-investor-reportingSkill
- meta-board-and-investor-reportingSkill
- benchmark-methodologySkill
- business-plan-orchestratorSkill
- competitive-platform-analysisSkill
- competitive-report-structureSkill
- idea-testingSkill
- kaizen-improvement-systemSkill
- meta-business-model-designSkill
- meta-consulting-synthesisSkill
- meta-critical-thinking-business-logicSkill
- meta-digital-transformationSkill
- meta-due-diligenceSkill
- meta-international-market-entrySkill
- meta-living-plan-governanceSkill
- meta-market-validationSkill
- meta-monitoring-evaluationSkill
- meta-operational-readiness-due-diligenceSkill
- meta-quarterly-gameplanSkill
- meta-statisticsSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
30 rules. 0 are common, 28 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 31 edited versions we read keep these.
28
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Use this skill to write and publish a full blog article workflow, including topic development, article drafting, on-page structure, and …
- Distinctive: line 20
Use when the user asks for a blog article, blog post, or publishable long-form website content.
- Distinctive: line 21
Use when the task includes article structure, SEO, and website content integration.
- Distinctive: line 22
Use when an approved topic needs to become a finished article.
- Distinctive: line 26
Do not use for raw idea generation without committing to article production.
- Distinctive: line 27
Do not write on topics the client cannot credibly support with expertise or examples.
- Distinctive: line 28
Do not prioritise SEO formulas over usefulness, voice, and trustworthiness.
- Distinctive: line 47
Read the client and site context before drafting.
- Distinctive: line 101
Read these files first:
- Distinctive: line 112
Read the reference files as needed during writing:
- Distinctive: line 154
Write as the author would write for a business audience the register of a senior professional writing a LinkedIn article or industry blog.
- Distinctive: line 162
Practical focus: Every article should leave the reader with something they can use.
- Distinctive: line 175
Contraction calibration: Use contractions sparingly for natural rhythm (don't, can't, it's 2-4 per 500 words).
- Distinctive: line 185
Write as a bilingual professional would for francophone African business readers Dakar boardrooms and Abidjan tech meetups, not Parisian …
- Distinctive: line 190
Accents mandatory: Every e, e, e, c, a, u must be correct.
- Distinctive: line 208
Never keyword-stuff: Every instance must read naturally.
- Distinctive: line 209
Alt text: every image has descriptive alt text.
- Distinctive: line 215
Every article page must include:
- Very specific: line 249
Sitemap: remove noindex after first real article so blog pages are indexed
- Very specific: line 250
Page speed: all images optimised via Astro <Image>, lazy loading on in-article images
- Distinctive: line 254
Every article targets at least one keyword cluster.
- Distinctive: line 256
Use the primary service terms from the company profile
- Distinctive: line 258
Prefer long-tail phrases (higher intent, less competition)
- Distinctive: line 385
After writing a blog post, scroll through reading only the section headings.
- Distinctive: line 387
Fix: Don't just repeat what everyone else says.
- Distinctive: line 391
If the site has blog categories and tags:
- Distinctive: line 392
All categories should contain approximately equal numbers of posts
- Distinctive: line 393
If one category is twice as large as the rest, split it into two
- Distinctive: line 394
Do not assign too many categories or tags to a single post
- Distinctive: line 395
Remove tags or categories used only once or twice
“Common” is measured: kept by at least 6 in 10 of the 31 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
<!-- dual-compat-start -->Blog Writer Article Generation Skill
Overview
Use this skill to write and publish a full blog article workflow, including topic development, article drafting, on-page structure, and website integration where the project supports it. It owns the article artifact, not just the idea stage.
Use When
- Use when the user asks for a blog article, blog post, or publishable long-form website content.
- Use when the task includes article structure, SEO, and website content integration.
- Use when an approved topic needs to become a finished article.
Do Not Use When
- Do not use for raw idea generation without committing to article production.
- Do not write on topics the client cannot credibly support with expertise or examples.
- Do not prioritise SEO formulas over usefulness, voice, and trustworthiness.
