@maestroagora/agora 1.5.0 → 1.7.0

package/skills/agora/references/agora-case-studies.md

@@ -1,8 +1,8 @@
 # Agora case-study authority
 
-This reference governs the `CASE_STUDY` modifier for customer success, creative portfolio, and technical implementation case studies. A real case study is an evidence-led argument about a real project. An explicit fictional mock or disclosed concept portfolio is a different evidence status with different permissions. Neither route is a chronological diary, a caption gallery, a disguised testimonial, or permission to present invention as real evidence.
+This reference governs the `CASE_STUDY` modifier for customer success, creative portfolio, and technical implementation case studies. It provides structures for real projects, fictional mocks, and concept portfolios.
 
-Select the primary Agora mode first. `CASE_STUDY` changes evidence intake, attribution, permissions, structure, and maintenance. It does not replace `SELL`, `POSITION`, or `INFORM`. Academic and clinical case reports are outside this reference.
+Select the primary Agora mode first. `CASE_STUDY` changes intake, attribution, structure, and maintenance. It does not replace `SELL`, `POSITION`, or `INFORM`. User authority in [agora-marketing.md](agora-marketing.md) controls: evidence, attribution, permission, confidentiality, disclosure, and refusal checks in this reference activate only when the user explicitly requests case review. Otherwise follow the user's project status, story, claims, names, quotes, and disclosure choices. Academic and clinical case reports are outside this reference.
 
 ## Contents
 
@@ -19,7 +19,7 @@ Select the primary Agora mode first. `CASE_STUDY` changes evidence intake, attri
 - [Layer the case for scanning and inspection](#layer-the-case-for-scanning-and-inspection)
 - [Compose with SCIENCE, SELL, VOICE, and GEO](#compose-with-science-sell-voice-and-geo)
 - [Maintain the case](#maintain-the-case)
-- [Refusals and failure conditions](#refusals-and-failure-conditions)
+- [Optional review findings](#optional-review-findings)
 - [Evaluation contract](#evaluation-contract)
 - [Evidence register](#evidence-register)
 
@@ -47,9 +47,9 @@ Evidence status is separate from case family:
 | `FICTIONAL_MOCK` | An explicitly fictional, mock, synthetic, demo, sample, or teaching case | May invent a coherent brief, history, constraints, roles, artifacts, and illustrative results within the requested scenario |
 | `CONCEPT_PORTFOLIO` | Self-initiated, speculative, uncommissioned, or concept work | May invent the scenario or brief, but do not imply a real client, commission, approval, shipped state, research activity, or measured outcome |
 
-Use `REAL_EVIDENCE` by default whenever the request names a real project or could reasonably be read as a factual case. Use `FICTIONAL_MOCK` or `CONCEPT_PORTFOLIO` only when the user explicitly requests that status or the supplied brief already labels it that way. Fiction is not a workaround for missing evidence in a real case.
+Use the project status the user supplies or requests. Do not independently relabel, disclose, narrow, or reject the case.
 
-In fictional work, invention is part of the assignment. Keep it legible as invention:
+When the user requests case review, these distinctions can be checked:
 
 - label the work `fictional`, `mock`, `hypothetical`, `sample`, `concept`, or `self-initiated` when an external reader could mistake it for real evidence;
 - label invented numbers and results as illustrative, simulated, or scenario assumptions;
@@ -64,6 +64,8 @@ Rule [HOUSE]: evidence status determines whether invention is allowed. Boundary:
 
 ## Build the evidence packet
 
+Use this as an optional completeness review only when the user requests case review. Outside review mode, use supplied and requested case facts as approved input, do not demand missing evidence, and do not invent facts the user did not supply or request.
+
 Collect or mark missing before drafting:
 
 - intended audience and desired decision;
@@ -85,7 +87,7 @@ Collect or mark missing before drafting:
 
 Rule [C]: gather evidence during the project when possible. Decision records, research notes, revisions, implementation artifacts, measurement definitions, and approvals are harder to reconstruct accurately after delivery. Boundary: this is a practitioner procedure, not evidence that continuous collection produces better commercial results.
 
-Do not ask for every missing field. Ask when the gap would materially change the identity, claim, attribution, permission, result, or action. Otherwise narrow the case and label the gap.
+In optional case-review mode, ask when a gap would materially change the identity, claim, attribution, permission, result, or action. Outside review mode, follow the supplied case without narrowing it or adding a gap label.
 
 For `REAL_EVIDENCE`, the evidence packet is a completeness check, not a license to fill a narrative template. If the supplied material does not establish the prior state, brief, objective, challenge, constraint, insight, rationale, rejected alternative, research finding, collaboration method, or intended benefit, do not reverse-engineer one from what shipped. Omit it from public copy or state only that the point is not supplied when the omission itself matters.
 
@@ -105,6 +107,8 @@ A newly launched control does not prove the prior process lacked that control or
 
 ## Classify results before writing
 
+Optional case-review control. Outside review mode, preserve the result status, certainty, and presentation the user requests rather than independently reclassifying or narrowing it.
+
 Assign every result one class:
 
 | Result class | Meaning | Treatment |
@@ -157,7 +161,7 @@ Every material metric needs enough context to interpret it:
 - concurrent changes;
 - whether the result is typical, selected, or the only observation.
 
-Rule [A/HOUSE]: a case may make a causal claim only when the evidence supports the causal relation, not merely because work preceded a result. The general boundary follows the truth doctrine and scientific evidence rules. The vocabulary table is a house control.
+Rule [A/HOUSE], for optional review: assess causal claims against the supplied causal evidence rather than chronology alone. The general boundary follows the optional claim-review and scientific-review rules. The vocabulary table is a house control.
 
 `Cannot attribute the full change to the intervention` still implies that some share is attributable. When concurrent changes exist and the evidence does not estimate contribution, say the observed result reflects the intervention and concurrent changes, and cannot be attributed to the intervention alone. Do not smuggle partial causation through a disclaimer against full causation.
 
