@sellable/mcp 0.1.258 → 0.1.259

package/skills/create-post/references/hook-research-playbook.md

@@ -28,11 +28,10 @@ Worker owns:
 - tracked-person post fetches
 - full-text matching by URL/activity ID
 - duplicate removal
-- follower-band and reach-normalized signal scoring
 - lead-magnet, giveaway, engagement-bait, and off-voice filtering
 - market belief mapping across kept and rejected examples
 - premise input extraction: real scenes, observed tensions, reader value, proof gaps
-- rendered hook opening measurement
+- hook opening measurement
 - exact phrase-pattern extraction
 - body-structure extraction
 - rejected-example notes
@@ -55,14 +54,11 @@ Research packet:
 - market belief map: max 8 bullets
 - controversy candidates: max 8
 - premise inputs: max 8
-- hook reverse-engineering autopsies: max 12
 - full adapted hook blocks: max 12
-- angle territories tested: max 12
 - exact phrase patterns: max 20
 - body patterns: max 8
 - source URLs and author profile URLs
-- reach-normalized signal notes
-- rendered preview records
+- preview measurements
 - confidence gaps
 - save recommendations
 ```
@@ -78,13 +74,6 @@ Use `mcp__sellable__search_engagement_posts` with practical constraints:
 
 - explicit `maxAgeDays: 120` by default so research covers the past 30-120 days, not only this week's posts
 - tighten to 30-60 days for trend-sensitive topics; widen only when the topic has low volume
-- when the user gives a follower range, pass it as `targetFollowerMin` and
-  `targetFollowerMax` so the tool can expose reach-normalized signals and
-  prioritize comparable creators
-- if a source hook looks promising but follower count is missing, use
-  `mcp__sellable__fetch_linkedin_profile` on a bounded shortlist before calling
-  the source a keeper; if profile fetch is unavailable or too slow, mark
-  `follower_count_unavailable`
 - high enough engagement to matter
 - narrow enough to match the idea
 - enough result depth to see whether a creator has repeated winners, not just one viral outlier
@@ -93,19 +82,14 @@ Record every keyword, filter, search window, page, and result count.
 
 ## Weighted Signals
 
-Rank source posts with a weighted signal view. Do not sort by total engagement
-alone. Use the numeric score to decide which sources deserve study; do not let
-the number choose the final hook by itself.
+Rank source posts with a weighted signal view. Do not sort by total engagement alone.
 
 Use this scoring shape:
 
 ```text
 hook_score =
   topic_fit
-  + rendered_mobile_preview_strength
   + hook_clarity
-  + content_pattern_replicability
-  + reach_adjusted_evidence
   + creator_repeat_success
   + repost_share_strength
   + comment_quality
@@ -123,135 +107,6 @@ Guidance:
 - If share or repost data is unavailable, record `repost_data_unavailable` instead of inventing it.
 - Prefer creators with repeated high-performing posts in the same lane over one-off viral posts.
 
