speaking-reference
Use when correcting a communication or influence misconception, looking up a claimed statistic about body language, attention span or persuasion, finding the sources, or needing a quick-reference picker — plus the current status of the famous body-language claims and what the persuasion evidence now shows. Companion to the other speaking, influence and community skills.
- License 许可
- MIT
- 最近更新
- 2026-11-15
- Stars
- ★ 5
- Forks
- 3
01 前言 Front Matter
- name
- speaking-reference
- description
- Use when correcting a communication or influence misconception, looking up a claimed statistic about body language, attention span or persuasion, finding the sources, or needing a quick-reference picker — plus the current status of the famous body-language claims and what the persuasion evidence now shows. Companion to the other speaking, influence and community skills.
03 SKILL.md 正文
Speaking, Influence and Community: What's Live, Misconceptions, Numbers, and Sources
Part 6 of 6 of the Public Speaking, Influence and Community reference (plugin
speaking-influence-and-community), covering §27–§32. Sibling skills:speaking-what-the-field-knows-anxiety-audience-and-structure(§0–§5),speaking-language-delivery-visual-aids-and-practice(§6–§11),speaking-listening-rapport-difficult-conversations-and-negotiation(§12–§17),speaking-persuasion-and-the-ethics-of-influence(§18–§19),speaking-groups-community-facilitation-organizing-and-conflict(§20–§26). Section numbers are shared across the set; a reference written as §N →skillpoints into that sibling skill.Currency: The craft is old and stable. Two areas have moved. See §27 for the status of the famous body-language claims, and what the persuasion evidence now shows.
⚠️ A domain with an unusually bad ratio of confident advice to actual evidence. ⚠️ A great deal of what is taught in communication training traces to small 1960s studies, misread, or to findings that failed to replicate — and is still being repeated in material published this year (§27.1).
⚠️ This file tries to separate three things: what is well supported, what is craft wisdom that experienced practitioners agree on without formal evidence, and what is folklore.
⚠️ GOTCHA boxes mark where the standard advice is wrong or overstated.
The three ideas that organize this document:
- ⚠️ SUBSTANCE IS THE TECHNIQUE (§4 →
speaking-what-the-field-knows-anxiety-audience-and-structure, §18 →speaking-persuasion-and-the-ethics-of-influence, §27.2). The persuasion evidence points consistently at content — relevant facts, specific evidence, real engagement with the other person's actual position — rather than at delivery tricks. This is both the most reassuring finding for nervous speakers and the least commercially attractive one for the training industry.- ⚠️ INFLUENCE WITHOUT A LEGITIMACY CHECK IS MANIPULATION (§19 →
speaking-persuasion-and-the-ethics-of-influence). The techniques in this file work on people who don't want them used. The distinction between persuasion and manipulation is not a matter of degree or intent — it has a testable structure, and it belongs at the front, not in an appendix.- ⚠️ COMMUNITIES ARE MAINTAINED, NOT FOUNDED (§21 →
speaking-groups-community-facilitation-organizing-and-conflict, §24 →speaking-groups-community-facilitation-organizing-and-conflict). Almost all the failure modes are in sustaining: the founder bottleneck, volunteer burnout, unhandled conflict, and the transition from a group that knows each other to one that cannot.
§27. What's Live — checked August 2026
27.1 ⚠️ The body-language claims: still repeated, still wrong
⚠️ §1 → speaking-what-the-field-knows-anxiety-audience-and-structure's folklore tier, with the receipts — and the striking thing is how current the
propagation still is.
- ⚠️ THE 7-38-55 RULE. ⚠️ Mehrabian's 1967 studies asked participants to judge a speaker's FEELINGS from single spoken words in different tones, and then from a word paired with a facial photograph — with samples of 30 and 37 women respectively. ⚠️ The ratio applies only to communicating LIKE/DISLIKE where verbal and nonverbal signals CONFLICT.
- ⚠️ MEHRABIAN HIMSELF DISOWNED THE POPULAR VERSION, stating that his findings are often misquoted and that <cite index="210-1">it is absurd to imply that the verbal portion of all communication constitutes only 7% of the message</cite>.
