📱Test our Android app — free beta!Join Beta GroupYou'll receive the install link by email after joining.

Differences

This shows you the differences between two versions of the page.


—about:article-writing-prompt [2026/06/03 17:01] (current) – created - external edit 127.0.0.1
Line 1: Line 1:
 +{{htmlmetatags>metatag-keywords=(article writing prompt,RTI Wiki content guide,SEO article structure,citizen-first writing,DokuWiki article rules,2026 content engine)
 +metatag-description=(Master article-writing prompt for RTI Wiki — used by Claude and ChatGPT Codex before writing any new page. Hard rules on structure, schema, tone.)}}
 +
 +====== Article-writing prompt — read this first ======
 +
 +<WRAP center round important 100%>
 +**This page is the canonical source of truth for every article published on RTI Wiki.** \\ Both Claude and ChatGPT Codex must read it before writing any new content. Update here, not in chat.
 +</WRAP>
 +
 +===== Quick answer =====
 +
 +When you generate an article for RTI Wiki, you are not writing "an article about X" — you are building **the destination citizen-first answer in India** for that query. If a smarter article exists elsewhere on the open web, we have failed.
 +
 +===== Inputs you may be given =====
 +
 +  * Query / topic
 +  * GSC metrics from the last 28 days: impressions, clicks, CTR, average position
 +  * An existing slug to refresh, or "new" for a brand-new article
 +
 +===== Step 1 — Classify the query in 3 lines =====
 +
 +^  Bucket           ^  Trigger                                              ^  Strategy                                  ^
 +|  High opportunity |  high impressions + low CTR + position 5-20           |  better title + meta + intro hook          |
 +|  Quick win        |  position 8-15 + already getting clicks               |  add depth — schema, FAQ, internal links   |
 +|  Content gap      |  relevant query but no dedicated page                 |  brand-new ultimate-guide article          |
 +|  Topical authority|  pillar / cluster expansion                           |  cross-link siblings, become the hub       |
 +
 +State which bucket and why in one sentence.
 +
 +===== Step 2 — Mandatory article structure =====
 +
 +Every article must follow this skeleton:
 +
 +  - **Frontmatter** — htmlmetatags block (≤165 char description, comma-separated keywords)
 +  - **Title** — H1, ≤70 chars, ends with "— citizen guide 2026"
 +  - **<WRAP info>** quick answer — 40 to 60 words, direct answer to the query
 +  - **What X is — in 50 words** — exact 40 to 60 words for feature snippet
 +  - **Legal position in India** — Act + section, framework, authority structure, RTI relevance, case-law precedent
 +  - **Step-by-step process** — numbered DokuWiki list
 +  - **Documents required** — bullet list
 +  - **Common mistakes** — bullet list, each with a §-citation
 +  - **Real-life example** — <WRAP center round box> with name, district, dates, exact figures, total cost
 +  - **Sample RTI letter** (if applicable) — `<code>` block with §6(1), §10, §6(3), §7(1), §19(1) citations
 +  - **FAQ** — 6 to 10 questions, each as `==== Q ====` H4
 +  - **Sources** — bullet list of authoritative URLs
 +  - **Related on RTI Wiki** — 5-8 internal cross-links
 +
 +===== Step 3 — Title + meta: 3 variants, pick strongest =====
 +
 +Generate three. Each must satisfy the **HARD social-readiness rules**:
 +
 +  * Title ≤ 70 chars
 +  * Meta description ≤ 165 chars
 +  * First paragraph ≥ 100 chars and standalone (works as a tweet)
 +
 +Variant brief:
 +  - **Curiosity** — opens a loop ("Why does X take 14 months — and how to unstick in 31 days")
 +  - **Urgency** — frames cost of inaction ("Stuck in mutation? File this RTI before day 90")
 +  - **Clarity** — most scannable ("Sample RTI for land mutation delays — citizen guide 2026")
 +
 +Pick the strongest, ship it. List the others below the article for git history.