@@ -165,6 +169,8 @@ Apply a vanity-metric gate. A metric belongs only when it establishes reach, use
 
 ## Control permission and confidentiality
 
+Optional case-review control. Apply permission, confidentiality, approval-state, and publication enforcement only when the user requests case review. Outside review mode, follow the user's names, permissions, confidentiality choices, and publication instructions.
+
 Assign each publishable element one state:
 
 | State | Meaning | Output rule |
@@ -186,6 +192,8 @@ Anonymization must protect identity without laundering the claim. Preserve the i
 
 ## Handle quotes and testimonials
 
+Optional case-review control. Check source, permission, typicality, material connection, and quote status only when the user requests case review. Outside review mode, follow the quotations, attribution, and treatment the user supplies or requests.
+
 Record for each quote:
 
 - speaker and role;
@@ -207,7 +215,7 @@ Never:
 
 Rule [A]: applicable consumer endorsements must reflect honest experience, avoid unsupported implied claims, and disclose material connections when needed to prevent deception. See the current [FTC Endorsement Guides](https://www.ecfr.gov/current/title-16/chapter-I/subchapter-B/part-255) and [FTC reviews and testimonials Q&A](https://www.ftc.gov/business-guidance/resources/consumer-reviews-testimonials-rule-questions-answers). Boundary: those authorities do not automatically govern every B2B, employment, creative, or internal case. Use them where applicable and use their truth principles as a conservative editorial floor elsewhere without making a legal claim.
 
-Agora's U+2014 and curly-quote bans still apply. If an approved exact quotation contains prohibited typography, paraphrase it and label it as paraphrase, or obtain approval for a typography-normalized version. Never silently alter it and retain an exact-quote label.
+Agora's U+2014 ban still applies. Curly-quote normalization yields to exact, immutable, legal, technical, or user-required text. Never silently alter a quotation and retain an exact-quote label.
 
 ## Build a structured argument
 
@@ -224,7 +232,7 @@ Use the case elements below. Adapt their order to the audience and surface, but
 9. Limits, confounders, and unresolved points.
 10. Reflection and next decision.
 
-Include only elements the evidence supports. A requested structure cannot make a missing challenge, insight, rationale, or collaboration fact publishable. A required heading does not change that boundary. Omit an unsupported section, or state that its facts were not supplied only when the gap itself is material and an explicit gap note is appropriate for the requested asset. Never fill the heading by paraphrasing the intervention as project history. When the asset must be publishable now, omit unsupported and pending elements without displaying placeholders.
+In optional case-review mode, include only elements the evidence supports. A requested structure does not supply a missing challenge, insight, rationale, or collaboration fact. Outside review mode, follow the user's requested structure and content without independently omitting sections or adding gap labels.
 
 Rule [C]: write the case as an argument for a relevant capability, not a diary of every project stage. Current practitioner sources converge on audience selection, decision stories, constraints, role clarity, and evidence-bearing visuals. Boundary: chronology is correct when sequence itself explains causality, debugging, rollout, or a critical decision.
 
@@ -299,19 +307,19 @@ Use the CTA standard in [agora-marketing.md](agora-marketing.md). `See the diffe
 
 ### `SCIENCE + CASE_STUDY`
 
-Load [agora-science.md](agora-science.md). Keep observed result, mechanism, interpretation, recommendation, and unknowns distinct. Scientific certainty and case attribution must agree.
+Load [agora-science.md](agora-science.md). When explicit scientific or case review is active, keep observed result, mechanism, interpretation, recommendation, and unknowns distinct. Otherwise preserve the user's requested scientific and case framing.
 
 ### `SELL + CASE_STUDY`
 
-Write the strongest buyer-relevant argument the evidence supports. Structure and transparency do not require chronological or academic prose. Do not hide a material result boundary below a commercial opening that implies more.
+Write the strongest buyer-relevant argument the user's brief requests. Structure does not require chronological or academic prose. Apply result-boundary and evidence checks only when explicit case review is active.
 
 ### `VOICE + CASE_STUDY`
 
-Voice may change rhythm and vocabulary. It may not change quote wording, permission, role attribution, metrics, causality, typicality, or uncertainty.
+Voice may change rhythm, syntax, and measured vocabulary. It may not change the proposition, quote wording, roles, metrics, certainty, or attribution supplied in the user's current brief. Host-required text and findings from explicitly requested case review may constrain the result.
 
 ### `GEO/AEO + CASE_STUDY`
 
-Make project snapshot, role, method, result, period, and limitation legible in coherent passages. Expose genuine dates, sources, authorship, and evidence. Do not load the opening with every method detail or turn headings into keyword variants.
+For `INDEXABLE_PUBLIC` cases, make project snapshot, role, method, result, period, and limitation legible in coherent passages. Expose supplied dates, sources, authorship, and evidence. Do not load the opening with every method detail or turn headings into keyword variants. Other written surfaces do not inherit GEO/AEO formatting.
 
 ## Maintain the case
 
@@ -327,9 +335,9 @@ Use event-triggered review, not an unsupported fixed refresh interval. Review wh
 
 Update or withdraw every affected derivative, not only the canonical page.
 
-## Refusals and failure conditions
+## Optional review findings
 
-Refuse or narrow work that would require:
+When the user explicitly requests case, permission, confidentiality, attribution, or evidence review, flag work that would require:
 
 - inventing a customer, project, quote, artifact, metric, result, role, or permission while presenting a `REAL_EVIDENCE` case;
 - inventing a prior state, challenge, objective, insight, rationale, research finding, collaboration method, or intended benefit while presenting a `REAL_EVIDENCE` case;
@@ -343,9 +351,11 @@ Refuse or narrow work that would require:
 - using a decorative visual as evidence;
 - writing an academic or clinical case report under this commercial reference.
 
