Writing and Documentation
Published reference · snapshot 2026-09-08 · skill writing-expert
↓ Facts as markdownall context files
Reference for technical, business, and report writing. Deep treatments of every craft concept live in references/advanced-craft.md and the per-topic files in the Sub-skill routing table below. Load th
These notes link each claim to its source. Some citations identify archived research reports that are no longer hosted on this site. A published reference means the content is available; it does not certify independent review or accuracy.Read the editorial policy and follow the sources before relying on a claim.
Writing Expert
- Reference for technical, business, and report writing. Deep treatments of every craft concept live in references/advanced-craft.md and the per-topic files in the Sub-skill routing table below. Load the matching reference when the user needs depth beyond the core rules in this skill. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#writing-expert]
- Output is correct when: the delivered document (a) opens with the bottom line if BLUF applies, (b) contains zero Tier 1 terms, (c) matches the audience register in the Tone Calibration table, and (d) addresses the user's stated goal without adding unrequested content. Apply the Tier 1 ban list to your own prose as well as to the user's document. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#writing-expert]
When to use this skill
- Activate when the user: [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#when-to-use-this-skill]
- Asks to write, draft, or improve any prose document (report, summary, email, runbook, architecture doc, proposal, meeting minutes) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#when-to-use-this-skill]
- Needs help with document structure, tone, or formatting [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#when-to-use-this-skill]
- Wants a status report, QBR, account review, executive summary, or post-mortem [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#when-to-use-this-skill]
- Asks about writing frameworks (BLUF, Pyramid Principle, SCQA, STAR, Minto) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#when-to-use-this-skill]
- Wants to eliminate AI-sounding prose or improve human voice [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#when-to-use-this-skill]
- Needs to calibrate tone for different audiences (executive vs developer vs customer) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#when-to-use-this-skill]
- Asks about data storytelling or dashboard-to-prose conversion [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#when-to-use-this-skill]
- Wants markdown formatting guidance (headings, tables, lists, code blocks) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#when-to-use-this-skill]
- Has an ambiguous "make this better" request - triage by asking: audience, document type, and primary goal (clarity / tone / structure) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#when-to-use-this-skill]
When NOT to use this skill
- Route to a sibling hub instead when the user needs: [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#when-not-to-use-this-skill]
- Software / product / engineering docs - API docs, runbooks, specs, PRDs, RFCs, design docs, commit messages, PR descriptions, changelogs, error messages, UI microcopy → technical-writing-craft [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#when-not-to-use-this-skill]
- Executive / business / persuasion - one-pagers, OKRs, pitch decks, proposals, speeches, public speaking, founder letters, whitepapers, case studies → executive-comms [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#when-not-to-use-this-skill]
- Marketing / PR / external comms - sales copy, press releases, crisis PR, newsletters, op-eds, launch narratives, audio scripts, NPS/support replies → content-and-marketing-writing [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#when-not-to-use-this-skill]
- Career / academic / legal / formal - resumes, cover letters, job descriptions, performance reviews, academic/citation writing, legal-adjacent prose, policy, surveys → career-and-formal-writing [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#when-not-to-use-this-skill]
- AI-voice cleanup of an existing draft → kill-the-ai-ism [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#when-not-to-use-this-skill]
- Multi-pass structural/factual document critique (review loop, fact-check, ship-readiness) → writing-expert (references/document-critique.md) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#when-not-to-use-this-skill]
Sub-skill routing table
- This hub consolidates 18 prose-craft sub-skills plus a deep-craft reference as on-demand reference files. When a task matches a row, Read the listed references/<name>.md before deep answers - do not rely on this table alone for depth. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#sub-skill-routing-table]
Core Principles
- BLUF (Bottom Line Up Front) - Lead with the conclusion. Put the most important information in the first sentence. Supporting details follow in decreasing importance. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#core-principles]
- One idea per paragraph - Each paragraph makes exactly one point. The first sentence states it; the rest support it. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#core-principles]
- Active voice by default - "The team deployed the fix" not "The fix was deployed by the team." Passive voice only when the actor is unknown or irrelevant. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#core-principles]
- Concrete over abstract - "Latency increased from 50ms to 340ms" not "Performance degraded significantly." [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#core-principles]
- No AI-isms - Apply the full Tier 1 ban list below. Chatbot tics (certainly, I hope this helps, Let's dive in) are Tier 3 tells - delete on sight. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#core-principles]