-## Reach-Normalized Hook Scoring
-
-Raw engagement is not the clearest signal when source creators have wildly
-different audience sizes. A post from a 100k+ follower creator can win on
-distribution even when the hook is ordinary. A post from a creator near the
-user's follower range that overperforms is a clearer signal that LinkedIn and
-readers rewarded the hook/premise.
-
-This calculation is a source-quality filter, not the final creative decision.
-After reach is controlled, the LLM still chooses the hooks to steal based on the
-visible hook, rendered first-screen promise, content pattern, premise fit, and
-whether the idea can carry without the source creator's distribution.
-
-When the user gives a target range, default to that range. For example, if the
-user says "8k to 20k followers," call `mcp__sellable__search_engagement_posts`
-with:
-
-```text
-targetFollowerMin: 8000
-targetFollowerMax: 20000
-```
-
-If the user gives no range, use the user's known follower count from memory or
-ask only when the decision depends on it. If no follower count is available, use
-raw engagement as a fallback and mark `target_follower_band_unknown`.
-
-For every shortlisted source post, record:
-
-- `authorFollowerCount`
-- `targetFollowerBand`
-- `followerBandFit`: `in_target_band`, `below_target_band`,
-  `above_target_band`, or `unknown`
-- `engagementPer1kFollowers`
-- `weightedEngagementPer1kFollowers`
-- `reachAdjustedScore`
-- `creatorBaselineMedianEngagement` when repeated posts from that creator are
-  available
-- `baselineLift`: this post's engagement divided by the creator's recent median
-  engagement in the same lane, or `creator_baseline_unavailable`
-- `confidence`: `high`, `medium`, or `low`
-- `normalizationNotes`
-
-Use this Harvest-compatible calculation when follower counts are available:
-
-```text
-weightedEngagement =
-  likes
-  + (comments * 4)
-  + (shares * 12)
-
-engagementPer1kFollowers =
-  totalEngagement / authorFollowerCount * 1000
-
-weightedEngagementPer1kFollowers =
-  weightedEngagement / authorFollowerCount * 1000
-
-reachPenaltyMultiplier =
-  1.00 when in target follower band
-  0.75 when below target band
-  0.65 when above target band but <= 2x target max
-  0.35 when above target band but <= 5x target max
-  0.15 when above target band and > 5x target max
-  0.40 when follower count is unknown
-
-reachAdjustedScore =
-  weightedEngagementPer1kFollowers * reachPenaltyMultiplier
-```
-
-When repeated posts from the same creator are available, calculate:
-
-```text
-creatorBaselineMedianEngagement =
-  median weightedEngagement across recent same-lane posts
-
-baselineLift =
-  post weightedEngagement / creatorBaselineMedianEngagement
-```
-
-Use this scoring shape when deciding which hooks to study:
-
-```text
-hook_score =
-  topic_fit
-  + rendered_mobile_preview_strength
-  + hook_clarity
-  + same_follower_band_bonus
-  + weighted_engagement_per_1k_followers
-  + creator_baseline_lift
-  + repost_share_strength
-  + substantive_comment_quality
-  + creator_repeat_success
-  - celebrity_reach_penalty
-  - tiny_sample_penalty
-  - lead_magnet_penalty
-  - engagement_bait_penalty
-  - off_voice_penalty
-```
-
-Rules:
-
-- Prefer in-band creators when the hook is strong and the engagement is real.
-- Use near-band creators as secondary evidence.
-- Penalize creators far above the target range, especially accounts above 5x
-  the target max or above 100k followers when the target range is 8k-20k.
-- Do not automatically reject large-account posts; they can still teach body
-  structure, topic heat, or category language. Do not treat them as primary hook
-  proof unless they also overperform their creator baseline.
-- Large-account hooks can be selected only when the hook carries without the
-  creator: the rendered mobile opening is strong, the premise is reusable by the
-  user, the body pattern does not depend on celebrity authority, and the source
-  either beats baseline or has unusually high reach-adjusted quality after the
-  penalty.
-- Do not overvalue tiny-account anomalies. Very high engagement per follower
-  with low absolute engagement is interesting but lower confidence.
-- When follower data is unavailable, do not invent it. Mark
-  `follower_count_unavailable`, lower confidence, and rely more on creator repeat
-  evidence, repost/share strength, comment quality, and rendered preview quality.
-- A source hook is strongest when it is in/near the target follower band, has
-  real absolute engagement, beats the creator's apparent baseline, has
-  share/comment quality, and passes rendered mobile preview.
-
-Final hook selection must explain both:
-
-- `whyTheHookCarries`: the visible words, specificity, tension, and first-screen
-  promise that work independent of reach
-- `whyTheReachEvidenceIsTrustworthy`: follower-band fit, reach-adjusted score,
-  baseline lift, share/comment quality, or why a large-account example is only
-  secondary pattern evidence
-
 Penalize lead-magnet and engagement-bait mechanics unless the user explicitly asks for that style:
 
 - `comment "template"` / `comment "guide"` / `comment "playbook"`
@@ -263,104 +118,6 @@ Penalize lead-magnet and engagement-bait mechanics unless the user explicitly as
 - "like and comment"
 - broad giveaway framing that makes engagement inflate without proving the hook/body worked
 