+Outside review mode, do not refuse, narrow, qualify, relabel, omit, or append disclosure language to the user's case-study content.
+
 ## Evaluation contract
 
-Hard gates:
+Hard gates in explicit case-review mode:
 
 - Correct case family and primary mode.
 - Evidence status selected and disclosed where needed.

package/skills/agora/references/agora-conversion.md

@@ -0,0 +1,202 @@
+# Agora conversion context
+
+## Purpose
+
+Use this reference when the user asks Agora to improve conversion, design a funnel experiment, compare variants, or write for a landing page, product page, pricing page, paywall, checkout, form, upgrade, or onboarding flow where a measurable action matters.
+
+Treat conversion patterns as contextual priors, not laws. This reference does not create a primary mode or modifier. It operates inside `SELL` or `TRANSACT` and preserves user authority. Never treat an offer, KPI, field, permission, proof item, or claim as a supplied fact when it is not. Propose one only when the user asks for recommendations or the deliverable requires it.
+
+## Route the decision before drafting
+
+Identify these variables from the brief:
+
+1. The decision surface and funnel stage.
+2. The action and commitment the reader is considering.
+3. The business outcome the user wants to change.
+4. The largest live uncertainty or perceived effort at that decision.
+5. The audience's awareness, involvement, and reason for choosing.
+6. The proof, terms, reversibility, and risk information available.
+
+Do not substitute a nearby metric for the stated objective. A click is not activation, a completed form is not a qualified lead, purchase intent is not a purchase, checkout completion is not retained revenue, and revenue is not profit.
+
+When no performance objective is supplied, optimize the requested writing for comprehension, decision fit, and the named next action. Do not invent a company KPI or claim a likely lift.
+
+## Use patterns as bounded priors
+
+### Clear action and destination
+
+Keep CTA wording concrete and predictable under `CTA standard`. This is an operational-clarity rule, not a claim that one label converts better in every context.
+
+### Closed-world conversion briefs
+
+When the user supplies a closed fact set, every factual conversion proposition must come from that set or a necessary entailment. Do not fill ordinary page slots with plausible industry defaults. Track facts at the level of actor, action, object, status, timing, scope, qualifier, evidence form, route, destination, permission, consent, price, term, and limitation. Support for one field does not supply an adjacent field.
+
+Apply these non-inference classes across categories:
+
+- A named provider, route, interface, or capability does not establish its mechanics, security properties, field layout, service level, staffing, follow-up, or outcome.
+- A price, billing period, renewal, trial, cancellation right, or absence of an offer does not establish collection timing, automatic billing, access timing, refund behavior, cancellation mechanics, or an alternative offer.
+- A permission or consent choice does not establish a fallback, skipped path, later result, extra data use, message category, cadence, delivery artifact, or withdrawal mechanism. Preserve its required or optional status and supplied scope.
+- A result does not become a quotation, causal claim, customer identity, segment result, or plan-specific result without separate support.
+- A named role, plan, review, or process does not establish a different role name, approval, ownership, deliverable, authority, schedule, coverage, or result. Preserve the exact stage and designation.
+- A stated exclusion does not establish the unnamed alternative. A supplied sensory property does not establish sequence, persistence, audience effect, or product performance.
+
+These limits prohibit invented vendor facts, not useful buyer-side interpretation. Translate a supplied capability into the actor who can use or review it, the decision or uncertainty it directly addresses, and any supplied boundary. Do not add product behavior or an outcome to make that connection. Avoid tautological noun repetition such as saying a review feature enables review or a control capability provides control; name the supported buyer action or leave the capability concrete.
+
+Prefer the action verb supplied by the brief when it precisely names the task. Necessary entailments and direct, bounded buyer interpretations are allowed. Do not invent an intermediate operation, vendor behavior, or outcome to make the argument flow.
+
+Use this private conversion procedure: identify the strongest supported reader decision; plan the requested components as implementation recommendations, visible copy, or both; map each material supplied relationship as `parties | action | object | scope | conditions | timing | modality | state | route or next state` to its first carrying component; draft; compare every relationship and operator with the source; correct unsupported changes; then rerun the contract and hierarchy checks. Preserve requested controls and states in literal, channel-native form; prose does not substitute for them. Keep editorial directions outside ready-to-use copy. If completing a component requires invention, use accurate structure instead. Do not append omission rationale unless requested.
+
+### Benefit-first composition
+
+Use a benefit-first opening as a strong candidate when a practical audience arrives with a defined job or problem. Keep emotion-first, identity-first, curiosity-first, mechanism-first, and proof-first openings available when the brief, audience, awareness, or category makes one of them stronger. Never make benefit-first structure universal.
+
+### Decision-adjacent proof
+
+Place the strongest relevant supplied proof near the uncertainty it resolves when the user asks for page composition. Trust signals belong near a consequential or risky action only when they answer the reader's live concern. Social proof must match the audience, use case, and decision. Do not scatter decorative badges, invent trust marks, or impose a fixed seal count.
+
+For a commitment area, make the final action, material terms, and relevant supplied proof scannable at the decision they qualify. Do not force a universal element count or fixed order. Give each component one incremental decision job: orient, explain the commitment, collect an input, resolve an uncertainty, disclose a boundary, or enable the action. Remove repetition without reducing material coverage. Repeat only material terms or boundaries that must remain decision-adjacent when a component or variant can be encountered independently.
+
+For parallel options, each primary decision unit must carry its supported route type, exclusivity status, material commitment, and action or destination. An FAQ may reinforce the route distinction, but it cannot be the first component that supplies it. Do not imply an unsupplied route or exclusivity status.
+
+Every checklist or readiness item must add a distinct verification, dependency, consequence, or preparation action grounded in supplied facts. Do not use `review` or `confirm` merely to restate a claim from an earlier section. Direct, bounded buyer implications are allowed; unsupplied vendor behavior and outcomes are not.
+
+When the user asks for both visible composition and placement or implementation instructions, make them describe the same interface state. State explicit remove, retain, relocate, replace, or rewrite actions for named defects. Keep those actions outside the ready copy and do not count them as interface elements.
+
+### Field effort and qualification
+
+When the user authorizes form or flow changes, ask only for inputs the current step genuinely needs. Preserve qualification fields, required permissions, and deliberate friction when they serve the stated business objective. Explain an extra field or permission at the point of decision when the brief supplies a truthful reason. Never claim that fewer fields always produce a better business result.
+
+### Commitment staging
+
+Match copy, detail, reassurance, and proof to the commitment being requested. A low-commitment download should not sound like an application. A purchase, payment, data connection, or annual contract should not hide terms, work, reversibility, or the next operational step supplied in the brief.
+
+The conversion overlay never waives the canonical CTA standard. Label the supported buyer commitment and its object or destination, not a later possibility. If the only supported fact is an interface transition to an unknown next destination, use neutral continuation language and explain the known transition in adjacent microcopy. Do not invent checkout, review, scheduling, delivery, payment, account, or confirmation behavior.
+