- Route to
content-writinginstead for general copy, orblog-writerfor a complete article.
Required Inputs
| Input | Source / provider | Required? | If absent |
| Blog Writer brief and decision audience | Client, plan owner, or approved project files | Yes | Stop before making a recommendation; state the missing decision context. |
| Claims, assumptions, and supporting evidence | Source register, model, research notes, interviews, or operating records | Yes | Separate known facts from assumptions and return a qualified gap list. |
| Authority and delivery constraints | Requesting owner and repository instructions | Yes | Remain read-only and produce a draft or review only. |
- Topic, audience, and commercial purpose of the article
- Client voice, service context, and existing site structure
- Language, SEO, and publishing requirements
- Any related assets, references, or prior article ideas
Workflow
- Read the client and site context before drafting.
- Confirm the article angle, audience intent, and outcome the article should create.
- Draft the article with strong structure, human voice, and useful specificity.
- Apply
premium-commercial-writingwhen the article must build authority, support a premium offer, handle objections, or perform in SEO/AI search. - Apply SEO, design, and publishing integration requirements where relevant.
- Reconcile the article with brand voice, existing content, and site structure.
- Flag unsupported claims, weak sourcing, or missing assets.
Decision, stop, and recovery controls
- Decision point: confirm that the requested output is the publication-ready article package and that the decision concerns whether the article is accurate, distinctive, accessible, and ready for approval.
- Stop condition: halt the affected conclusion if required evidence is missing (approved brief, audience, verified sources, voice, media rights, and publish target) or if the work could lead to this identified risk: publishing unsupported claims or unlicensed media.
- Recovery: obtain the missing record or reviewer, repeat the affected check, and update the exception record before release.
Quality Bar
- The article is useful, credible, and publishable.
- Voice feels human and specific to the client.
- SEO and site-integration needs are met without degrading readability.
- The article advances brand authority or demand generation.
Anti-Patterns
- AI-sounding filler and recycled content patterns.
- Writing for search engines instead of readers.
- Publishing claims or case-study language the client cannot support.
- Copying a visual or editorial pattern that conflicts with the existing site.
- Treating a generic blog writer template as a conclusion. Correction: tie each choice to the named audience, evidence, and operating constraint.
- Applying the wrong neighbouring route to blog writer. Correction: confirm the decision and route to the named neighbour before analysis.
- Treating an assumption as verified evidence. Correction: label it, cite its source or owner, and assign a verification action.
- Recommending action without a decision threshold. Correction: state the measurable acceptance condition and review trigger.
- Recording an unavailable check as passed. Correction: mark it
not assessedand state the consequence for the decision. - Mutating or publishing during an analysis-only task. Correction: remain read-only until the owner gives explicit authority.
Outputs
| Artefact | Consumer | Observable acceptance condition |
| Blog Writer deliverable | Named decision-maker or plan author | The recommended choice, assumptions, countercase, and next action are explicit. |
| Evidence and exception register | Reviewer, funder, board, or implementation owner | Every load-bearing claim is sourced or labelled as an assumption; missing checks are not shown as passes. |
- A finished article draft and related publishing updates where applicable
- SEO and structural elements needed for publication
- Any assumptions, sourcing gaps, or media dependencies
Generate detailed, rich, educating, and captivating blog articles with authentic human voice, professional photography, and full SEO optimisation. Each article is a marketing asset a demonstration of expertise that builds trust and attracts clients through organic search.
Use the frontend-design plugin throughout article page creation for distinctive, high-quality design.
