@sellable/mcp 0.1.269 → 0.1.272

package/skills/create-post/references/post-validation.md

@@ -6,18 +6,37 @@ Every saved draft needs a validation receipt. A draft without this receipt is no
 
 - `sourceIdeaId`
 - `hookResearchId`
+- `transcriptWorldviewPacket`
 - `iteration`
 - `selectedPremiseCard`
 - `candidateHooksConsidered`
 - `selectedHook`
 - `selectedHookWhy`
+- `sourceMessageOutline`
+- `preDraftNarrativeOutline`
+- `preDraftStructureBrief` as a legacy compatibility alias when older drafts or
+  downstream readers still expect it
+- `selectedSourceTemplate`
+- `postPositioningBreakdown`
+- `viralPostOutline`
+- `hookToBodyPromiseMap`
+- `bodyExpressionCandidates`
+- `combinedBodyPlan`
+- `visibleFlowTrace` when the user asked for whole-flow, debug, or
+  step-by-step mode
 - `proofClaimsUsed`
 - `proofClaimSources`
+- `worldviewSource`
+- `hotTakeSource`
 - `storyFilesConsulted`
 - `goldStandardsConsulted`
 - `voiceRulesApplied`
-- `marketBeliefAudit`
+- `audienceTensionAudit`
+- `thoughtLeaderInspirationLab`
 - `premiseValueAudit`
+- `mobileScanabilityAudit`
+- `templateAdaptationAudit`
+- `abstractionToConcreteRewriteAudit`
 - `linkedinPreviewAudit`
 - `simplifierConcreteLanguageAudit`
 - `antiAiAudit`
@@ -74,9 +93,13 @@ Each candidate should include:
 
 - hook text
 - selected premise
+- selected source template or no-template rationale
 - premise tension opened
 - reader value implied
 - source pattern
+- hook-to-body promise
+- see-more tension
+- curiosity debt
 - score
 - char count including newlines and first-line / first-two-line preview measurements
 - physical line count, content line count, longest nonblank line, and blank-line risk
@@ -91,14 +114,50 @@ Each candidate should include:
 After the first draft:
 
 1. remove unsupported claims
-2. verify the draft is anchored to the selected market belief and controversy
+2. verify the draft is anchored to the selected audience tension and credible angle
 3. verify the real story/scene, tension, and reader value are visible early
-4. tighten the hook
-5. simplify abstract phrasing
-6. replace generic language with concrete words only when supported
-7. preserve the user's actual story and point
-8. remove AI tells
-9. re-check LinkedIn preview fit after edits
+4. verify the body repays the selected hook's curiosity debt
+5. verify the final post follows the selected positioning sequence or explains
+   why it departed from the template
+6. tighten the hook
+7. simplify abstract phrasing
+8. replace generic language with concrete words only when supported
+9. preserve the user's actual story and point
+10. remove AI tells
+11. re-check LinkedIn preview fit after edits
+
+## Visible Flow Trace Audit
+
+When the user asks to see the whole flow, run the process step by step, validate
+that it is working, or debug a bad output, the validation receipt must preserve a
+`visibleFlowTrace`.
+
+Record:
+
+- `mode`: visible_whole_flow_debug
+- `checkpointStatuses`: each checkpoint marked `pass`, `weak`, `fail`, or
+  `blocked`
+- `checkpointOutputs`: the concrete output shown to the user for each
+  checkpoint
+- `qualityBreak`: the first checkpoint that made the draft weak, if any
+- `downstreamEffect`: how that break affected the hook, premise, body, or ready
+  status
+- `userVisibleBeforeSave`: yes | no
+- `draftSavedDespiteWeakness`: yes | no
+- `reasonDraftSaved`: why a `needs_revision` draft was still worth saving, if
+  it was saved
+
+Save as `needs_revision` when:
+
+- the trace was not shown before draft prose in visible debug mode
+- the body-expression lab was summarized after the fact instead of generating
+  real candidates before prose
+- a weak premise, missing proof, or wrong source template produced a bad body
+- the final response claims the workflow worked only because artifacts were
+  saved
+
+Do not mark a run successful unless the visible trace, final draft, and saved
+receipt all agree on the same quality state.
 