- ⚠️ The studies never examined body language other than facial expressions, and reporting notes no follow-up studies looked at the ratio in ordinary conversation.
⚠️ GOTCHA — this has been debunked repeatedly for decades and is STILL being published as fact. ⚠️ Among the sources I retrieved in August 2026 are pieces from June 2026 presenting 7-38-55 straightforwardly as a communication model, alongside pieces documenting it as a myth. ⚠️ If you encounter the figure in a training course, that tells you something useful about the course.
- ⚠️ POWER POSING. ⚠️ A series of replication studies found the original findings were not as straightforward as they appeared, and one of the original authors, Dana Carney, posted publicly that as evidence came in over the following years her views updated to reflect it. ⚠️ The commonly reported split: the effect on how OTHERS perceive you is unsurprising and holds; the claimed HORMONAL changes are what failed to replicate.
- ⚠️ The sharpest critique is a structural one worth carrying: ⚠️ one analysis notes that these poses were pushed hardest at the people with the LEAST power, as a substitute for having any — and that if the powerless can gain power by standing differently, then structural inequity gets reframed as a personal failure of posture.
- ⚠️ Deception detection from body language deserves the same scepticism — ⚠️ the same analysis notes the post-9/11 SPOT programme built on microexpression-style premises, and the pattern of small elite-lab studies generalized into headline advice and taken up by the training industry before replication had a chance.
⚠️ What this leaves standing. ⚠️ Nonverbal communication matters — nobody disputes that tone and expression carry information, or that first impressions form fast. ⚠️ What is not supported is the PERCENTAGE claim, the idea that posture hacks your hormones, and the notion that you can read a person's inner state from isolated cues. ⚠️ Even sources sympathetic to body-language training concede that reading requires CLUSTERS of congruent cues, never a single gesture in isolation.
27.2 ⚠️ The persuasion evidence, including a genuinely uncomfortable finding
⚠️ §18 → speaking-persuasion-and-the-ethics-of-influence's mechanisms, now measured at scale — and the headline result has implications well
beyond §19 → speaking-persuasion-and-the-ethics-of-influence.
- ⚠️ CONVERSATION BEATS BROADCAST, measurably. ⚠️ In one large study, AI was substantially more persuasive in conversation than via a static 200-word message — +2.94pp (41% more persuasive) for one model and +3.60pp (52%) for another.
- ⚠️ AND THE EFFECTS ARE DURABLE. ⚠️ A one-month follow-up found between 36% and 42% of the immediate persuasive effect still present at recontact. ⚠️ A separate study on AI-mediated deep-canvassing-style conversations about transgender rights found significant attitude change that ATTENUATED at one-week recontact — so durability varies by topic and method, and sustaining change needs complementary work.
- ⚠️ THE LEVER IS INFORMATION, NOT TECHNIQUE — and this is the most useful finding here. ⚠️ One research summary reports that the primary levers of persuasion were NOT personalisation or model scale but the FACTUAL RICHNESS of responses, with separate work across the US, Canada and Poland finding persuasion happened through presentation of relevant facts and evidence.
- ⚠️ MICROTARGETING IS WEAKER THAN ADVERTISED. ⚠️ The evidence is genuinely conflicting: one study found psychologically-tailored messages significantly more persuasive, while another found only small effects from personalisation. ⚠️ A PNAS study testing customization and elaboration found all four AI strategies produced significant attitude change but no evidence that microtargeting or interactive elaboration added much beyond the baseline.
⚠️ GOTCHA — attitude change and BEHAVIOUR change are not the same thing and may not correlate. ⚠️ One study found sizable AI persuasion effects on behaviour (+19.7 percentage points on petition signing) but NO evidence of correlation between the effects on attitudes and on behaviour — and noted that information-dense conversations, the very feature driving the attitudinal advantage, are LESS effective at moving real-world political action. ⚠️ For anyone doing community or advocacy work this is the practical warning: winning the argument and changing what someone does are separate problems, and success at the first does not deliver the second.