Before Writing
Read these files first:
docs/en/company-profile.md(and all enabled language versions) author background, services, expertisesrc/pages/en/blog.astrocurrent blog index structure (check for existing articles)src/pages/fr/blog.astroFrench blog index (if FR enabled)src/layouts/BaseLayout.astrolayout props, structured data, design systemsrc/styles/global.csscurrent styles (add prose styles if missing)- Existing articles in
src/pages/{lang}/blog/count them to determine layout variation photo-bank/scan for article photos the user has uploadedsrc/assets/images/_catalog.jsoncurrent image catalog
Read the reference files as needed during writing:
references/human-voice-standards.mdREAD FIRST AI vocabulary/phrase/structure blacklists, human voice techniques, self-check (ensures content sounds 100% human)references/writing-craft.md7-step process, sentence craft, paragraph structure, opening hooks, clarity, concisenessreferences/content-strategy.mdaudience segments, buyer journey, SEO strategy, R.E.S.U.L.T.S. framework, blog creation checklist, 5-stage keyword mappingseo/references/seo-content-writing.mdkeyword density rules, search intent types, featured snippets, voice search, on-page SEO checklistsales-copywriting/references/headline-mastery.mdRead for ALL blog headlines (10 formulas + 4 U's scoring)sales-copywriting/references/resistance-and-objections.mdRead for persuasive and opinion articlesreferences/reader-experience.mdtouchpoint mapping, reader types, quality gates, tone calibration, publishing rhythmreferences/storytelling.mdauthentic stories, human touch, cultural markersreferences/editorial-standards.mdpunctuation, capitalisation, numbers, grammar, British spellingreferences/article-design.mdimage requirements, layout variations, design variety systemreferences/ideation-and-research.mdideation techniques, research methods, competitor analysis, headline generationreferences/topic-ideas.mdcurated topic suggestions (project-specific, if present)../premium-commercial-writing/references/seo-ai-search-visibility.mdRead for authority articles, service-led blogs, answer-engine visibility, entity coverage, and search intent matching../premium-commercial-writing/references/commercial-persuasion-patterns.mdRead for premium-offer articles, persuasive opinion pieces, lead magnets, objections, CTAs, and differentiation anglesblog-idea-generator/references/content-formats.md20 content formats with structural templates (How-to, Case study, List, Opinion, Guide, Story, Comparison, etc.)sales-copywriting/references/fascination-bullets.md21 bullet point templates for engaging list items and key takeawayssales-copywriting/references/closing-and-guarantees.mdclosing templates for strong article conclusions and CTAs
User Input
The user provides:
- Article title (or topic idea)
- Brief summary (2-5 sentences describing what the article should cover)
- Photos uploaded to
photo-bank/(at least 3: 1 featured/hero + 2 in-article)
From this simple prompt, generate the complete article pipeline below.
Article Content Pipeline
Build the article from verified research through outline, draft, editorial challenge, source checks, and publishing preparation. Keep research notes and generated media provenance with the article record.
See references/article-production-workflow.md for the detailed procedure.
English Voice
Write as the author would write for a business audience the register of a senior professional writing a LinkedIn article or industry blog. Not academic, not casual.
Read references/storytelling.md for authentic human touch and cultural markers.
- Simple and clear. Short sentences. One idea per paragraph. No jargon without explanation.
- British spelling. organisation, programme, centre, colour, specialise.
- Warm but professional. Polite, measured, confident. Not stiff, not chatty.
- First person where natural. "In my experience" and "I have found" the author has authority.
- Practical focus. Every article should leave the reader with something they can use.
- Real examples. Reference actual business contexts and projects from the company profile.
| Use | Avoid |
| practical, effective, significant | cutting-edge, game-changing, revolutionary |
| I have found that | It is widely acknowledged that |
| In our experience | Research conclusively demonstrates |
| This approach works because | This paradigm shift enables |
| I recommend | One might consider |
| This works | This can potentially |
| Two approaches matter | There are several approaches |
Contraction calibration: Use contractions sparingly for natural rhythm (don't, can't, it's 2-4 per 500 words). Zero contractions sounds like AI or academia. Too many sounds casual.
Commit, don't hedge: Say what you think. "This is the best approach for SMEs" not "This could arguably be considered a viable approach." Readers trust writers who commit.
Read references/editorial-standards.md for punctuation, capitalisation, numbers, and grammar rules.
French Voice
Write as a bilingual professional would for francophone African business readers Dakar boardrooms and Abidjan tech meetups, not Parisian literary prose.
- Formal but accessible. Vous throughout. Professional register. Not stiff or bureaucratic.