 ## Premise Value Audit
 
@@ -116,55 +175,262 @@ Record:
 - `readerValue`: what the reader learns, sees differently, or can do
 - `proofAvailable`: source-backed proof used
 - `proofMissing`: claims intentionally avoided or requiring user input
+- `transcriptWorldviewPacket`: clusters, transcript references, cards, repeated
+  phrasing, worldview ingredients, hot-take ingredients, proof/story available,
+  proof/story missing, private exclusions, and confidence
+- `worldviewSource`: the source-backed belief that makes the post feel earned
+- `hotTakeSource`: the source-backed disagreement or operating lesson behind
+  the hook/premise
+- `sourceMessageOutline`: source post decomposition in original order, with
+  paragraph/line/phrase branches, high-level goal of each branch, reader effect,
+  reusable move, and adaptation guard
+- `preDraftNarrativeOutline`: hierarchical `I.`, `A.`, `i.` outline showing
+  hook debt, thesis, operating model, working body patterns adapted, narrative
+  beats, scan path, proof claims, and abstractions to remove
+- `preDraftStructureBrief`: legacy compatibility alias only; the canonical
+  artifact is `preDraftNarrativeOutline`
 - `premiseQualityGates`: pass/fail for `specific_scene_or_pattern`,
   `clear_reader`, `visible_tension`, `reader_value`, `credible_speaker`,
-  `proof_safety`, and `market_heat`
+  `proof_safety`, `audience_tension`, and `pre_draft_narrative_outline`
 - `bodyOutline`: how the body delivers the premise before prose
+- `viralPostOutline`: the selected narrative structure, including beat jobs
+- `hookToBodyPromiseMap`: how the body repays the hook's open loop
+- `combinedBodyPlan`: which body-expression lines were kept, rewritten, or cut
 
 If the draft has no specific scene or observed pattern, no visible tension, or
 no reader value beyond "this is interesting," save as `needs_revision`. Do not
 mark it `ready` because the hook passes preview limits.
 
-## Market Belief Audit
+Save as `needs_revision` when the post claims a worldview or hot take but the
+receipt cannot trace it to raw source, transcript/content-memory, core memory,
+or a current user answer.
+
+## Pre-Draft Narrative Outline Audit
+
+Before a draft can be `ready`, validate that the narrative outline was locked
+before the body was written.
+
+Record:
+
+- `hook`: selected hook plus mobile/desktop rendered preview verdict
+- `thesis`: one sentence the post defends
+- `readerBeingTaught`: specific reader and why the post is written for them
+- `coreEquationOrMechanism`: the operating idea being taught
+- `keyDefinitions`: concrete definitions and examples for terms the reader
+  could misunderstand
+- `proofClaims`: claims, sources, and public-safety status
+- `sourceTemplateOrNoTemplateRationale`
+- `workingBodyPatternsAdapted`: body pattern name, beat order, why it worked,
+  what gets borrowed, and what must not be copied
+- `hierarchicalNarrativeBeats`: `I.`, `A.`, `i.` outline of the final post's
+  argument, examples, proof, and line/section shapes
+- `mobileScanPath`: what a skimmer understands from the hook, separators,
+  section labels, numbers, and close
+- `sectionOutline`: legacy summary of section order plus the job of each
+  section; do not substitute this for `hierarchicalNarrativeBeats`
+- `bodyPromiseAfterSeeMore`: what the body immediately repays
+- `abstractionsToRemove`: abstract phrases and their concrete replacements
+- `userCorrectionsApplied`: user corrections applied to the outline before
+  prose
+
+Save as `needs_revision` when the draft was written before the narrative
+outline, when the outline is a flat checklist instead of hierarchical
+`I.`, `A.`, `i.` notation, when the outline does not match the final prose, when
+working body patterns are unnamed or vaguely borrowed, when the mobile scan path
+is unclear, or when key terms are left abstract.
+
+## Mobile Scanability Audit
+
+A LinkedIn post must still teach the main idea when a reader scans it.
+
+Record:
+
+- `scanVisibleFrom`: hook, separators, numbered labels, ranges/numbers, example
+  prompts, and close
+- `readerGetsWithoutReadingEveryWord`: the specific takeaway a skimmer gets
+- `sectionSeparators`: present | absent | not_needed
+- `sectionLabels`: concrete | abstract | missing
+- `numbersOrProofVisible`: yes | no
+- `mobileLineLengthRisk`: pass | warn | fail
+- `skimVerdict`: pass | needs_revision
+
+Save as `needs_revision` when a skimmer cannot understand the thesis, hierarchy,
+or practical next action.
+
+## Abstraction-To-Concrete Rewrite Audit
+
+Record every meaningful abstraction found in the draft and the concrete
+replacement. Do not merely say "made concrete."
+
+Use this format:
+
+```text
+abstractionToConcreteRewriteAudit:
+1.
+  original:
+  issue:
+  replacement:
+  source:
+  kept_or_cut:
+```
+
+Common abstractions to flag:
+
+- vague nouns such as `signal`, `market`, `attention`, `system`, `quality`,
+  `context`, `machine`, or `workflow` when the sentence does not name the actual
+  source, action, number, or object
+- broad persona labels used as lead sources
+- "warm" without explaining what made the source warm
+- "offer" without explaining why the recipient would believe or want it
+- "learning" without naming what metric changes the next decision
+
+Do not make language concrete by inventing facts. If the concrete replacement
+requires missing proof, ask the user or save as `needs_revision`.
+
+## Template Adaptation Audit
+
+Before a draft can be `ready`, validate that source posts were converted into
+templates rather than copied.
+
+Record:
+
+- `selectedSourceTemplate`: source, template name, and why it fits
+- `positioningSequenceBorrowed`: category sequence being adapted
+- `viralPostOutlineBorrowed`: beat sequence being adapted
+- `lineShapesBorrowed`: reusable line shapes, not copied wording
+- `userStoryInputsUsed`: source-backed user facts filling the template
+- `userProofInputsUsed`: source-backed user proof filling the template
+- `forbiddenBorrowingAvoided`: source proof, jokes, personal context, status,
+  phrases, or examples not used
+- `hookToBodyRepayment`: whether the body answers the hook's curiosity debt
+- `bodyExpressionCandidatesReviewed`: which variants were tested and what won
+- `copyingRisk`: pass | needs_revision | blocked
+
+Save as `needs_revision` when the draft copies outside wording, borrows outside
+proof, keeps a source template's status without equivalent user authority, or
+uses a hook whose promised body payoff is not delivered.
+
+## Audience Tension Audit
 