- ⚠️ THE UNCOMFORTABLE RESULT. ⚠️ A June 2026 preprint reports that AI systems out-persuade expert human persuaders — including 19 professional canvassers from a UK firm with a median of roughly 10,000 career conversations. ⚠️ Reported figures: +5.9pp more persuasive than professional canvassers on attitude shift, and nearly 3× more effective at eliciting real-money charitable donations (+17.2pp versus +6.4pp). ⚠️ Coaching elite debaters with an AI tool increased their message length and fact density but only narrowed the gap by about 1.0pp, failing to reach parity.
- ⚠️ The donation measure matters methodologically — as one commentator notes, it is a BEHAVIOUR with a real cost to the participant, not a costless declaration in a survey.
⚠️ What I would actually take from this as a human speaker or organizer. ⚠️ The
findings converge on things that are good news for honest communicators: substance
persuades, conversation beats broadcast, and eliciting someone's view before advancing your
own produces durable change. ⚠️ They are bad news for the trick-based model of
influence. ⚠️ And §19 → speaking-persuasion-and-the-ethics-of-influence becomes structural rather than personal — highly effective
personalized persuasion is now available at scale and near-zero marginal cost, which means
the question is no longer only "am I influencing ethically" but "what happens to a public
sphere in which this is cheap."
⚠️ Sourcing note: this is a fast-moving literature and the headline result is a PREPRINT
that had not, so far as I could establish, completed peer review. ⚠️ The findings on
information density, conversation-versus-static and attitude-behaviour decoupling appear
across multiple independent published studies and I hold those more firmly.
§28. Misconceptions
| Misconception | Correction |
|---|---|
| 93% of communication is nonverbal | ⚠️ Two 1967 studies, n=30 and 37, on conflicting cues about FEELINGS (§27.1) |
| Power posing raises your confidence hormonally | ⚠️ The hormonal claim failed to replicate (§27.1) |
| You can read deception from body language | ⚠️ Weakly supported at best; clusters not single cues (§27.1) |
| Speaking anxiety means you're not cut out for it | ⚠️ It's an ordinary threat response. Exposure is the fix (§2 → speaking-what-the-field-knows-anxiety-audience-and-structure) |
| The goal is to feel calm | ⚠️ The goal is functioning while activated. Reappraise (§2 → speaking-what-the-field-knows-anxiety-audience-and-structure) |
| The audience can see how nervous you are | ⚠️ Far less than you feel it (§2 → speaking-what-the-field-knows-anxiety-audience-and-structure) |
| Delivery is what makes a talk good | ⚠️ Structure and substance dominate (§4 → speaking-what-the-field-knows-anxiety-audience-and-structure, §18 → speaking-persuasion-and-the-ethics-of-influence) |
| Slides carry the talk | ⚠️ Dense slides force a choice between reading and listening (§8 → speaking-language-delivery-visual-aids-and-practice) |
| Bullet points are what slides are for | ⚠️ They're your notes. Use a handout instead (§8 → speaking-language-delivery-visual-aids-and-practice) |
| End with Q&A | ⚠️ Close after it. The last words should be yours (§5 → speaking-what-the-field-knows-anxiety-audience-and-structure, §9 → speaking-language-delivery-visual-aids-and-practice) |
| "I don't know" damages credibility | ⚠️ Bluffing does. Not knowing doesn't (§9 → speaking-language-delivery-visual-aids-and-practice) |
| Filler words are a serious problem | ⚠️ Far less noticeable to audiences than to you (§7 → speaking-language-delivery-visual-aids-and-practice) |
| Mirroring builds rapport | ⚠️ The deliberate version is detectable and costs trust (§13 → speaking-listening-rapport-difficult-conversations-and-negotiation) |
| Listening means waiting politely | ⚠️ It's the mechanism of durable persuasion (§12 → speaking-listening-rapport-difficult-conversations-and-negotiation, §18 → speaking-persuasion-and-the-ethics-of-influence) |
| Someone describing a problem wants a solution | ⚠️ Usually not. Ask which they want (§12 → speaking-listening-rapport-difficult-conversations-and-negotiation) |