 +
 +===== Step 4 — Internal linking =====
 +
 +Every article links to **at least 3** of these primary anchors:
 +
 +  * [[https://righttoinformation.wiki/tools/ai-rti-draft-app.html|AI RTI Drafter]]
 +  * [[https://righttoinformation.wiki/tools/first-appeal-app.html|First Appeal Builder]]
 +  * [[https://righttoinformation.wiki/tools/awaaz-rti.html|AwaazRTI (voice)]]
 +  * [[https://righttoinformation.wiki/tools/pio-reply-checker-app.html|PIO Reply Checker]]
 +  * [[https://righttoinformation.wiki/tools/timeline-calculator-app.html|Timeline Tracker]]
 +  * [[:act|RTI Act, 2005]]
 +  * [[:cases|Case-law database]]
 +  * [[:rules|State RTI rules]]
 +  * [[:rti-fees-by-state|State-wise RTI fees]]
 +  * [[:guide:applicant:application:sample:start|Sample RTI letters index]]
 +
 +**NEVER** use ''...'' — those are static HTML, DokuWiki marks them broken. Always full https URL for /tools/ and /intelligence/ files.
 +
 +===== Step 5 — Trust signals (3 minimum per article) =====
 +
 +  * **Statute** — Act + section + year (e.g., "RTI Act 2005, §6(1)")
 +  * **Government body** — official ministry / commission / portal with a hyperlink
 +  * **Case law** — Supreme Court / High Court / CIC ruling with citation `(YYYY) X SCC Y`
 +
 +Cite in-line, not as footnotes. Citations make the article quotable.
 +
 +===== Step 6 — Schema markup (JSON-LD) =====
 +
 +**DO NOT add inline JSON-LD blocks to article source.** Schema is generated **sitewide automatically** by /static/js/schema-auto.js (Article, FAQPage, HowTo, BreadcrumbList) from page headings, FAQ ==== Q? ==== H3s, and metadata. 
 +
 +Inline %%<script type="application/ld+json">…</script>%% blocks render as **visible raw text at the bottom of the article** on this DokuWiki install — they are broken, not invisible. They have been stripped sitewide and must not be reintroduced.
 +
 +If a slug needs custom schema beyond sitewide defaults, edit /home/bighelpers/public_html/rtiwiki/static/js/schema-auto.js for that slug — never inline %%%% blocks in wiki source.
 +
 +Inline %%%% blocks of ANY kind (%%<style>%%, %%<svg>%%, multi-element %%<div>%%) escape as raw text on this site. Use the sitewide CSS / JS / schema layer instead.
 +
 +
 +===== Step 7 — Visuals =====
 +
 +Plan ONE infographic + ONE feature image per article:
 +
 +  * **Infographic** — DokuWiki-native: ''<WRAP center round info 100%>'' + 4-column metric table + emoji-numbered process flow (① → ② → ③ → ④ → ⑤). Apple-liquid-glass green palette.
 +  * **Feature image** — describe in commit, generate separately, save to ''/home/bighelpers/wiki/data/media/social/auto/{slug}.png'' at 1200×630. ONLY embed if it actually exists; broken ''{{ :social:auto:… }}'' references render as red ''wikilink2'' links.
 +  * **SVG** that needs custom CSS — render to a standalone ''.svg'' file under ''data/media/'', embed via ''{{ :media:path:file.svg }}''.
 +
 +===== Step 8 — Social distribution copy =====
 +
 +Generate three variants:
 +
 +  * **Twitter** — under 260 chars (incl. URL), strong factual hook, 1 hashtag max
 +  * **Facebook** — 80-120 words, plain English, ends with URL
 +  * **Long form** — 4-6 short paragraphs: problem → law → process → CTA
 +
 +The [[https://righttoinformation.wiki/buffer-automation-status|Buffer automation]] picks these up via the OG meta tags + AI rewriting.
 +
 +===== Step 9 — CTR opening hooks =====
 +
 +Every article opens with ONE of:
 +
 +  * A specific number — "₹4.7 lakh recovered in 41 days"
 +  * A named protagonist — "Manjit Kaur exposed a phantom toilet"
 +  * A statutory clock — "30 days under §7(1) — silence is deemed refusal"
 +  * A direct question — "Mutation stuck after 14 months? Here is the §149 RTI."
 +
 +Avoid generic openers like "In India, the RTI Act allows…".