 Before a draft can be `ready`, validate that it is not merely an internally
-coherent idea. It must be anchored to the saved research's market belief map.
+coherent idea. It must be anchored to the saved research's audience tension
+snapshot.
 
 Record:
 
 - `resonatingIdea`: the current-space idea this draft enters
-- `implicitBelief`: the belief the audience likely already holds
+- `visibleAudienceTension`: the contradiction, tradeoff, cost, or unfinished
+  question readers are reacting to
 - `audienceWant`: what the audience wants permission, leverage, proof, or a new
   category for
-- `audienceResentmentOrFear`: what frustration or risk gives the post tension
-- `selectedControversy`: the claim the post is testing
+- `audienceObjectionOrFear`: what skepticism, frustration, or risk gives the post tension
+- `selectedAngle`: the claim the post is testing
 - `credibleWhyUs`: why the user can credibly say this from raw idea, memory,
   story, proof, or product mechanism
 - `engagementReason`: why someone would react, comment, repost, or argue
 - `unsupportedHypeRemoved`: unsupported claims removed during finalizer
 
-If `selectedControversy` is missing, if the audience belief is only a generic
-label like "founders want growth," or if `credibleWhyUs` depends on borrowed
-proof from another creator, save as `needs_revision`.
+If `selectedAngle` is missing, if the audience tension is only a generic label
+like "founders want growth," or if `credibleWhyUs` depends on borrowed proof
+from another creator, save as `needs_revision`.
+
+## Thought Leader Voice Variant Audit
+
+For draft-producing create-post flows, validate the configured thought-leader
+voice variant lab by default. If it was skipped, record the explicit opt-out
+reason. When thought leaders or creators were used, validate that background
+workers produced complete role-play variants before final prose was synthesized.
+
+This audit is a ready-status gate. It is not enough to mention that creators
+were reviewed. The receipt must prove that the configured influencer workflow
+ran before prose was drafted.
+
+Record:
+
+- `activeInfluencerSource`: `discovery/influencers.md` | named subset | user
+  opt-out
+- `expectedActiveInfluencerCount`
+- `actualVoiceVariantCount`
+- `missingVoiceVariants`
+- `weakVoiceVariants`
+- `workerExecutionMode`: `background_agents` | `sequential_fallback`
+- `backgroundWorkerIds`: worker IDs or labels when available
+- `thoughtLeaderList`: names and profile URLs or handles
+- `voiceModels`: inferred target length, rhythm, vocabulary, formatting, proof
+  style, and close style per person
+- `mechanicsReceipts`: target word-count band, actual word count, line rhythm,
+  vocabulary markers, formatting markers, close style, and
+  `mechanics_match: pass | weak | fail` per person
+- `voiceVariants`: one representative-length role-played post per person, or
+  `not_available` with reason
+- `normalizationConfidence`: high | medium | low
+- `selectedSynthesisIngredients`: hooks, body moves, proof order, rhythm, close
+- `finalVoice`: usually `Christian/Sellable`
+- `forbiddenBorrowingAvoided`: exact outside wording, proof, jokes, personal
+  stories, status, and fake user facts avoided
+- `voiceVariantsGeneratedBeforeFinalProse`: yes | no
+- `selectedSynthesis`: what won and why
+- `styleSimulationRisk`: pass | needs_revision | blocked
+
+Save as `needs_revision` when a final draft copies exact outside wording,
+borrows another creator's proof/status as if it were the user's, invents user
+facts, or lets a creator with a giant audience win without any
+confidence-adjusted reason.
+
+Save as `needs_revision` when `actualVoiceVariantCount` is lower than
+`expectedActiveInfluencerCount`, when the active configured list was not loaded,
+when variants are replaced by a generic influencer summary, or when voice
+variants were generated after final prose instead of before final prose. Return
+`retry-needed` when a tool/package/search failure prevents fetching configured
+profiles or posts.
+
+Save as `needs_revision` when the variants do not demonstrate person-specific
+writing mechanics, when `mechanicsReceipts` are missing, or when multiple
+variants are effectively the same long LinkedIn essay with different creator
+labels.
+
+Only mark `thought_leader_adaptation: not_used` when the user explicitly opted
+out before drafting.
+
+Save as `needs_revision` when the host supports background agents but the
+configured influencers were processed sequentially without a recorded fallback
+reason. The default expected value is `workerExecutionMode:
+background_agents`.
 