- Concrete vocabulary. "entreprise" not "firme", "mettre en place" not "implementer", "formation" not "enseignement".
- No anglicisms where French words exist. Say "logiciel" not "software", "numerique" not "digital", "reseau" not "network". Technical terms (ERP, API, SaaS) stay in English.
- Accents mandatory. Every e, e, e, c, a, u must be correct. Gender agreement verified.
SEO Requirements (Every Article)
On-Page SEO Checklist
- Title tag
{Article Title} {Author Name}(under 60 chars). Must contain primary keyword. Don't write cute-only headlines combine creative hook with search-practical keywords: "The Three-Hour Problem: Fixing Slow Reconciliation in Multi-Branch Retail". Seereferences/writing-craft.mdheadline rules. - Meta description under 155 chars. Must include primary keyword + geographic location.
- URL slug lowercase, hyphenated, keyword-rich:
/en/blog/erp-implementation-mistakes/ - Heading hierarchy one h1 (article title), 4-7 h2s (main sections), h3s for subsections.
- Keyword placement:
- Primary keyword in the title (h1)
- Primary keyword in the first 100 words
- Primary keyword in at least one h2
- Primary keyword in the conclusion
- Secondary keywords distributed naturally through body text
- Never keyword-stuff. Every instance must read naturally.
- Alt text every image has descriptive alt text. Include the primary keyword in the featured image alt.
- Internal links at least 3 per article: one to a service page, one to about/portfolio, one to contact.
- External links link to authoritative sources when citing facts or data (opens in new tab).
Structured Data (Article JSON-LD)
Every article page must include:
{
"@context": "https://schema.org",
"@type": "Article",
"headline": "Article Title",
"author": {
"@type": "Person",
"name": "Author Name",
"url": "https://site.com/en/about/"
},
"datePublished": "2026-03-01",
"dateModified": "2026-03-01",
"publisher": {
"@type": "Organization",
"name": "Company Name",
"url": "https://site.com"
},
"description": "Meta description",
"image": "https://site.com/path/to/featured-image.jpg",
"inLanguage": "en-GB",
"mainEntityOfPage": {
"@type": "WebPage",
"@id": "https://site.com/en/blog/article-slug/"
}
}Technical SEO
- Canonical URL automatic from BaseLayout
- Hreflang links between all language versions (automatic from BaseLayout)
- Open Graph title, description, featured image via
ogImage={heroImg.src}prop on BaseLayout (each article uses its own featured image, not the default site OG image) - Sitemap remove
noindexafter first real article so blog pages are indexed - Page speed all images optimised via Astro
<Image>, lazy loading on in-article images
Keyword Research Per Article
Every article targets at least one keyword cluster. Research what the target audience searches for:
- Use the primary service terms from the company profile
- Append geographic modifiers (city, country, region)
- Prefer long-tail phrases (higher intent, less competition)
- Include the primary keyword and 2-3 secondary keywords naturally
Article Quality Standards
| Element | Standard |
| Word count | 1,500-2,500 words (EN) / 1,800-3,000 words (FR) |
| Paragraphs | 2-4 sentences each, max 5. One idea per paragraph. |
| Headings | h2 for main sections (4-7 per article), h3 for subsections |
| Lists | Use where content is naturally enumerable (max 9 items per list) |
| Images | 1 featured + 2-4 in-article (at least 1 landscape + 1 portrait) |
| Stories | At least 1 concrete story from the author's experience |
| Internal links | At least 3 (service, about/portfolio, contact) |
| CTA | Natural call to action in the conclusion |
| Read time | Calculate at 200 words/min (EN) or 180 words/min (FR) |
Publishing Checklist
Quality Gates (from references/reader-experience.md)
- 8-Second Test title, hero image, and first paragraph make you want to keep reading
- Scanner Test headings, bold text, and first sentence of each section convey the key points
- So-What Test every major claim is followed by what the reader can do with it
- Ambiguity Test no word could mean two things to a non-native English speaker
- Touchpoint Test every transition feels natural and the conclusion has a clear "what's next"
Content Quality
- Article is detailed, educating, and provides genuine value
- At least one authentic story with specific details (places, outcomes)
- Concrete language throughout no vague abstractions
- Active voice in 90%+ of sentences
- Opening hook captures attention (not a definition or generic statement)
- Conclusion has a clear, natural CTA
- No filler phrases (in order to, due to the fact that, it is important to note)
- No weak modifiers (really, very, quite, basically, actually)
- Every paragraph connects to the previous one with a logical bridge
Human Voice (from references/human-voice-standards.md)
- Zero Tier 1 AI blacklist words (delve, tapestry, landscape, leverage, realm, navigate, foster, etc.)