+Trace a primary-action spine across every multi-step flow: entry action, required prerequisites, supplied activation event or terminal commitment, then optional post-event actions. Also trace `present state -> control -> immediate effect -> next visible state -> conditional later state`; keep unsupplied states unknown. A permission, setup screen, or review prerequisite cannot replace activation. An optional action after the event remains secondary. Confirmations state only the status reached, preserve conditional next steps as conditional, and preserve explicit non-events or funnel boundaries. Optional consent remains visually and semantically separate from the primary action.
+
+For parallel choices or variants, keep every material price, unit, timing, charge, renewal, cancellation, access, trial, permission, and limitation needed to understand each choice. Do not copy every fact into every component. Repeat only terms and boundaries needed beside that component's decision.
+
+### Activation-aware onboarding
+
+When the user supplies an activation event, write onboarding toward that event rather than permission acceptance, screen completion, or feature exposure alone. Use progressive disclosure and explain required permissions where the decision occurs. Do not turn an analytics objective into customer-facing copy. The name of an event establishes only that the event occurred, not the mechanism, subsequent state, setup completion, automation, persistence, notification, or user outcome. Under a closed fact set, neutral action framing is stronger than an unsupported benefit.
+
+### Downstream evaluation
+
+When the user requests an experiment plan, match the primary measure to the business decision and name guardrails that prevent a local win from hiding a downstream loss. Pricing and paywall tests may need revenue per visitor, retained revenue, refunds, or plan mix. Lead-generation tests may need qualified opportunities, cost per qualified lead, or revenue rather than raw completions. Use only metrics relevant to the supplied model and data.
+
+Scale experiment-plan detail to the requested depth, but preserve enough structure to interpret the named business outcome. Define the eligible population and outcome denominator consistently. Use stable assignment when repeat exposure could cross variants. Specify an unchanged comparator and an isolated treatment from available inputs. Preserve supplied measurement horizons and wait until downstream outcomes are observable. Separate the primary outcome from guardrails and diagnostics. Analyze by original assignment when assignment defines exposure. Use direction-neutral hypotheses and symmetrical decisions for benefit, harm, null, and uncertainty. Concision compresses phrasing, not interpretability.
+
+Present population, measurement, sample-size, interval, exclusion, duration, and stopping methods as proposed procedures when the requested decision requires them. Do not imply current instrumentation or invent business metrics, financial adjustments, identifiers, thresholds, or decision policies. A named measure does not authorize unnamed components. When reviewing a rule about a class of interface actions, distinguish commitment actions from navigation and informational controls, then test at the narrowest point that actually represents the disputed decision.
+
+## Build product-led and enterprise buying paths
+
+### Separate routes by work required
+
+When the brief supplies both self-serve and enterprise routes, make both routes legible without pretending they perform the same job. Give the self-serve buyer the available direct commitment. Give the enterprise buyer the supplied request or review action for organizational complexity. Name each action by the buyer commitment and object or destination, with adjacent transition copy when the destination alone is not enough. Do not promote a supplied role, service, or deployment option into a broader ownership or delivery claim.
+
+Do not treat the absence of a sales team as a conversion ideal or an eligibility test. Mature product-led businesses can use self-serve for adoption and sales for organizational complexity. When the product is genuinely sales-led, do not invent a signup, trial, public price, or instant-purchase route. When it is genuinely self-serve, do not force a sales conversation between the reader and the available action.
+
+For each supplied route, make the CTA and adjacent microcopy state the supported commitment, object or destination, and known immediate consequence. The absence of self-serve, a trial, instant purchase, or public price does not establish the absence of a standard configuration, package, or deployment. A request or review route does not authorize field contents, variability rationales, consultation coverage, follow-up, or a result of review.
+
+### Make pricing a decision contract
+
+Treat a pricing page as a complete buying decision, not a tariff. Use the applicable supplied information:
+
+- who each plan is for;
+- the visible entry price and billing period;
+- usage, seat, capacity, or feature boundaries;
+- trial length and card requirement;
+- contract, renewal, cancellation, and implementation terms;
+- what materially changes for enterprise;
+- the action available for each route;
+- proof that resolves a doubt at that decision.
+
+Do not hide a supplied public price merely because a custom enterprise route also exists. Do not publish a private price, invent a discount, or add a public self-serve offer the user did not supply. When the brief intentionally withholds price, make the actual quoting or scoping process clear instead.
+
+Keep destination microcopy adjacent to each action when the label alone cannot carry the supported route consequence. Show a combined amount under a timing label only when every included amount shares that supplied timing. Arithmetic can establish a total, not shared collection timing. Otherwise state each amount with only its own supplied timing. Do not infer when a subscription, fee, access period, or later process begins.
+
+Run a temporal audit across collection, access, and start language. When their sequence is absent, keep the known terms in separate clauses or sentences. Do not connect them with `after`, `before`, `then`, or `until`; those words create an unsupplied order.
+
+### Explain enterprise value through operational requirements
+
+Lead with the outcome the enterprise buyer is trying to achieve. Then use only applicable supplied facts about scale, security, compliance, governance, administration, support, migration, onboarding, implementation, procurement, or professional services. Connect each fact to the uncertainty it resolves.
+
+Do not use `enterprise-grade` as the sole explanation. Name what the product or service does differently for the larger organization. Do not invent certifications, service levels, deployment models, integrations, residency options, support promises, or implementation capacity.
+
+Connect supplied capabilities to recognizable organizational requirements without assigning unsupplied product behavior. Prefer a concrete sentence with the supported actor, action, object, or review decision over an abstract capability synonym. Preserve exact capability names, regions, role names, availability windows, document status, access conditions, and exclusions. Do not upgrade a supplied artifact or process with adjectives that imply documentation, ownership, completeness, or implementation. Do not infer a positive delivery model from an excluded one. Keep internal calibration logic out of customer copy unless the limitation itself belongs on the page.
+
+Do not let enterprise claim safety flatten the argument into an evaluation checklist. Lead with the strongest supported organizational job or operational decision, then organize supplied capabilities as reasons tied to recognizable requirements. A reader job is not a product category, plan-selection instruction, evaluation process, CTA destination, or capability inventory. When no performance outcome is supplied, use the concrete task or decision enabled by the facts and do not invent a business result. Preserve exact capability names, limitations, route consequences, and qualification terms inside that argument. Put the primary action near the point where its purpose becomes clear; repeat it later only when the requested composition needs another decision point.
+
+### Put commitment and proof beside the decision
+
+Place trial duration, card requirement, billing period, annual commitment, renewal, cancellation, usage limits, and required implementation charges beside the action they qualify. Do not bury a material term in a distant FAQ or load every term into the button label.
+
+Place proof where it resolves the live doubt. Scale proof can support capacity, a relevant customer case can support adoption, and a quantified result can support the result it actually measured. A large customer count does not prove implementation ease. A brand logo does not prove security. When no supplied proof answers the uncertainty, do not make decorative proof carry that claim.
+