| Intent is what matters | ⚠️ You can't know theirs. Speak to impact (§14 → speaking-listening-rapport-difficult-conversations-and-negotiation) |
| The feedback sandwich softens criticism | ⚠️ It gets learned and discounted. Be direct and kind (§16 → speaking-listening-rapport-difficult-conversations-and-negotiation) |
| Conflict means something is wrong | ⚠️ No visible conflict usually means it's suppressed (§17 → speaking-listening-rapport-difficult-conversations-and-negotiation) |
| Facts change minds | ⚠️ Facts help; identity-linked beliefs resist them (§18 → speaking-persuasion-and-the-ethics-of-influence) |
| Microtargeting is enormously effective | ⚠️ Evidence conflicts; measured effects are small (§27.2) |
| Persuasion and manipulation differ by degree | ⚠️ Structurally different. Apply the disclosure test (§19 → speaking-persuasion-and-the-ethics-of-influence) |
| A structureless group has no power structure | ⚠️ It has an invisible, unaccountable one (§20 → speaking-groups-community-facilitation-organizing-and-conflict) |
| The platform makes the community | ⚠️ Purpose, people and rhythm do (§21 → speaking-groups-community-facilitation-organizing-and-conflict) |
| A code of conduct signals safety | ⚠️ Only if enforced. Unenforced is worse than none (§21 → speaking-groups-community-facilitation-organizing-and-conflict, §25 → speaking-groups-community-facilitation-organizing-and-conflict) |
| Volunteers are unpaid staff | ⚠️ Paid in meaning, belonging and being asked (§24 → speaking-groups-community-facilitation-organizing-and-conflict) |
| Burnout is a personal resilience issue | ⚠️ Usually structural. Self-care advice can dodge the fix (§24 → speaking-groups-community-facilitation-organizing-and-conflict) |
| Working around a harmful person keeps the peace | ⚠️ The missing stair. It sacrifices everyone unwarned (§25 → speaking-groups-community-facilitation-organizing-and-conflict) |
| Autistic people have a communication deficit | ⚠️ Double empathy: the difficulty is mutual (§26 → speaking-groups-community-facilitation-organizing-and-conflict) |
| Winning the argument changes behaviour | ⚠️ Attitude and behaviour effects may not correlate (§27.2) |
§29. Numbers and Claims
⚠️ ⚠️ "7-38-55" ⚠️ FOLKLORE as commonly used. n=30 and n=37,
single words, conflicting cues, attitudes only. ⚠️ Mehrabian
himself called the general reading absurd
⚠️ ⚠️ "Fear of public speaking beats fear of death" ⚠️ traces to
a survey artifact, not a finding about what people fear most
⚠️ Working memory ⚠️ why 3 main points, not 7 (§4)
⚠️ ⚠️ AI conversation vs static message ⚠️ +41% and +52% more
persuasive (reported, two models)
⚠️ ⚠️ Durability at one month ⚠️ 36-42% of effect retained
(reported) · ⚠️ but attenuated at ONE WEEK in a different
study — varies by topic and method
⚠️ ⚠️ AI vs professional canvassers ⚠️ +5.9pp attitude shift ·
donations +17.2pp vs +6.4pp (⚠️ PREPRINT, June 2026)
⚠️ ⚠️ AI persuasion on behaviour ⚠️ +19.7pp petition signing,
⚠️ with NO correlation to attitude effects (reported)
⚠️ ⚠️ Primary persuasion lever ⚠️ FACTUAL RICHNESS, not
personalization or model scale (reported)
⚠️ Elite debater coaching with AI ⚠️ +1.0pp, did not reach
parity (reported, preprint)
§30. Sources
| Source | Why |
|---|---|
| Stone, Patton & Heen, Difficult Conversations | ⚠️ §14 → speaking-listening-rapport-difficult-conversations-and-negotiation. The three-conversations model |
| Fisher & Ury, Getting to Yes | ⚠️ §15 → speaking-listening-rapport-difficult-conversations-and-negotiation. Interests vs positions, BATNA |
| Patterson et al., Crucial Conversations | §14 → speaking-listening-rapport-difficult-conversations-and-negotiation, §17 → speaking-listening-rapport-difficult-conversations-and-negotiation |
| Rogers on listening; Motivational Interviewing (Miller & Rollnick) | ⚠️ §12 → speaking-listening-rapport-difficult-conversations-and-negotiation — and MI has a real evidence base |