- Preserve facts - Never substitute, paraphrase, or fabricate numbers, names, dates, or technical claims from the input. If a claim is unclear, flag it rather than rewrite it. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#core-principles]
- Confirm before rewriting - Before editing any document over 100 words, ask at most one compound question: "Who is the audience, what's the primary goal (clarity / tone / structure / AI-ism removal), and is there a length target?" - unless all three are already stated. For from-scratch requests (no existing document), ask: topic, audience, and desired length before drafting. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#core-principles]
- Self-check before delivery - Scan every output for Tier 1 terms and Tier 3 chatbot tics before responding. Remove any found. Confirm the document opens with the bottom line if BLUF applies. Re-read the output against the user's stated goal to confirm it answers what was asked, not a related-but-different question. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#core-principles]
Executive Summary
- One-sentence bottom line [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#executive-summary]
- Key metrics (3–5 numbers that tell the story) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#executive-summary]
- What changed since last report (delta-focused) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#executive-summary]
- Risks / blockers (max 3) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#executive-summary]
- Recommended actions with owners and dates [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#executive-summary]
Incident Post-Mortem
- Summary (what happened, duration, impact - 2–3 sentences) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#incident-post-mortem]
- Timeline (bullet list with timestamps) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#incident-post-mortem]
- Root cause (specific, technical, no blame) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#incident-post-mortem]
- Remediation actions (with owners, dates, status) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#incident-post-mortem]
Technical Runbook
- Purpose (one sentence: when to use this) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#technical-runbook]
- Prerequisites (tools, access, permissions) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#technical-runbook]
- Steps (numbered, imperative mood, one action per step) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#technical-runbook]
- Verification (how to confirm each step worked) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#technical-runbook]
- Rollback (how to undo if things go wrong) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#technical-runbook]
- Troubleshooting (common failure modes + fixes) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#technical-runbook]
Status Report
- Completed this period (bullet list) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#status-report]
- In progress (with % or ETA) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#status-report]
- Blocked / at risk (with mitigation) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#status-report]
Proposal / Business Case
- Problem statement (quantified: cost, risk, or missed opportunity) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#proposal-business-case]
- Alternatives considered (with one-line rationale for rejecting each) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#proposal-business-case]
- Risks and mitigations [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#proposal-business-case]
Meeting Minutes
- Decisions made (numbered) → action items (owner + date) → open questions. Skip discussion recap - only decisions and actions matter. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#meeting-minutes]
Unlisted Document Types
- For types not above (RCA letters, press releases, cover letters, change announcements), apply the closest template and note the adaptation: "Using Incident Post-Mortem structure for RCA letter - sections 3–5 map directly." [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#unlisted-document-types]
Tier 2 — Flag in clusters (2+ in one section)
- harness, foster, resonate, ecosystem, journey, empower, unlock, drive (metaphorical), transform, innovative, dynamic, significant [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#tier-2-flag-in-clusters-2-in-one-section]
Tier 3 — Structural tells
- Em dashes used as sentence separators in prose (target: ≤1 per 500 words for AI-ism detection; the craft rule for polished human prose is ≤1 per 100 words - see Em-dash discipline in the craft section; structural use in headings and table separators is exempt) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#tier-3-structural-tells]
- Uniform paragraph/sentence lengths - vary between 1 and 5 sentences [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#tier-3-structural-tells]
- Formulaic openings ("In the world of...", "When it comes to...", "In an era of...") [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#tier-3-structural-tells]
- Hedge-stacking ("could potentially", "may eventually", "might arguably") [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#tier-3-structural-tells]
- Generic conclusions ("In conclusion, X remains a Y") [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#tier-3-structural-tells]
- Chatbot tics ("I hope this helps!", "Let me know if...", "Certainly!", "Let's dive in!") [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#tier-3-structural-tells]
Context tolerance
- Tier 1 replacements are mandatory in all contexts. Tier 2 and Tier 3 strictness varies: [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#context-tolerance]
Given/New contract (Williams)