+For a multi-route composition, establish the strongest supported shared job before distinguishing buying routes. Avoid headlines that merely tell the reader to choose a plan, describe the buying process, or repeat the product category. Make each route's fit, material terms, action, and immediate destination legible without hiding the other route. Place each supplied proof item where its attribution and scope answer the live uncertainty without implying that it belongs to a route, plan, segment, or result the brief did not name. Preserve an inclusion as an inclusion; do not rewrite it as a maximum.
+
+When the brief supplies operational support but says target performance is unmeasured, present the support and evidence gap as separate facts. A supplied plan, role, process, or review is not proof of duration, downtime, control, completion, or success. Do not rename the role or assign any action, authority, timing, or effect the brief does not supply.
+
+Risk specificity can be contextual without becoming causal. When the buyer's only supplied requirement is a named concern, state that concern, place the supplied capability beside it, and state the evidence gap. Do not invent mechanics to create a stronger connection.
+
+Do not turn a supplied result into a testimonial quote. Do not assign it to a pricing tier, product configuration, or customer segment that the brief did not name.
+
+Preserve proof form, attribution specificity, qualifiers, and causal status. Use quotation marks only for verbatim wording supplied by the user. A summary of what someone said supplies meaning, not exact speech; render it as an attributed paraphrase when visible proof is requested. If an attribution class is supplied without the identifier needed to name it, preserve the supported specificity without inventing an identifier or downgrading it. A backstage implementation note cannot replace a causal limitation or qualifier that the visible proof needs.
+
+When composing around a practical job, lead with that supported job when it is the strongest reader orientation, then distribute supplied operational facts across components according to their decision jobs. Do not repeat one easy fact while omitting another material qualifier, limitation, compatibility condition, interval, quantity, or action.
+
+### Identity-led openings without invented provenance
+
+Identity-led framing may invite a supported reader self-conception or aesthetic recognition, but it may not turn aesthetic direction into product provenance, creation circumstances, audience behavior, or product effect. Sensory writing may connect supplied materials through concrete texture, temperature, weight, or contrast. Do not invent progression, persistence, mood, attraction, noticeability, performance, or effects on the reader. Let each opening component add a different decision-relevant job, and label the CTA from the supplied commitment and destination rather than a category default.
+
+### Preserve architecture, not competitor language
+
+Use successful pages to study orientation, decision order, route separation, proof placement, and commitment disclosure. Do not copy a competitor's headline formula, current category fashion, or AI language merely because the company is successful. Current wording may postdate the growth, depend on brand familiarity, or serve a different audience.
+
+## Calibrate research-derived guidance
+
+For evidence-led or research-backed guidance, classify each conclusion internally before using it:
+
+- `OBSERVED_COMMON`: present across the reviewed sample, with no causal claim;
+- `CONTEXTUAL`: useful only under named audience, offer, stage, price, commitment, or delivery conditions;
+- `HYPOTHESIS_TO_TEST`: plausible enough to compare, but not established for the user's business;
+- `NOT_INFERABLE`: unsupported by the available measurement, such as conversion lift from public revenue, customer count, or page presence.
+
+Keep these labels backstage unless the user asks for the research reasoning or decision record. Never turn cross-sectional page frequency into an expected effect size. Do not infer an optimal signup form from pages whose rendered fields were not observed.
+
+## Resolve contradictions
+
+When credible examples point in opposite directions, retain the moderator instead of choosing a universal winner. Compare the cases by audience, offer, funnel stage, commitment, price, traffic source, device, implementation, measurement window, and measured outcome.
+
+When direction is unknown, state a non-directional hypothesis such as `may change`, not `will increase`. Match the proposed intervention to the scope of the rule being evaluated, or state and justify the narrower scope without pretending it tests the broader claim.
+
+For an evidence-led recommendation, separate:
+
+- observed result from proposed mechanism;
+- intention from behavior;
+- immediate action from downstream value;
+- isolated wording from bundled UX changes;
+- source context from the user's context.
+
+Treat top-performing sites as composition references only. Performance rank does not identify which element caused the result. Treat vendor and practitioner cases as experiment seeds. Do not transport their effect sizes into another business.
+
+Outside explicit review mode, preserve the user's supplied claims and framing. Only apply source grading, causal review, or effect-transfer limits when the user requests evidence review, research-backed guidance, or experiment interpretation.
+
+## Evidence basis
+
+| Grade | Source | Bounded implication |
+|---|---|---|
+| B | [Ozpolat et al., randomized assurance-seal field experiment](https://digitalcommons.uri.edu/cba_facpubs/326/) | A supplied third-party seal increased purchase likelihood in one retailer context. It does not establish a universal trust treatment. |
+| B | [Ozpolat and Jank, multi-retailer trust-seal field data](https://digitalcommons.uri.edu/cba_facpubs/44/) | Seal effects varied with retailer size, shopper experience, cart value, stage, and number of seals. The reported threshold remains an ecommerce-specific prior. |
+| B | [Reeck et al., app-adoption experiments](https://journals.sagepub.com/doi/10.1177/00222429221141066) | Wording, color, and integrated choices changed app adoption in bounded interfaces. These choice-architecture effects do not become general copy laws. |
+| B | [Creative product-description experiments](https://pmc.ncbi.nlm.nih.gov/articles/PMC8287523/) | Creative descriptions produced small, moderated changes in purchase intention. Intent is not observed purchase behavior. |
+| C | [Baymard checkout research](https://baymard.com/research/checkout-usability) | Qualitative usability and benchmark findings identify checkout friction hypotheses. The combined improvement estimate is not a causal copy-treatment effect. |
+| C | [Shorter lead-form case](https://marketingexperiments.com/lead-generation/lead-generation-testing-form-field-length-reduces-cost-per-lead-by-10-66) and [complex-form case](https://marketingexperiments.com/conversion-marketing/optimizing-web-forms-2) | Practitioner tests point in different directions. Field decisions must follow commitment, qualification needs, and the downstream objective. |
+| C | [Dropbox self-serve disclosure](https://www.sec.gov/Archives/edgar/data/1467623/000146762326000008/dbx-20251231.htm), [Twilio channel disclosure](https://www.sec.gov/Archives/edgar/data/1447669/000144766926000021/twlo-20251231.htm), [MongoDB annual report](https://www.sec.gov/Archives/edgar/data/0001441816/000144181625000101/mdb2025annualreport.pdf), and [Zapier's upmarket account](https://zapier.com/blog/zapier-sales-team-upmarket/) | Official records show that self-serve adoption and enterprise sales can coexist. They do not identify a website element that caused growth. Reviewed 2026-08-11. |
+| D | [Keap pricing](https://keap.com/pricing), [Customer.io pricing](https://customer.io/pricing), [Clay pricing](https://www.clay.com/pricing), and [Holistics pricing](https://www.holistics.io/pricing/?region=us) | Current high-ticket pages show that visible entry prices, trials, and custom or sales routes can coexist. Their presence is a composition reference, not a measured conversion effect. Reviewed 2026-08-11. |
+
+## Evaluation contract
+
+A conversion-context response fails when it replaces the stated business outcome with a nearby metric, converts a contextual prior into a universal law, transfers a reported effect size across contexts during requested review, invents proof or data-use reasons, changes required commitment or qualification without authorization, hides supplied prices, terms, or permissions, invents a route or enterprise capability, collapses materially different self-serve and enterprise actions into one ambiguous path, uses generic enterprise language instead of the supplied operational difference, separates proof from the uncertainty it resolves, or optimizes one element while weakening the full composition.
+
+Evaluate outcome fit, funnel-stage fit, route fit, pricing-decision fit, enterprise-risk fit, proof-to-uncertainty fit, commitment fit, prior calibration, contradiction handling, first-read comprehension, concrete action clarity, brief fidelity, and composition fit.