| Cialdini, Influence | ⚠️ §18 → speaking-persuasion-and-the-ethics-of-influence — read alongside §19 → speaking-persuasion-and-the-ethics-of-influence, since it is also a manipulation manual |
| Petty & Cacioppo, Elaboration Likelihood Model | §18 → speaking-persuasion-and-the-ethics-of-influence |
| Broockman & Kalla on deep canvassing (Science, 2016) | ⚠️ §18 → speaking-persuasion-and-the-ethics-of-influence, §27.2 — durable attitude change, field experiment |
| Jo Freeman, "The Tyranny of Structurelessness" | ⚠️ §20 → speaking-groups-community-facilitation-organizing-and-conflict. Free, short, and still correct |
| Anderson, TED Talks | §4–§7 → speaking-what-the-field-knows-anxiety-audience-and-structure, speaking-language-delivery-visual-aids-and-practice, craft-level and sensible |
| Tufte on presentation graphics | ⚠️ §8 → speaking-language-delivery-visual-aids-and-practice |
| Milton on the double empathy problem | ⚠️ §26 → speaking-groups-community-facilitation-organizing-and-conflict |
| Kaner, Facilitator's Guide to Participatory Decision-Making | ⚠️ §22 → speaking-groups-community-facilitation-organizing-and-conflict |
§31. Quick Reference
31.1 Picker
| Question | Where |
|---|---|
| Terrified of speaking | ⚠️ Exposure, preparation, reappraisal — in that order (§2 → speaking-what-the-field-knows-anxiety-audience-and-structure) |
| Where do I start writing a talk? | ⚠️ Audience and the one sentence. Not slides (§3 → speaking-what-the-field-knows-anxiety-audience-and-structure, §4 → speaking-what-the-field-knows-anxiety-audience-and-structure) |
| Talk is too long | ⚠️ Cut a whole point, don't speak faster (§4 → speaking-what-the-field-knows-anxiety-audience-and-structure) |
| What goes on the slide? | ⚠️ Not your notes. A handout is a separate document (§8 → speaking-language-delivery-visual-aids-and-practice) |
| Hostile question | ⚠️ Answer the legitimate part calmly. The room is watching (§9 → speaking-language-delivery-visual-aids-and-practice) |
| They won't hear my feedback | ⚠️ Behaviour not character; check the identity layer (§14 → speaking-listening-rapport-difficult-conversations-and-negotiation, §16 → speaking-listening-rapport-difficult-conversations-and-negotiation) |
| Conversation keeps escalating | ⚠️ Pause. Arousal impairs the reasoning you need (§17 → speaking-listening-rapport-difficult-conversations-and-negotiation) |
| How do I actually change a mind? | ⚠️ Listen first, then evidence. Not force (§12 → speaking-listening-rapport-difficult-conversations-and-negotiation, §18 → speaking-persuasion-and-the-ethics-of-influence, §27.2) |
| Is this persuasion or manipulation? | ⚠️ Apply the disclosure test (§19 → speaking-persuasion-and-the-ethics-of-influence) |
| Community has stalled | ⚠️ Check onboarding and the founder bottleneck (§21 → speaking-groups-community-facilitation-organizing-and-conflict) |
| Meetings are frustrating | ⚠️ Decide how you'll decide, before discussing (§22 → speaking-groups-community-facilitation-organizing-and-conflict) |
| Volunteers keep leaving | ⚠️ Unbounded asks. Make them specific and time-limited (§24 → speaking-groups-community-facilitation-organizing-and-conflict) |
| Someone is harming the group | ⚠️ Address it. Working around them is the failure (§25 → speaking-groups-community-facilitation-organizing-and-conflict) |
| Is that communication stat real? | ⚠️ If it's 7-38-55, no (§27.1) |
31.2 Before you speak
- [ ] ⚠️ One sentence: what should be different afterwards? (§3 →
speaking-what-the-field-knows-anxiety-audience-and-structure) - [ ] Audience's existing knowledge and beliefs considered (§3 →
speaking-what-the-field-knows-anxiety-audience-and-structure) - [ ] ⚠️ Structure explicit, three main points, signposted (§4 →
speaking-what-the-field-knows-anxiety-audience-and-structure) - [ ] ⚠️ Cut to time, with margin (§4 →
speaking-what-the-field-knows-anxiety-audience-and-structure) - [ ] Opening and closing written out and known cold (§5 →
speaking-what-the-field-knows-anxiety-audience-and-structure) - [ ] ⚠️ Read aloud; stumbles fixed (§6 →