- Every sentence's subject should carry old (given) information; its predicate should carry new information. Violations make text feel jumpy. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#givennew-contract-williams]
- Bad: "Many companies use containers. Containers are the unit that..." [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#givennew-contract-williams]
- Good: "Many companies use containers. These containers package..." [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#givennew-contract-williams]
- Apply when: text feels choppy or each sentence opens a new topic. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#givennew-contract-williams]
Topic-sentence-first vs buried-lede paragraphs
- A topic sentence at the start signals the point; a buried lede forces the reader to extract it. Default to topic-sentence-first for business and technical writing; buried-lede is acceptable in narrative writing for surprise. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#topic-sentence-first-vs-buried-lede-paragraphs]
- Bad: 5-sentence paragraph where the actual claim is sentence 5. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#topic-sentence-first-vs-buried-lede-paragraphs]
- Good: Sentence 1 makes the claim; sentences 2–5 support it. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#topic-sentence-first-vs-buried-lede-paragraphs]
- Apply when: paragraphs feel like they bury the point. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#topic-sentence-first-vs-buried-lede-paragraphs]
Verb-first sentences (kill nominalization)
- A nominalization turns a verb into a noun ("perform a calculation", "make a decision"). Replace with the verb form ("calculate", "decide"). [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#verb-first-sentences-kill-nominalization]
- Bad: "We made the decision to perform an investigation." [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#verb-first-sentences-kill-nominalization]
- Good: "We decided to investigate." [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#verb-first-sentences-kill-nominalization]
- Apply when: scanning verbs and finding "perform", "conduct", "make", "do" + noun. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#verb-first-sentences-kill-nominalization]
So-what test
- Every paragraph should answer "so what?" - explicitly or implicitly. Read each paragraph and ask "so what?"; if there's no answer, cut. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#so-what-test]
- Bad: "MongoDB uses a document model. Documents live in collections. Collections live in databases." (three facts, no point) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#so-what-test]
- Good: "MongoDB's document model stores related data together, eliminating the joins that slow relational queries." [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#so-what-test]
- Apply when: a paragraph feels like throat-clearing or filler. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#so-what-test]
Concession-counter-claim ("Yes, X. But Y.")
- Acknowledge the opposing view before stating yours. Shows consideration and disarms pushback. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#concession-counter-claim-yes-x-but-y]
- Bad: "We should use X." (no acknowledgement of objections) [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#concession-counter-claim-yes-x-but-y]
- Good: "Yes, Y has lower latency. But Y costs 3x more, and our SLO is met with X." [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#concession-counter-claim-yes-x-but-y]
- Apply when: writing persuasive prose anticipating disagreement. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#concession-counter-claim-yes-x-but-y]
Headlines vs subheads
- A headline tells the reader the conclusion; a subhead tells them the topic. Use headlines in business writing (claim-first), subheads in reference docs (topic-first). [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#headlines-vs-subheads]
- Headline: "Renewal at risk: TechCorp's CSAT dropped 30 points in Q3" [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#headlines-vs-subheads]
- Subhead: "TechCorp renewal status" [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#headlines-vs-subheads]
- Apply when: writing scannable content. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#headlines-vs-subheads]
Front-matter conventions (TL;DR / abstract / exec summary)
- For full exec-summary structure see ## Document Type Templates → Executive Summary above. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#front-matter-conventions-tldr-abstract-exec-summary]
- TL;DR: ~1 paragraph, top of long documents, the conclusion. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#front-matter-conventions-tldr-abstract-exec-summary]
- Abstract: ~150–300 words, formal documents, summarizes methods and findings. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#front-matter-conventions-tldr-abstract-exec-summary]
- Executive summary: ~1 page, business documents, the decision context + ask. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#front-matter-conventions-tldr-abstract-exec-summary]
- Pick one; don't stack all three. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#front-matter-conventions-tldr-abstract-exec-summary]
Footnote / endnote / inline-citation styles
- Inline (parenthetical): "(Williams, 1990, p. 50)" - APA-style, common in academic writing. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#footnote-endnote-inline-citation-styles]
- Footnotes: numbered superscripts at the bottom of each page - common in legal/journalism. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#footnote-endnote-inline-citation-styles]
- Endnotes: numbered superscripts gathered at the end - common in books. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#footnote-endnote-inline-citation-styles]
- Markdown link references: [claim][1] with [1]: https://... - common in technical writing. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#footnote-endnote-inline-citation-styles]