- Zero banned AI phrases ("In today's...", "It's important to note...", "Game-changer", etc.)
- Burstiness present 3+ short sentences (<8 words) per 500-word section
- At least 3 clear opinions the author stands behind
- Paragraph lengths vary (1, 2, 3, 4 sentences not all the same)
- Max 2 em dashes in the entire article
- No "Furthermore/Moreover/Additionally" as paragraph openers
- Stories contain at least one sensory or physical detail
- 2-4 contractions per 500 words (natural rhythm, not zero)
Language
- English: British spelling, East African professional tone, warm but measured
- French: formal francophone African register, vous throughout, accents correct
- French article feels native not a translation
Images
- Featured image present, minimum 1200px wide,
loading="eager" - At least 2 in-article images (1 landscape + 1 portrait)
- All images have descriptive alt text
- All images use Astro
<Image>component - Images distributed through article body, not clustered
Design
- Layout variation differs from the previous article
- Design matches article tone and website brand
- Mobile-responsive at 375px, 768px, 1280px
- Author bio section present
frontend-designplugin used for design decisions
SEO
- Title tag under 60 chars with primary keyword
- Meta description under 155 chars with keyword + location
- Primary keyword in first 100 words, one h2, and conclusion
- Article JSON-LD schema with all required fields including image (
heroImg.src) - OG image uses article's featured image via
ogImage={heroImg.src}(not default site OG) - Featured image is landscape orientation for optimal OG/social sharing display
- Internal links to at least 3 other pages
- Featured image alt text includes primary keyword
- Hreflang tags present
Technical
npm run buildpasses with no errors- Blog index updated with new article card
noindexremoved from blog pages (if first real article)- All images tracked in
_catalog.json
References
| File | When to Read |
../../language/writing-quality/references/article-and-blog-phrase-guidance.md | During drafting and review: headline and lede patterns, evidence phrasing, transitions that do not sound machine-made, closings with a concrete next step, before-and-after rewrites |
../../language/writing-quality/references/business-plan-phrase-bank.md | When an article discusses plans, strategy or markets: verb and precision-word banks, evidence classes (fact, assumption, estimate, projection) |
references/writing-craft.md | During outlining and writing 7-step process, lead types (9 techniques), article arc (nut 'graph, full circle), sentence craft, headline SEO formula, clarity, conciseness |
references/content-strategy.md | During planning audience segments, buyer journey, SEO strategy, pillar content, touchpoints |
references/reader-experience.md | During planning and review touchpoint mapping, reader types, quality gates, tone calibration |
references/storytelling.md | During writing authentic stories, cultural markers, the human touch |
references/editorial-standards.md | During proofing punctuation, capitalisation, numbers, grammar, British spelling |
references/article-design.md | During page building layout variations, image placement, design variety |
references/ideation-and-research.md | During planning ideation techniques (clustering, spin, 9 value-adding angles, W5 discovery), research methods (2X rule, evidence types), competitor analysis framework, headline generation |
references/topic-ideas.md | When suggesting topics curated list with keyword targets (project-specific, generated by blog-idea-generator skill) |
../premium-commercial-writing/references/seo-ai-search-visibility.md | When an article must rank, answer search intent, earn AI-search citation, or build topical authority |
../premium-commercial-writing/references/commercial-persuasion-patterns.md | When an article supports a premium offer, lead magnet, sales conversation, or objection-handling goal |
Cross-cutting skills that apply throughout:
language-standardslanguage and tone standards for all languageseast-african-englishdetailed English voice guide (if present in project)premium-commercial-writingcommercial authority, premium positioning, proof, CTAs, and SEO/AI-search visibilitybrand-alignmentvisual and messaging consistency with the overall website brandseomulti-language SEO, hreflang, language-specific sitemaps (ensures articles are SEO-ready)sales-copywritingheadline formulas, fascination bullets, closing techniques (always active for all articles)
Blog Index Page Structure
The blog index page (/en/blog/, /fr/blog/) is one of the most visited pages. Don't just show a grid of latest posts. Structure it for discovery:
- Blog focus statement (1-2 sentences at the top) tell readers what you blog about
- Featured posts row 2-3 hand-picked posts (most popular, posts with lead magnets)
- Newsletter signup prominently placed for visitors impressed by your content
- Topic categories list several post categories so readers can jump to topics of interest
- Latest posts grid chronological listing below the curated sections
Heading Substance Test
After writing a blog post, scroll through reading only the section headings. If a reader could learn everything from the headings alone, the article lacks substance you've written "X obvious things about Y" formatted beautifully but without depth.