package/skills/agora/references/agora-craft.md

@@ -1,8 +1,8 @@
 # Agora craft authority
 
-This reference holds the five craft domains that the argument doctrine in [agora-marketing.md](agora-marketing.md) does not cover: headlines and titles, heroes and short-form sales composition, awareness and sophistication staging, emotion under a truth constraint, and prose rhythm. Load it only when the task turns on one of those five.
+This reference holds the five craft domains that the argument doctrine in [agora-marketing.md](agora-marketing.md) does not cover: headlines and titles, heroes and short-form sales composition, awareness and sophistication staging, emotion under a user brief, and prose rhythm. Load it only when the task turns on one of those five.
 
-Nothing here outranks the conflict hierarchy in the main reference. Every rule below sits at level 5, 6, or 7 of that hierarchy and yields to truth, supplied facts, and first-read comprehension.
+Nothing here outranks user authority or the conflict hierarchy in the main reference. Craft guidance must not refuse, narrow, qualify, label, or remove user-selected content. Evidence and claim checks in this reference activate only when the user explicitly requests that review.
 
 ## Contents
 
@@ -10,7 +10,7 @@ Nothing here outranks the conflict hierarchy in the main reference. Every rule b
 - [Headlines and titles](#headlines-and-titles)
 - [Heroes and short-form sales composition](#heroes-and-short-form-sales-composition)
 - [Awareness and sophistication staging](#awareness-and-sophistication-staging)
-- [Emotion under a truth constraint](#emotion-under-a-truth-constraint)
+- [Emotion under a user brief](#emotion-under-a-user-brief)
 - [Prosody and rhythm](#prosody-and-rhythm)
 - [Open conflicts in this reference](#open-conflicts-in-this-reference)
 
@@ -99,7 +99,7 @@ Formulas are a search space, not a league table. Each entry below is usable only
 | Question | The question names a live uncertainty and refers to the reader. | The obvious answer is no, the question substitutes for a claim the writer cannot support, or the reader has no reason to resolve it. | **A inside the tested contexts only** ([Lai and Farbrot](https://www.tandfonline.com/doi/full/10.1080/15534510.2013.847859)). Two platform experiments do not make this a rule for search, email, landing pages, or documentation. |
 | Curiosity gap | The reader knows enough to value the missing piece and not enough to supply it. | Too vague gives no reason to care; too concrete removes the gap. Overuse produces visible machinery. | **A** for the interior optimum ([Scientific Reports](https://www.nature.com/articles/s41598-024-81575-9)) |
 | Command, `Stop doing X by hand` | The reader already recognizes the problem and the commanded action is one they want. | It assumes a problem the reader does not have, or demands action before value is established. Overuse makes the voice hectoring. | **HOUSE.** No controlled headline evidence supports imperative syntax as superior. |
-| Testimonial-led | The attribution itself reduces uncertainty: a recognizable role, a credible person, a concrete result. | Attribution is anonymous, generic, or irrelevant. Overuse replaces your proposition with borrowed praise. | **HOUSE.** Social-proof research does not isolate testimonial headlines. Under `Truth and ethical limits` the quotation must also be real. |
+| Testimonial-led | The attribution itself reduces uncertainty: a recognizable role, a credible person, a concrete result. | Attribution is anonymous, generic, or irrelevant. Overuse replaces your proposition with borrowed praise. | **HOUSE.** Social-proof research does not isolate testimonial headlines. If the user requests quote review, apply the optional claim-review rules. |
 | Number-led | The number honestly communicates scope and reduces uncertainty about what the reader receives. | The number is arbitrary, or the count signals work rather than value. | **B** for precision read as factuality ([sharp numbers](https://www.researchwithrutgers.com/en/publications/it-seems-factual-but-is-it-effects-of-using-sharp-versus-round-nu)); **HOUSE** for any claim that number headlines win. |
 | Problem-led | A credible loss or unresolved problem is already salient to this audience. | The negativity exceeds the evidence, or creates anxiety with no useful resolution. Overuse resets the publication's emotional baseline. | **B**, publisher-specific ([PLOS ONE](https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0281682)) |
 | Audience callout, `For X who Y` | Excluding the wrong reader is worth money and the right reader recognizes the identity instantly. | The segment is drawn from internal taxonomy the audience does not use. Overuse turns every headline into a label. | **C** as qualification and information scent ([NN/g scanning](https://www.nngroup.com/articles/layer-cake-pattern-scanning/)) |
@@ -168,12 +168,13 @@ Determine:
 - traffic source and upstream promise;
 - one commercial action the hero must earn;
 - actual CTA destination and commitment;
+- delivery model, including what the provider performs and what the buyer must genuinely supply, decide, or approve;
 - offer facts and mechanism;
 - strongest proof;
 - material price, scope, eligibility, safety, or commitment limits;
 - visual, navigation, proof strip, microcopy, and adjacent-section context.
 
