@sellable/mcp 0.1.236 → 0.1.238

package/skills/create-post/references/gold-standard-post-pack.md

@@ -0,0 +1,203 @@
+# Gold Standard Post Pack
+
+The gold-standard pack is user-owned memory with an MCP-owned schema.
+
+MCP owns:
+
+- this schema
+- selection workflow
+- scoring rubric
+- decomposition rules
+- validation rules
+
+The user's computer owns:
+
+- personal best posts
+- approved inspiration posts from the space
+- copied or distilled examples
+- approval notes
+- allowed-use limits
+
+## Storage
+
+Approved gold standards live under:
+
+```text
+~/.sellable/configs/core/references/linkedin-posts/
+  INDEX.md
+  gold-standard-<slug>.md
+```
+
+The pack is capped at 20 approved gold standards. Candidate examples do not
+count toward the cap until the user approves them.
+
+Do not store gold standards under `~/.sellable/content/linkedin/**`. Content
+folders are for ideas, hook research, drafts, published records, and future
+comment history. Gold standards are durable writing memory.
+
+## Import Modes
+
+### Personal Best Import
+
+Use when the user asks to import their best posts, calibrate on their old posts,
+or build the pack from their LinkedIn profile.
+
+1. Ask for the user's LinkedIn profile URL or handle if it is not already known.
+2. Call `mcp__sellable__fetch_linkedin_posts`.
+3. Rank candidate personal posts by engagement quality, topic fit, full-text
+   availability, voice usefulness, and whether the user says the post felt like
+   them.
+4. Present a numbered candidate list.
+5. Ask which posts to add, skip, or mark as anti-examples.
+6. Add only the user-approved selections.
+
+### Space Benchmark Research
+
+Use when the user asks to research what is working in the space or add outside
+gold standards.
+
+1. Derive search terms from the user's topic, ICP, current idea, and proven
+   search memory.
+2. Use the hook research playbook and `mcp__sellable__search_engagement_posts`.
+3. Prefer recent multi-month winners, repeated creator success, strong
+   share/repost signals, and full-text availability.
+4. Penalize lead magnets, giveaway mechanics, engagement bait, celebrity-only
+   reach, and examples that cannot be adapted to the user's voice.
+5. Present candidates with a clear "should we use these as gold standards?"
+   approval gate.
+6. Add only the user-approved selections.
+
+## Candidate Presentation
+
+Show compact candidate cards. Include:
+
+- candidate number
+- type: `personal_best`, `space_benchmark`, or `anti_example`
+- author
+- source URL
+- engagement breakdown when available
+- why it might belong in the pack
+- hook mechanism
+- content/body mechanism
+- rhythm notes
+- sentence-structure notes
+- proof/story use
+- voice fit
+- risks
+- allowed use recommendation
+
+Approval prompt:
+
+```text
+Gold-standard pack: <current_count>/20 approved.
+
+These look like candidates worth saving. Which should I add?
+Reply with numbers to add, "skip all", or "replace <existing> with <new>" if the pack is full.
+```
+
+Do not write candidates to the approved pack before the user chooses.
+
+## Approved Index Schema
+
+`INDEX.md` should use a table with these fields:
+
+- `Status` - `approved` or `anti-example`
+- `Type` - `personal_best` or `space_benchmark`
+- `Title`
+- `Source URL`
+- `Copied Path`
+- `Added`
+- `Score`
+- `Tags`
+- `Primary Use`
+- `Allowed Use`
+- `Hook Pattern`
+- `Body Pattern`
+- `Rhythm Notes`
+- `Sentence Notes`
+- `Risks`
+- `Key`
+
+Use stable keys from normalized source URL/title plus an optional content hash.
+If the same source appears again, update the existing row instead of adding a
+duplicate.
+
+## Approved Example File Schema
+
+Each copied or distilled `gold-standard-<slug>.md` should include:
+
+```text
+# <Title>
+
+Source URL:
+Type:
+Status:
+Added:
+Allowed use:
+Tags:
+
+## Original Or Distilled Text
+
+<Full text only when safe and approved. Otherwise store a short distilled summary.>
+
+## Hook Breakdown
+
+- hook text:
+- char count:
+- first-line chars:
+- first-two-line chars:
+- mobile preview fit:
+- desktop preview fit:
+- hook mechanism:
+- internal question:
+- emotional trigger:
+
+## Content / Body Breakdown
+
+- thesis:
+- body mechanism:
+- story mechanism:
+- proof mechanism:
+- argument moves:
+- close:
+- what made it work:
+
+## Rhythm
+
+- line breaks:
+- paragraph length:
+- sentence length:
+- pacing:
+- punctuation:
+
+## Sentence Structure
+
+- sentence starts:
+- fragments:
+- contrast moves:
+- specificity moves:
+- repeated syntax:
+
+## Usage Notes
+
+- imitate:
+- do not copy:
+- voice fit:
+- risks:
+```
+
+## Selection Rules For Drafting
+
+Before drafting a post, use at most 1-3 relevant gold standards. Prefer:
+
+- the user's own approved posts over outside benchmarks
+- examples with matching topic, mechanism, or story shape
+- examples whose allowed use includes `imitate structure`
+- examples with clear hook/body/rhythm/sentence decomposition
+
+Never copy outside wording. For personal posts, reuse wording only when the user
+explicitly asks to reuse their own line. Otherwise, use the pack for structure,
+taste, and judgment.
+
+If the pack is empty, continue with core memory and hook research. Do not block
+normal drafting just because no gold standards exist.