 ## LinkedIn Preview Audit
 
-Audit the selected hook and top candidates against conservative LinkedIn
-preview budgets. LinkedIn does not publish exact "see more" cutoff rules, and
-rendering varies by device, app version, font, media, and line break. This audit
-is a mobile-first safety gate, not a claim about an official LinkedIn limit.
+Audit the selected hook and top candidates against the rendered-preview
+contract. LinkedIn does not publish exact "see more" cutoff rules, and rendering
+varies by device, app version, font, media, line break, and whether the post has
+media attached. This audit is a mobile-first safety gate, not a claim about an
+official LinkedIn limit.
+
+Treat character counts as diagnostics only. The gate is the literal rendered
+mobile and desktop visible block from `references/linkedin-preview-rendering.md`
+or an authenticated LinkedIn screenshot.
 
 Use:
 
-- `pass`: hook is <= 110 chars including newlines, every nonblank line is <= 45 chars, and the hook's core point lands before likely truncation.
-- `warn`: hook is 111-140 chars including newlines, any nonblank line is 46-55 chars, or blank lines create visual-line risk. Blank lines are allowed, but they count as physical lines.
-- `fail`: hook is > 140 chars including newlines, any nonblank line is > 55 chars, or the hook's point depends on text after likely truncation.
+- `pass`: the rendered mobile preview shows the pain, proof, or curiosity by the
+  end of the first 3 rendered lines, and either the core point is visible or a
+  specific intentional open loop is visible with immediate body payoff planned
+- `warn`: the rendered mobile preview creates useful curiosity but wrapping,
+  blank-line rhythm, media risk, or one missing context word weakens it; include
+  a compact fallback
+- `fail`: the hook's real point appears after the rendered mobile review clamp,
+  the visible open loop is vague, blank lines consume the preview before the
+  point, or desktop fit is the only reason it looks good
 
 Desktop preview usually has more room. Still record desktop fit, but never let
 desktop fit compensate for a mobile `fail`.
 
 Record:
 
+- `renderedPreview`
+- `renderedPreviewBasis`: `linkedin_css_contract` |
+  `authenticated_linkedin_screenshot` | `manual_user_source`
+- literal mobile visible block
+- literal desktop visible block
 - `charCount`
 - `charCountIncludingNewlines`
 - `firstLineChars`
@@ -184,9 +450,11 @@ Record:
 - `compactFallback` when `previewBudgetStatus` is `warn`
 
 If the hook only works after likely truncation, rewrite it. A draft cannot be
-`ready` with `previewBudgetStatus: fail`. A draft may be `ready` with
+`ready` with `previewBudgetStatus: fail`, with no rendered preview block, or
+with only a character-count claim. A draft may be `ready` with
 `previewBudgetStatus: warn` only when the warning is explicit, usually because
-the user prefers blank-line rhythm, and the receipt includes a compact fallback.
+the user prefers blank-line rhythm, separators, or a deliberate open loop, and
+the receipt includes a compact fallback.
 
 ## Simplifier / Concrete-Language Audit
 
@@ -259,7 +527,9 @@ If the necessary proof or story is missing, ask the user or return blocked/retry
 
 Use:
 
-- `ready` only when proof, voice, anti-AI, and concrete-language gates pass
+- `ready` only when proof, voice, anti-AI, concrete-language, pre-draft
+  structure, mobile-scanability, hook-to-body repayment, and
+  template-adaptation gates pass
 - `needs_revision` when a draft exists but a gate failed
 - `blocked` when required context is missing
 - `retry-needed` when a tool/package/search failure blocked the pipeline