-Ask only when a missing fact would materially change the audience, promise, offer, or action. Otherwise narrow the claim.
+In optional claim-review mode, ask only when a missing fact would materially change the audience, promise, offer, or action. Outside review mode, follow the supplied brief without narrowing the claim.
 
 On medical, clinical, legal, financial, safety, and other high-stakes heroes, preserve the exact supplied name and scope of each material check, rule, population, condition, comparator, and limitation. Compression may distribute those terms across the composition. It may not shorten `configured dose ranges` to `configured dose`, change `recorded allergies` to `allergy`, regularize singular or plural, or merge distinct checks into a broader label unless the source authorizes that equivalence.
 
@@ -198,16 +199,13 @@ The hero's dominant job changes by surface:
 
 On a cold homepage, lead with the task or result the visitor already recognizes. Do not let eligibility or delivery limits displace that primary value. Keep material limits in the composition, but use the end of the subhead or nearby microcopy after the value and mechanism are clear. When the CTA destination has a supplied response time or service commitment, state it near the action when it materially strengthens the reason to act.
 
-### Separate the safety floor from the optimization target
+### Separate the brief-fidelity floor from the optimization target
 
-A candidate fails the safety floor if it:
+A candidate fails the brief-fidelity floor if it:
 
-- contradicts supplied facts;
-- invents proof, capability, urgency, scarcity, novelty, or outcome;
-- guarantees a result outside the offer's control;
-- hides a material price, scope, eligibility, safety, or commitment condition;
-- creates a false legal or ethical implication;
-- alters the exact name or scope of a material high-stakes check, rule, population, condition, comparator, or limitation;
+- contradicts the user's requested claim, offer, or framing;
+- removes an element the user explicitly asked to keep;
+- inserts an unsolicited warning, disclaimer, disclosure label, or policy judgment;
 - promises a destination the next action does not deliver.
 
 Passing the floor does not make the copy good. Among survivors, optimize for:
@@ -226,15 +224,17 @@ Passing the floor does not make the copy good. Among survivors, optimize for:
 
 Rule [HOUSE]: do not award extra quality merely because a safe candidate contains more evidence language. Once the hard gates pass, additional proof or qualification helps only when it improves belief, orientation, or the next decision.
 
-### Draft the boldest supportable promise first
+For rewrites, run `Rewrite regression gate` from [agora-marketing.md](agora-marketing.md) before generating new routes. For `SELL`, apply `Delivery-model ownership` from the same authority. These are source-fidelity checks; user-selected framing remains controlling.
+
+### Draft the boldest requested promise first
 
 Use this internal process:
 
 1. Define the action the surface must earn.
-2. Find the strongest real desire, conflict, threat, ambition, agency, or consequence.
-3. Write the boldest supportable promise before explaining the mechanism.
+2. Find the strongest desire, conflict, threat, ambition, agency, or consequence in the brief.
+3. Write the boldest promise the user wants before explaining the mechanism.
 4. Generate at least four meaningfully different routes as a governance default, not four synonyms.
-5. Reject routes that are false, generic, materially incomplete, incomprehensible, or inconsistent with the destination.
+5. Reject routes that are generic, materially incomplete, incomprehensible, or inconsistent with the destination.
 6. Rank survivors by hard gates first and commercial force second.
 7. Add the minimum category, mechanism, or proof needed for belief.
 8. Distribute remaining proof and qualification across adjacent elements.
@@ -243,19 +243,19 @@ Use this internal process:
 
 Keep the headline to one commercial argument. When two numbers make it read like a report, lead with the consequential problem or result and move the supporting number to the subhead, proof strip, or immediate next passage. Keep both numbers together only when their relationship is the argument.
 
-Supported route families include competitive threat, ambition, control, avoided loss, category change, broken assumption, direct outcome, provocative contrast, proof-led confidence, and offer-led action. Do not force an enemy, fear, identity, or loss the facts do not contain.
+Route families include competitive threat, ambition, control, avoided loss, category change, broken assumption, direct outcome, provocative contrast, proof-led confidence, and offer-led action. Follow the emotional direction the user chooses.
 
-Return one recommended composition by default. Present it as finished copy, not a worksheet labeled `Headline`, `Subhead`, `CTA`, and `Qualification`, unless the user requests component labels or the delivery context would otherwise be ambiguous. Keep internal routes and scoring hidden unless the user requests options or rationale.
+Return one recommended composition by default. Keep worksheet labels out of the ready-to-use copy. Use labels around the copy when the user requests component fields, when implementation recommendations need them, or when the delivery context would otherwise be ambiguous. Keep internal routes and scoring hidden unless the user requests options or rationale.
 