-## Hook Reverse Engineering Autopsy
-
-For any space or LinkedIn topic, do not stop at "this is a good hook." Reverse
-engineer why the opening earned attention, which shape can be reused, and which
-parts belong to the source and must not be copied.
-
-For each keeper source hook, record a `hookAutopsy`:
-
-```text
-hookAutopsy:
-  sourceHook: <exact visible opening used for analysis>
-  renderedFirstScreen: <mobile and desktop visible blocks>
-  sourceMechanism: <what the hook does structurally>
-  openLoopType: none | hidden_payoff | contradiction | proof_gap | workflow_reveal | asset_reveal | story_gap
-  clickQuestion: <the question a reader has before clicking see more>
-  promisedPayoff: <what the body/video must deliver after the click>
-  curiosityGap: <what is withheld and why that is fair>
-  specificityAnchor: <tool, person, number, object, scene, or enemy named>
-  tensionOpened: <belief, resentment, fear, status, cost, or contradiction>
-  proofImplied: <what proof the source suggests in the first screen>
-  whyItWorks: <specific words and structure, not a vibe label>
-  whyItMightBeInflated: <reach, giveaway, celebrity, outrage, or topic heat>
-  sourceShapeToKeep: <portable structure, written as a template>
-  sourceWordsNotToCopy: <phrases, jokes, proof, or context owned by source>
-  adaptationRule: <how to make it true for the user's idea and voice>
-```
-
-Good `sourceShapeToKeep` examples:
-
-- "The best [desired asset] I have right now is not in [default tool]."
-- "I gave [system/person] one prompt: [specific request]."
-- "[Common vanity metric] is useless until it becomes [business outcome]."
-- "I built [familiar workflow] inside [new interface]."
-- "Most teams [surface behavior]. Then they miss [hidden opportunity]."
-
-Bad autopsies:
-
-- "contrarian hook"
-- "strong curiosity"
-- "good storytelling"
-- "viral format"
-
-Those labels are allowed only after the concrete shape, click question, and
-payoff obligation are recorded.
-
-## Angle Exploration Before Drafting
-
-After selecting a premise, create a hook angle matrix before drafting the post.
-This is mandatory when the user asks to nail the hook, study hooks, explore a
-space, or write from a specific idea.
-
-Default matrix:
-
-- at least 8 angle territories for normal drafting
-- at least 12 angle territories when the user asks for "a ton of angles" or
-  says the hook is the main constraint
-- at least 24 generated hooks across those territories for normal drafting
-- at least 40 generated hooks when the user explicitly asks to optimize hooks
-
-Angle territories should be materially different, not synonyms. Use territories
-such as:
-
-- enemy/tool contrast
-- hidden asset
-- first-person build proof
-- workflow reveal
-- contrarian category claim
-- mistake/confession
-- market timing
-- customer/operator pain
-- asset/free reveal without comment bait
-- specific person/company signal
-- before/after transformation
-- question hook
-
-For each territory, record:
-
-```text
-angleTerritory:
-  name:
-  sourceShapesUsed:
-  premiseTensionOpened:
-  readerValueImplied:
-  bestHook:
-  mobileRenderedPreview:
-  desktopRenderedPreview:
-  clickQuestion:
-  payoffAfterFold:
-  whyThisAngleShouldWin:
-  whyThisAngleShouldLose:
-  proofNeeded:
-```
-
-Do not write the post body until the winning hook territory is chosen. The post
-body must then pay off the selected hook quickly. If the best hook says the list
-is not in Apollo, the next lines must reveal where it is. If the hook says "I
-gave Sellable one prompt," the next lines must show the prompt or the demo.
-
 ## Market Belief Map
 
 Before selecting a hook or writing a draft, synthesize a market belief map from
@@ -441,54 +198,24 @@ Measure the visible opening for every shortlisted source post before extracting
 the hook pattern. This makes the study useful for LinkedIn, not just generally
 "good writing."
 
-Use `references/linkedin-preview-rendering.md`. LinkedIn does not publish exact
-"see more" cutoff rules. Character counts are diagnostics only. A source post
-or generated hook is not properly studied until it has a rendered mobile and
-desktop preview record.
-
-Default deterministic renderer for unpublished drafts and research comparison:
+LinkedIn does not publish exact "see more" cutoff rules. Treat these as
+conservative v1 planning budgets:
 
-```text
-cssContractVersion: linkedin-preview-rendering/v1
-font size: 14px
-line height: 21px
-white space: pre-wrap
-overflow wrap: break-word
-mobile text width: 308px
-desktop text width: 582px
-review clamp: first 3 rendered text lines
-```
+- `pass`: opening hook is <= 110 chars including newlines, every nonblank line
+  is <= 45 chars, and the hook's core point lands before likely truncation.
+- `warn`: opening 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`: opening hook is > 140 chars including newlines, any nonblank line is
+  > 55 chars, or the hook's core point depends on text after likely truncation.
 
-Authenticated LinkedIn feed/composer screenshots are stronger evidence when
-available. If a screenshot is used, still record the wrapped lines and verdicts
-below so another agent can compare hooks without re-opening LinkedIn.
-
-Desktop preview has more room, but never let desktop fit compensate for a
-mobile `fail`.
+Desktop preview has more room, so record it separately, but never let desktop
+fit compensate for a mobile `fail`.
 
 For each source, record:
 
 - `sourceTextBasis`: `full_text`, `search_preview`, or `manual_user_source`
 - `openingTextUsed`
-- `renderedPreview`
-- `cssContractVersion`
-- `mobileRenderedPreviewBlock`
-- `desktopRenderedPreviewBlock`
-- `mobileRenderedLines`
-- `desktopRenderedLines`
-- `mobileRenderedLineCount`
-- `desktopRenderedLineCount`
-- `corePainProofOrCuriosityVisibleMobile`
-- `corePainProofOrCuriosityVisibleDesktop`
-- `corePointVisibleMobile`
-- `corePointVisibleDesktop`
-- `intentionalOpenLoop`
-- `specificClickQuestionVisible`
-- `payoffPlannedImmediatelyAfterClamp`
-- `seeMoreClickReason`
-- `clickQuestion`
-- `payoffAfterFold`
-- `pointAfterMobileClamp`
 - `charCountIncludingNewlines`
 - `physicalLineCount`
 - `contentLineCount`
@@ -501,28 +228,11 @@ For each source, record:
 - `desktopPreviewBudget`: `pass`, `warn`, or `fail`
 - `blankLineVisualRisk`
 - `corePointBeforeLikelyTruncation`
-- `openLoopType`
-- `renderedPreviewVerdict`: `pass`, `warn`, or `fail`
 
 If only a search preview is available, do not pretend the opening is complete.
 Record `sourceTextBasis: search_preview` and lower confidence when the hook
 appears cut off or body context is unavailable.
 