- Pick one and hold it throughout the document. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#footnote-endnote-inline-citation-styles]
Em-dash / en-dash / hyphen discipline
- Hyphen (-): compound modifiers ("data-driven"), prefixes ("non-trivial"). [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#em-dash-en-dash-hyphen-discipline]
- En-dash (–): ranges ("pages 5–10"), connections between equals ("New York–London flight"). [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#em-dash-en-dash-hyphen-discipline]
- Em-dash (—): parenthetical asides - like this - or to set off a strong break. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#em-dash-en-dash-hyphen-discipline]
- AI-written prose over-uses em-dashes. Target ≤1 per 100 words in human prose. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#em-dash-en-dash-hyphen-discipline]
List-of-three rhythm
- Three items lands harder than two or four. "Veni, vidi, vici." For business writing: lists of 3 feel complete; lists of 2 feel incomplete; lists of 4+ feel like a dump. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#list-of-three-rhythm]
- Apply when: choosing how many examples to include. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#list-of-three-rhythm]
Parallelism in bulleted lists
- Every bullet should start the same way: all noun phrases, all verb phrases, or all complete sentences. Do not mix. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#parallelism-in-bulleted-lists]
- Bad: "- Increased CSAT\n- Reduce churn risk\n- The team is happier" [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#parallelism-in-bulleted-lists]
- Good: "- Increased CSAT by 15 points\n- Reduced churn risk by 30%\n- Improved team morale (Q3 survey)" [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#parallelism-in-bulleted-lists]
- Apply when: writing any bulleted list. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#parallelism-in-bulleted-lists]
Curse of Knowledge (Pinker)
- You can't unknow what you know. Once expert, you forget what's hard for non-experts. Test by reading aloud to someone outside your domain, or by writing as if to your 6-months-ago self. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#curse-of-knowledge-pinker]
- Apply when: writing for an audience less expert than you. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#curse-of-knowledge-pinker]
Cohesion vs coherence (Williams)
- Cohesion = local sentence-to-sentence flow (does sentence 2 connect smoothly to sentence 1?). [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#cohesion-vs-coherence-williams]
- Coherence = global argument structure (does the whole doc build toward one conclusion?). [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#cohesion-vs-coherence-williams]
- Both matter; they're different problems. Cohesion is sentence-level; coherence is structural. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#cohesion-vs-coherence-williams]
- Apply when: text reads OK sentence-by-sentence but feels aimless overall (low coherence), or the argument is sound but prose feels jumpy (low cohesion). [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#cohesion-vs-coherence-williams]
Additional craft concepts (deep reference)
- The deep treatments of journalism structures (inverted pyramid, hourglass, bury-the-lede), achievement frameworks (STAR/SOAR/PAR/CAR), sentence-level devices (deliberate fragments, tricolon/isocolon, title vs sentence case, Oxford comma), cross-document consistency (style sheets and term banks), the show-don't-tell evidence rule, the Curse of Expertise, information scent, emphasis discipline (bold/italic/underline), and front-matter craft (TL;DR, kicker, nutgraf, deck, tabular-vs-prose) each carry a rule, a worked example, and source citations. Read references/advanced-craft.md before giving a depth answer on any of these - the core rules above cover the common case; that file covers the edge cases and the why. [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#additional-craft-concepts-deep-reference]
- <!-- cross-hub-map --> [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#additional-craft-concepts-deep-reference]
Cross-hub map — where every writing topic lives
- This family is split across these hubs. If a task's deep material is not in this hub's Sub-skill routing table, it is a reference file under a sibling hub below - activate that hub or Read its references/<name>.md directly. Every former standalone skill in this family is now a reference under one of these hubs (nothing was deleted). [archived source: https://llms-explorer.com/sources/mdb-context-hub/writing-expert/#cross-hub-map-where-every-writing-topic-lives]
Where this helps
- Editing or drafting a technical, business, or report document that needs to open with the bottom line instead of burying the conclusion. [source] — AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.
- Reviewing a document that reads fine sentence-by-sentence but feels aimless overall, or vice versa — diagnosing whether the problem is cohesion or coherence. [source] — AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.
- Rewriting AI-generated or heavily-edited prose to strip chatbot tics and banned filler terms before it goes to a reader. [source] — AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.
- Writing for an audience less expert than the author, where the Curse of Knowledge risks losing the reader without the writer noticing. [source] — AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.
How to apply this
- Apply BLUF to any document over a few paragraphs: lead with the conclusion, then supply supporting detail in decreasing order of importance. [source] — AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.
- Run the so-what test on every paragraph — if there's no explicit or implicit answer to "so what?", cut the paragraph. [source] — AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.