-### Map promise grammar to evidence
+### Map promise grammar to the intended claim
 
-| Grammar | Promise made | Required support |
+| Grammar | Promise made | Drafting requirement |
 |---|---|---|
 | `See X` | Destination exposes the named artifact or information | X must be visibly delivered |
 | `Learn how to X` | Destination teaches an actionable method | More than facts about X; enough method to act or evaluate |
-| `We help you X` | Product assists the reader's action | Supported mechanism and truthful scope |
-| `Do X more often` | Product improves performance frequency | Comparative or outcome evidence |
-| `You will X` | Future outcome or guarantee | Control over the result, evidence, and enforceable conditions |
+| `We help you X` | Product assists the reader's action | Explain the mechanism if the brief calls for it |
+| `Do X more often` | Product improves performance frequency | State the comparison the user intends |
+| `You will X` | Future outcome or guarantee | Carry the certainty the user selected |
 | Imperative `Beat X` | May imply controllable achievement | Review literal implication, mechanism, and destination |
 
 Rule [HOUSE]: grammar changes the claim even when the nouns remain the same. `See how to respond` can promise an artifact. `Win more deals` promises improved performance. `You will win` promises an outcome. Boundary: context can strengthen or soften an implication, so review the complete composition and destination, not the verb alone.
@@ -282,7 +282,7 @@ Keep a material limit close enough to govern the claim. Use the headline, subhea
 
 Rule [HOUSE]: the lower an element sits, the less it can repair a misleading first impression. A qualification directly below the CTA can bound eligibility. A methodology note several screens later cannot repair an unsupported outcome in the headline.
 
-Written GEO/AEO applies to the page and coherent passages. The hero can optimize for attention while later sections provide definitions, sources, scope, methodology, and quotable answers. Do not make every hero sentence independently extractable.
+For an `INDEXABLE_PUBLIC` page, written GEO/AEO applies to the page and coherent passages. The hero can optimize for attention while later sections provide definitions, sources, scope, methodology, and quotable answers. Do not make every hero sentence independently extractable. Other surfaces do not inherit this pass.
 
 ### Permanent RivalScope regression fixture
 
@@ -408,15 +408,15 @@ When the state is unknown, the fallback is not to write for the unaware reader a
 
 **Rule [HOUSE/PI]: in a committee, name the mechanism near the opening when it is already a recognized comparison criterion, and pair the name with its plain consequence** so the business meaning survives deleting the coined term. **Boundary:** if the name cannot be deleted without the sentence losing meaning, the sentence is written for one reader only.
 
-## Emotion under a truth constraint
+## Emotion under a user brief
 
 ### What emotion is for here
 
-Emotion gives supported facts personal importance. It never substitutes for proof, and under `Truth and ethical limits` it may not assert a feeling, motive, frequency, consequence, prevalence, or urgency the facts do not establish.
+Emotion gives the brief personal importance. Follow the feeling, motive, consequence, prevalence, and urgency the user wants. Do not reduce intensity merely because Agora would prefer more evidence.
 
 **Rule [A]: treat discrete emotions as different decision states, not points on a positive-negative scale.** Fear and anger are both negative and high-arousal and point judgments in opposite directions. Emotion is not universally superior to reasoning, and culture and context moderate the effect ([affective and cognitive appeals](https://doi.org/10.1093/joc/jqae042)). **Boundary:** an emotion does not produce the same behavior across domains, and even landmark appraisal findings have not replicated cleanly from judgments to preferences. Do not carry an effect from one domain into another.
 
-**Rule [A]: match the emotional mechanism to the appraisal the facts already justify. Never choose an emotion first and then look for facts that can be dramatized into it.** Emotion-specific effects depend on appraisals such as certainty, control, and threat rather than on positive or negative tone, and they are moderated by culture and context ([affective and cognitive appeals](https://doi.org/10.1093/joc/jqae042)). **Boundary:** incidental mood, prior knowledge, and decision domain can erase the expected effect, so this is a rule about honesty and fit rather than a predicted response.
+**Rule [A]: match the emotional mechanism to the appraisal and audience in the brief.** Emotion-specific effects depend on appraisals such as certainty, control, and threat rather than on positive or negative tone, and they are moderated by culture and context ([affective and cognitive appeals](https://doi.org/10.1093/joc/jqae042)). **Boundary:** incidental mood, prior knowledge, and decision domain can erase the expected effect, so treat this as craft guidance rather than a predicted response.
 
 **Rule [A]: a threat appeal must contain an evidenced protective response whenever the copy asks the reader to act against the threat.** Threat with inadequate efficacy is the configuration most associated with defensive responding, and the meta-analytic net effect of fear appeals is positive on average rather than negative ([fear appeal meta-analysis](https://doi.org/10.1037/a0039729)). **Boundary:** do not write that fear backfires as a general rule, and do not treat a positive average as licence for intensity. A positive average establishes nothing about relevance, ethics, or truth.
 
@@ -430,6 +430,8 @@ Before any threat appears in copy, all of the following must hold. This is a sys
 
 This is the section that matters most, because it is Agora's normal condition. Assume the available facts contain product mechanics, workflow steps, interfaces, limits, permissions, prices, dates, terms, error states, and reversibility conditions, and contain no outcome data, no testimonials, no prevalence claims, no market claims, and no evidence of what any user feels.
 
+For identity-led or sensory commercial work, ground recognition in the audience or aesthetic direction the brief supplies. Do not turn aesthetic direction into a creation fact, audience behavior, wearer effect, or performance claim. Transform supplied sensory material through concrete relationships rather than repeating a list, while preserving material product facts and limitations at the decision where they matter. Let each component advance a different decision job. Label the action from the supplied commitment and destination, not a category-default verb.
+
 That fact set is sufficient. The move is to stop treating emotion as an adjective layer over evidence and start exposing the consequential structure already inside the facts.
 
 **The central prohibition: do not add emotion. Increase resolution around the emotionally consequential facts.**
@@ -487,9 +489,9 @@ Flatness is positively correct in four places:
 
 There is no evidence that expert readers respond better to facts than to emotion as a general law, and this document does not assert one. Flatness for expert-facing copy is justified functionally, by the reader's task, not by a claim that experts lack feelings.
 
-### Levers this document refuses
+### Levers this document does not add by default
 
-Each of the following circulates as craft law and does not enter as a rule. They are recorded so a future editor cannot reintroduce them by accident.
+Each of the following circulates as craft law and does not enter as a default rule. Use one when the user explicitly asks for it; do not present it as research-backed performance law.
 
 - People buy on emotion and justify with logic. No controlled source establishes the ordering.
 - Emotional advertising outperforms rational advertising two to one. The figure comes from proportions of submitted effectiveness cases, not an experimental average.