-Pass/warn/fail is based on rendered output:
-
-- `pass`: the mobile rendered preview shows the pain, proof, or curiosity by
-  the end of the first 3 rendered lines, and either the core point is
-  understandable without opening "see more" or an intentional open loop creates
-  a specific click question with an immediate planned payoff.
-- `warn`: the mobile rendered preview creates useful curiosity but the core
-  point or click question is slightly softened by wrapping, blank-line rhythm,
-  or one missing context word. A compact fallback is required.
-- `fail`: the hook's real point appears after the first 3 mobile rendered
-  lines without an intentional open-loop plan, the visible open loop is vague,
-  the first rendered line is generic setup, blank lines consume the preview
-  before the reader sees the point, or desktop fit is the only reason it looks
-  good.
-
 ## Hook Extraction
 
 Extract structure and reusable language patterns, not copied prose. The goal is
@@ -535,13 +245,10 @@ For each shortlisted source post, record:
 - URL
 - author
 - author profile URL when available
-- author follower count and follower-band fit when available
 - engagement totals and available likes/comments/shares breakdown
-- reach-normalized metrics: engagement per 1k followers, weighted engagement
-  per 1k followers, reach-adjusted score, baseline lift, and confidence
 - creator repeat evidence
 - visible hook text or preview
-- rendered preview fields from the section above
+- opening preview measurement fields from the section above
 - hook mechanism
 - exact hook language patterns: reusable words, phrase shapes, contrast forms,
   sentence shapes, and transition moves
@@ -551,16 +258,10 @@ For each shortlisted source post, record:
 - proof/story dependency
 - lead magnet or engagement bait penalty
 - weighted signal notes
-- reach-normalized signal notes
 - replicability score
 - track person recommendation: `yes`, `no`, or `ask_user`
 - tracking reason when recommended
 
-Do not call a source hook a keeper because the full text is strong if the
-rendered mobile opening is weak. Study what a LinkedIn reader sees before
-"see more"; the body structure can still be useful, but the hook should not be
-copied into the hook pattern set.
-
 ## Specific Language Extraction
 
 For each keeper, extract the source's specific language mechanics in this

package/skills/create-post/references/post-file-contract.md

@@ -59,25 +59,10 @@ Hook research files must preserve:
 - source post URLs
 - author/profile URLs
 - engagement totals
-- author follower counts when available, target follower band, follower-band
-  fit, engagement per 1k followers, weighted engagement per 1k followers,
-  reach penalty multiplier, reach-adjusted score, baseline lift when available,
-  why the hook carries independent of creator reach, and normalization
-  confidence notes
 - full-text availability
 - source hook preview measurements, including text basis, char count including
   newlines, physical/content line counts, longest nonblank line, blank-line
   visual risk, and mobile/desktop preview budget status
-- rendered preview records for every kept source hook and adapted hook block,
-  including literal mobile/desktop preview blocks, rendered line wraps, render
-  basis, CSS contract version, text widths, first-screen promise visibility,
-  core point visibility, and whether the point lands after the mobile clamp
-- hook reverse-engineering autopsies for kept source hooks, including source
-  mechanism, open-loop type, click question, promised payoff, specificity
-  anchor, source shape to keep, source words not to copy, and adaptation rule
-- hook angle matrix summary, including angle territories tested, top generated
-  hooks, winning territory, runner-up territories, and why the winning angle
-  beat the alternatives
 - extracted hook patterns
 - selected hook basis
 
@@ -98,12 +83,6 @@ Draft files must preserve:
 - draft body
 - validation receipt, including LinkedIn preview pass/warn/fail status and
   compact fallback when the selected hook carries a warning
-- selected hook reverse-engineering audit, hook angle matrix summary, and
-  see-more click audit when the selected hook intentionally hides the payoff
-  after the mobile fold
-- rendered mobile and desktop preview blocks for the selected hook; drafts
-  cannot be ready when this rendered-preview audit is missing or fails mobile
-  visibility
 - status: `draft`, `ready`, `needs_revision`, `published`, or `archived`
 
 Multiple drafts for the same idea are expected. Keep the `ideaId` stable and