Fix: Don't just repeat what everyone else says. Add your own perspective, look at the topic from an unexpected angle, add a twist in the headings while keeping them clear, inject personality and humour.
Blog Taxonomy Rules
If the site has blog categories and tags:
- All categories should contain approximately equal numbers of posts
- If one category is twice as large as the rest, split it into two
- Do not assign too many categories or tags to a single post
- Remove tags or categories used only once or twice
- Show categories early on the page (near the top), not hidden at the bottom in small grey text
- Each category and tag page should have a title and short description
Evidence Produced
| Evidence | Format | Acceptance condition |
| Publication-ready article package decision trace | Sources, calculations, assumptions, countercase, and selected action | A reviewer can trace the selected action and rejected alternatives to the cited inputs. |
| Exception record | Failed and not-assessed checks with owner and due action | The register exposes every unresolved exception that could lead to publishing unsupported claims or unlicensed media. |
Capability and Permission Boundaries
Read supplied records and use non-mutating checks to produce the publication-ready article package; drafting files and previews; publication requires explicit approval is permitted when requested. Do not publish, contact third parties, alter live systems, commit funds, or claim legal, tax, audit, valuation, ESG, or investment assurance without the owner's explicit authorisation and the appropriate reviewer.
Degraded Mode
If approved brief, audience, verified sources, voice, media rights, and publish target cannot be obtained, return a qualified publication-ready article package covering only the checks that remain supportable. Leave this decision unresolved: whether the article is accurate, distinctive, accessible, and ready for approval. Record the evidence owner and next check; an inaccessible source, tool, or reviewer is never a pass.
Decision Rules
| Decision condition | Action | Failure or risk avoided |
| Evidence is sufficient to decide: whether the article is accurate, distinctive, accessible, and ready for approval | Record the conclusion, source trail, owner, and review trigger in the publication-ready article package. | Risk of publishing unsupported claims or unlicensed media |
| Material evidence conflicts or remains uncertain | Draft the disputed section from the verified source notes in two structures and retain the version that answers the reader question without unsupported claims. | Selecting an option without resolving the decision-relevant uncertainty |
| Required evidence is missing: approved brief, audience, verified sources, voice, media rights, and publish target | Mark the decision on whether the article is accurate, distinctive, accessible, and ready for approval not assessed in the publication-ready article package, and send it to the editor and publishing owner. | Otherwise, the work risks publishing unsupported claims or unlicensed media |
Quality Standards
Accept the publication-ready article package only when evidence is sufficient for this decision: whether the article is accurate, distinctive, accessible, and ready for approval. Assumptions and countercases remain visible, calculations and cross-references reconcile, and the reviewer can see how the recommendation addresses the risk of publishing unsupported claims or unlicensed media.
Worked Example
A draft cites a market percentage with no traceable source. Remove or verify the figure, preserve the useful argument, record image rights, and return an unpublished review copy.
<!-- dual-compat-end -->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.