speaking-language-delivery-visual-aids-and-practice) - [ ] ⚠️ Slides carry nothing you'd otherwise say (§8 →
speaking-language-delivery-visual-aids-and-practice) - [ ] ⚠️ Plan for delivering with no slides at all (§8 →
speaking-language-delivery-visual-aids-and-practice) - [ ] Rehearsed standing, aloud, timed (§11 →
speaking-language-delivery-visual-aids-and-practice) - [ ] Likely questions anticipated (§9 →
speaking-language-delivery-visual-aids-and-practice) - [ ] ⚠️ Accessibility: captions, structure, visuals described (§26 →
speaking-groups-community-facilitation-organizing-and-conflict)
31.3 Before a difficult conversation
- [ ] ⚠️ What outcome do I actually want? (§14 →
speaking-listening-rapport-difficult-conversations-and-negotiation) - [ ] ⚠️ What is MY contribution to this? (§14 →
speaking-listening-rapport-difficult-conversations-and-negotiation) - [ ] What might their story reasonably be? (§14 →
speaking-listening-rapport-difficult-conversations-and-negotiation) - [ ] ⚠️ Impact stated, intent not assumed (§14 →
speaking-listening-rapport-difficult-conversations-and-negotiation) - [ ] Private, unhurried, both parties functional (§14 →
speaking-listening-rapport-difficult-conversations-and-negotiation) - [ ] ⚠️ Am I engaging their reasoning or bypassing it? (§19 →
speaking-persuasion-and-the-ethics-of-influence) - [ ] ⚠️ Is there a power asymmetry that changes what's fair? (§19 →
speaking-persuasion-and-the-ethics-of-influence)
§32. Method
§1–§26 → speaking-what-the-field-knows-anxiety-audience-and-structure, speaking-language-delivery-visual-aids-and-practice, speaking-listening-rapport-difficult-conversations-and-negotiation, speaking-persuasion-and-the-ethics-of-influence, speaking-groups-community-facilitation-organizing-and-conflict draws on long-established craft and on the more durable parts of the research
literature — structure and comprehension, exposure for anxiety, the three-conversations
model, interests versus positions, the tyranny of structurelessness, and the facilitation
practices. ⚠️ I have tried throughout to mark which tier a claim sits in (§1 → speaking-what-the-field-knows-anxiety-audience-and-structure), because
this field's central problem is confident advice with no evidence behind it.
Two searches were run in August 2026, on the status of famous body-language claims and the persuasion evidence — ⚠️ both chosen because they are places where widely taught material is either wrong or has been overtaken, and where knowing the current state changes what you should actually do.
Confidence. High in §19 → speaking-persuasion-and-the-ethics-of-influence and §12 → speaking-listening-rapport-difficult-conversations-and-negotiation, which are the sections I'd most want read.
⚠️ The disclosure test — would this still work if I told them exactly what I was doing? —
is the most useful single tool here, because it converts a vague ethical unease into a
question with an answer. ⚠️ And §12 → speaking-listening-rapport-difficult-conversations-and-negotiation's finding that listening is not politeness but the
actual mechanism of durable persuasion is the thing that most changes how people behave once
they believe it.
⚠️ §24 → speaking-groups-community-facilitation-organizing-and-conflict's specific bounded ask is the small practical technique with the largest effect on
community sustainability that I know of.
High on §27.1, which is unusually well-documented: ⚠️ Mehrabian's studies used 30 and 37 participants, single spoken words, and conflicting cues about attitudes — and Mehrabian himself publicly rejected the general reading. ⚠️ The observation I'd most want carried is the meta-one: I retrieved sources from June 2026 presenting 7-38-55 as fact alongside sources documenting it as myth, which tells you the correction has not propagated and that encountering the figure is diagnostic of the source. ⚠️ On power posing I have deliberately reported the split — perception effects hold, hormonal claims did not replicate — rather than the flattened "it's debunked," because that is what the evidence actually says.