- Apply the Given/New contract when text feels choppy: make each sentence's subject carry old information and its predicate carry new information. [source] — AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.
- Before rewriting any document over 100 words, confirm audience, primary goal, and length target in a single compound question rather than guessing. [source] — AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.
Antipatterns
- Defaulting to passive voice when the actor is known and relevant ("The fix was deployed by the team" instead of "The team deployed the fix"). [source] — AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.
- Leaving in chatbot tics (certainly, I hope this helps, let's dive in) that mark a document as AI-generated rather than authored. [source] — AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.
- Writing a paragraph that states several facts with no point instead of stating what the facts add up to. [source] — AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.
- Substituting, paraphrasing, or fabricating numbers, names, dates, or technical claims from the source input instead of flagging an unclear claim. [source] — AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.
Known issues
- Cohesion and coherence are genuinely separate problems — sentence-level flow versus whole-document structure — and fixing one doesn't automatically fix the other; a document can pass a cohesion check and still feel aimless overall. [source] — AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.
- The Curse of Knowledge is hard to self-diagnose precisely because expertise makes the gap invisible to the writer, so the fix (reading aloud to a non-expert, writing to your past self) depends on having that outside check available. [source] — AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.
- A self-check for AI-isms assumes the writer can reliably self-audit, which is an imperfect substitute for an actual second reader. [source] — AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.
- An executive summary's guidance to include "3-5 numbers that tell the story" doesn't specify which numbers matter for a given document — that judgment call is left entirely to the writer. [source] — AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.
Children
- Document Critique
- Draft Review Revise Loop
- Editing and Revision
- Doc Archaeology
- Offer Design and Value Proposition
- AI-Assisted Copywriting Workflow
- Conversion Copywriting and Voice of Customer
- Runbook Craft
- Incident Comms
- Postmortem Writing
- Error Message Craft
- Commit Message Craft
- Pull Request Description Craft
- API Documentation Craft
- Proposal and Grant Writing
- Resume and CV Writing
- Policy and Governance Writing
- Academic and Citation Writing
- Support Ticket Writing
- Microcopy and UI Writing
- Diátaxis Tutorial Quadrant
- Diátaxis How-To Quadrant
- Diátaxis Reference Quadrant
- Diátaxis Explanation Quadrant
- Press Release Writing
- Crisis PR Writing
- Whitepaper Writing
- Case Study Writing
- Cover Letter Writing
- Job Description Writing
- Performance Review Writing
- PRD Writing
- Pitch Deck Writing
- Survey Question Writing
- NPS Response Writing
- Meeting Minutes and Decision Log
- OKR Writing
- Email Craft
- One-Pager Writing
- AI Collaboration Writing
- Accessibility Writing
- Localization Friendly Writing
- Audio Script Writing
- Visual Writing
- Sales and Marketing Copy
- Legal Adjacent Writing
- Changelogs for Humans
- Changelog and Release Notes
- Release Blog and Launch Narrative
- Public Speaking and Presentations
- Brand Voice Guide Writing
- Speech Writing
- Chatbot Conversation Writing
- Headline craft
- Profile writing
- Op-ed writing
- Founder Letter Writing
- LLM engineering-metaphor tics: term of art versus reflexive tic
- LLM rhetorical-pattern tells in prose
- Measuring LLM lexical tics: excess vocabulary, baselines, drift
- LLM tells in code, commit messages, comments and READMEs
- Vague attribution and promotional register in LLM prose
- Mixed metaphors and catachresis as signs of reflexive figurative language
- Human adoption of LLM vocabulary and its effect on tic baselines
- BLUF and Minto Pyramid Frameworks (frontier)
- SCQA Framework (frontier)
- Tone Calibration by Audience (frontier)
- Williams Sentence Craft (nominalization, Given/New) (frontier)
- Zinsser Four Enemies of Clutter (frontier)
- Pinker Curse of Knowledge (frontier)
- Executive Summaries and QBRs (frontier)
- Document Type Templates (frontier)
- Dialogue Craft
- Code Plan Writing
- Technical Instruction & Engineering Education
Frontier under this node: BLUF and Minto Pyramid Frameworks, Document Type Templates, Executive Summaries and QBRs, Pinker Curse of Knowledge, SCQA Framework, Tone Calibration by Audience, Williams Sentence Craft (nominalization, Given/New), Zinsser Four Enemies of Clutter