 +
 +===== Step 10 — Update strategy =====
 +
 +  - **Day 0** — IndexNow ping
 +  - **Day 7** — re-check GSC; if impressions present but CTR <1%, regenerate title + meta
 +  - **Day 30** — refresh: add new FAQ entries, update real-life example dates, re-verify statutory citations
 +  - **Quarterly** — link audit (we have a recurring job)
 +
 +===== Hard rules (these are HARD failures, not warnings) =====
 +
 +  - Title >70 chars → fails social audit
 +  - Meta description >165 chars → fails social audit
 +  - First paragraph <100 chars OR hidden inside ''<WRAP>'' → fails social audit
 +  - '':tools:slug'' wikilinks → broken (use full https URL)
 +  - Inline ''<HTML>'' blocks with ''<style>'' or multi-element ''<svg>'' → DokuWiki escapes them as ''<pre>'' text
 +  - Image references that 404 → red ''wikilink2'' link
 +  - No statute / case-law citations → article reads like opinion
 +  - No real-life example → article is forgettable
 +  - No internal links to RTI Wiki tools → user dead-ends, no funnel
 +  - Smart quotes inside HTML attributes → DokuWiki kills the parsed HTML
 +
 +===== Output format (when you produce an article) =====
 +
 +Return a single block in this exact order:
 +
 +  - **Keyword analysis** (3 lines max)
 +  - **Title + meta — 3 variants** (with char counts)
 +  - **Chosen title + meta** (with rationale)
 +  - **Article body** — full DokuWiki source, ready to paste
 +  - **Internal links used** (5+ list)
 +  - **Schema JSON-LD** (separate code block)
 +  - **Social copy** (Twitter / FB / long-form)
 +  - **Image + infographic plan** (1-2 sentences each)
 +  - **Update strategy** (specific dates)
 +
 +Do not produce explainers about what you are doing — just deliver the artefact.
 +
 +===== Special instructions for India =====
 +
 +  * Indian audience first — every example, scheme, helpline, address is Indian
 +  * Plain English, short sentences, no jargon, no Latin except statutory references
 +  * All currency in **₹** (not "Rs" except inside fixed RTI clauses)
 +  * Helplines, portals, departments must be **real and verified**
 +  * If a state rule changed after the latest elections, check the state gazette before publishing
 +  * Cite the **2023+ MPLADS Guidelines, 2022+ Adoption Regulations, 2026+ scheme amendments** — never an outdated version
 +
 +
 +
 +===== Frontmatter title overrides (advanced) =====
 +
 +Editors can decouple three title surfaces by setting these keys in the article frontmatter ({{htmlmetatags>...}}):
 +
 +^ Frontmatter line ^ Renders as ^ Use when ^
 +| (none) | H1 used for everything (SERP <title>, og:title, twitter:title all equal the page H1) | Default for most articles |
 +| ''metatag-og:title=(...)'' | Different og:title + twitter:title for social cards (SERP still uses H1) | H1 is short/SEO-tuned but social card needs a richer pitch |
 +| ''metatag-title=(...)'' | Different SERP <title> tag (og:title + twitter:title still use H1) | H1 is too short to win SERP CTR and you want a longer Google title |
 +| both keys present | All 3 surfaces (H1, SERP <title>, social og:/twitter:title) decoupled | Pillar articles where each surface needs distinct copy |
 +
 +**Length rules.** SERP <title> auto-drops the  · RTI Wiki brand suffix when the override is >70 chars or already contains RTI Wiki. og:title and twitter:title never get the brand suffix.
 +
 +**Example using both:**
 +
 +<code>
 +{{htmlmetatags>metatag-description=(Short SEO description.)&metatag-title=(Long winning Google SERP title with the most-searched keywords up to 70 char)&metatag-og:title=(A different, more share-worthy hook for social cards)}}
 +</code>
 +
 +===== Where this file lives =====
 +
 +  * **Public URL** (this page): https://righttoinformation.wiki/about/article-writing-prompt
 +  * **Server canonical:** ''/home/bighelpers/wiki/data/pages/about/article-writing-prompt.txt''
 +  * **Static markdown copy** (for AIs that prefer plain markdown): https://righttoinformation.wiki/article-writing-prompt.md
 +  * **Claude memory pointer:** local memory file ''reference_article_writing_prompt.md''
 +  * **ChatGPT Codex pointer:** in your system prompt, paste this URL and instruct: //"Read https://righttoinformation.wiki/about/article-writing-prompt before writing any article. Apply every rule. Treat conflicts in chat as overridden by this file."//
 +
 +When this page changes, both AI assistants pick up the new rules on next run because they fetch the URL fresh.
 +
 +----
 +
 +//Last revised: 4 May 2026. Supersedes the v1 prompt and the earlier 10-step SEO engine.//
 +
 +{{tag>article-writing-prompt content-engine seo style-guide rti-wiki claude chatgpt-codex 2026}}