Moderate on §27.2, and deliberately calibrated. ⚠️ The headline result — AI out-persuading professional canvassers — is a June 2026 PREPRINT, and I have marked it as such rather than treating it as established. ⚠️ What I hold more firmly, because it appears across multiple independently published studies, is the set of mechanism findings: conversation beats static messaging substantially, factual richness rather than personalization is the primary lever, microtargeting effects are smaller and more contested than the popular narrative implies, and attitude change and behaviour change can be uncorrelated. ⚠️ That last one is the practically important warning for anyone doing advocacy work, and it is the finding most likely to be ignored because it is inconvenient.
04 同仓库更多 Skills
white-paper-writing
Use when writing white papers, technical reports, policy documents, thought leadership pieces, or any long-form authoritative document. Triggers on requests to write, structure, outline, or review white papers, technical reports, position papers, policy briefs, or evidence-driven arguments. Also use for B2B content marketing strategy, technical documentation requiring authority, academic-style reports, or any document that must educate while persuading. Use when someone asks "how should I structure this" for a long-form document.
prose-technical-mechanics
Use when editing or writing prose at a technical/mechanical level: choosing between Anglo-Saxon and Latinate diction, placing information in topic vs stress positions, writing periodic vs cumulative sentences, handling sentence rhythm, punctuation as logic, transitions, paragraph structure, or phonesthetics. Use when someone wants to understand WHY prose works or doesn't, not just surface-level style advice. Triggers on word choice, sentence structure, emphasis, rhythm, diction, or any deep writing mechanics question.
prose-mechanics
Use when writing, editing, or analyzing prose style; when trying to avoid generic AI-sounding writing; when applying specific prose styles such as journalistic, academic, narrative, KJV biblical, Hemingway plain, Latinate/Jamesian, Orwellian, Augustan, Victorian, Early Modern (Bacon, Browne, Milton), or free indirect discourse; or when coaching someone on writing voice and mechanics. Triggers on any request to improve, analyze, or write in a specific prose style, to fix "AI-sounding" writing, to make prose more vivid or concrete, to vary sentence rhythm, or to understand how a particular writer achieves their effects.
narrative-structure
Use when structuring stories, pitches, presentations, white papers, or any persuasive narrative; analyzing the hero's journey in fiction or non-fiction; applying StoryBrand for business communication; designing narrative arcs for thought leadership; or understanding Vogler, Snyder, Propp, or Campbell frameworks. Triggers on any narrative structure, storytelling, pitch structure, StoryBrand, hero's journey, three-act structure, Freytag, Save the Cat, narrative arc, or "how should I structure this story/pitch/presentation" request.
legal-brief-writing
Use when writing legal briefs, motions, or any court filing; when analyzing judicial cognition and persuasion; when applying elite brief-writing techniques from Roberts, Clement, Kagan, Garner; or when structuring legal arguments for maximum persuasion. Also use for autistic/neurodivergent advocates who need to understand how their natural communication style maps to elite legal advocacy. Triggers on any legal writing, brief drafting, motion preparation, or legal argument structuring request.
journal-publishability-criteria
Use whenever a research paper, article or preprint is being written, revised, reviewed or published, and specifically before every publication of docs/paper.md. Covers what legitimate journals actually gate on, in order of gating — the editor's desk screen (scope, novelty, package problems), what reviewers judge (methodological soundness, claims the evidence can carry, statistical and qualitative reporting), EQUATOR reporting guidelines, the ICMJE authorship criteria, COPE's view of text recycling, the near-universal generative-AI policy (no AI author, disclosure, author responsibility), TOP 2025 transparency standards, how to verify a journal is legitimate, submitting without an institution, and a pre-submission checklist. Triggers on requests to evaluate, review, prepare or submit a paper, to judge publishability, to write a declarations or data-availability section, to disclose AI use, or to check a journal.