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

@@ -0,0 +1,126 @@
+# Hook Research Playbook
+
+Hook research must use current Sellable engagement data before drafting unless the user explicitly asks for `unsaved_preview`.
+
+## Search Inputs
+
+Derive 3-8 keyword searches from:
+
+- the raw idea
+- user-supplied topic
+- proven search terms in engage memory
+- tracked people/inspiration references when relevant
+
+## Default Search
+
+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
+- 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
+
+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 this scoring shape:
+
+```text
+hook_score =
+  topic_fit
+  + hook_clarity
+  + creator_repeat_success
+  + repost_share_strength
+  + comment_quality
+  - lead_magnet_penalty
+  - engagement_bait_penalty
+  - off_voice_penalty
+```
+
+Guidance:
+
+- Shares/reposts are the strongest signal because a reader spends their own feed reputation.
+- Comments are stronger than reactions only when they are substantive; giveaway comments are weak.
+- Reactions are weak reach unless paired with shares/reposts or strong comments.
+- If the tool returns `engagement.shares`, treat it as the repost/share proxy.
+- 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.
+
+Penalize lead-magnet and engagement-bait mechanics unless the user explicitly asks for that style:
+
+- `comment "template"` / `comment "guide"` / `comment "playbook"`
+- "DM me"
+- "I'll send it"
+- "free template"
+- "free prompt"
+- "repost for access"
+- "like and comment"
+- broad giveaway framing that makes engagement inflate without proving the hook/body worked
+
+## Full Text Reality
+
+Search results may only include previews.
+
+When full hook/body text matters:
+
+1. use the result's author/profile URL
+2. call `mcp__sellable__fetch_linkedin_posts`
+3. match recent posts by URL or LinkedIn activity ID
+4. record whether the full text was found
+
+If full text is unavailable, record `full_text_unavailable`. Use only the preview for hook analysis and do not infer missing body details.
+
+## Hook Extraction
+
+Extract structure, not wording.
+
+For each shortlisted source post, record:
+
+- URL
+- author
+- engagement totals and available likes/comments/shares breakdown
+- creator repeat evidence
+- visible hook text or preview
+- line count and mobile preview fit
+- hook mechanism
+- story mechanism when the post is a story
+- internal question created
+- emotional trigger
+- proof/story dependency
+- lead magnet or engagement bait penalty
+- weighted signal notes
+- replicability score
+
+## Story Mechanism
+
+For story posts, do not reduce the source to "strong first line" or a generic lesson. Extract the mechanism that made the story travel:
+
+- concrete first-person moment
+- visible tension or tradeoff
+- mistake, regret, reversal, or confession
+- before/after shift
+- founder/operator decision point
+- uncomfortable but specific truth
+- proof embedded in the scene rather than pasted on later
+
+If the source story only works because of celebrity, outrage, giveaway mechanics, or an unavailable body section, mark it as low-replicability or `full_text_unavailable`.
+
+## Blocked States
+
+Local idea capture can still succeed when research fails.
+
+Draft-ready output must block or retry when:
+
+- `unauthenticated`
+- `no_active_workspace`
+- `search_timeout_or_rate_limited`
+- `zero_useful_hook_results`
+- `full_text_unavailable` when the selected hook requires body context
+
+## Save Requirement
+
+Save the research with `mcp__sellable__save_hook_research` before drafting.

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

@@ -0,0 +1,88 @@
+# Post File Contract
+
+The v1 content library is local Markdown under `~/.sellable/content/linkedin/**`.
+
+## Ownership
+
+MCP/package owns:
+
+- tool definitions
+- prompt workflow
+- file schemas
+- validation rules
+- hook research rules
+
+Customer computer owns:
+
+- raw ideas
+- hook research artifacts
+- drafts
+- published post records
+- future comment history
+
+## Layout
+
+```text
+~/.sellable/content/linkedin/
+  ideas/
+    idea_YYYYMMDD_slug.md
+  research/
+    hooks/
+      research_YYYYMMDD_slug.md
+  drafts/
+    draft_YYYYMMDD_slug_v1.md
+  published/
+    YYYY/
+      post_linkedinActivityId.md
+  comments/
+    library/        # reserved only; no v1 comment drafting
+```
+
+## Required Fields
+
+Idea files must preserve:
+
+- `id`
+- `type: idea`
+- `status: captured`
+- `createdAt`
+- `updatedAt`
+- exact raw source between raw-source markers
+- optional distilled brief that does not add new claims
+
+Hook research files must preserve:
+
+- source idea ID
+- keywords searched
+- filters used
+- source post URLs
+- author/profile URLs
+- engagement totals
+- full-text availability
+- extracted hook patterns
+- selected hook basis
+
+Draft files must preserve:
+
+- source idea ID
+- hook research ID
+- draft body
+- validation receipt
+- status: `draft`, `ready`, or `needs_revision`
+
+Published files must preserve:
+
+- source draft ID when available
+- publish URL
+- LinkedIn activity ID when available
+- published date
+- optional future metrics placeholders
+
+## Safety
+
+- Do not write to a repo-local Sellable content directory.
+- Do not append new content to `~/.sellable/configs/content/linkedin-posts-drafts.md`.
+- List operations return metadata and short sanitized previews only.
+- Full raw source requires a single-object get call.
+- Drafts and published posts remain separate files.
+- Comment drafting is out of v1 scope.

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

@@ -0,0 +1,149 @@
+# Post Validation
+
+Every saved draft needs a validation receipt. A draft without this receipt is not ready.
+
+## Required Receipt Fields
+
+- `sourceIdeaId`
+- `hookResearchId`
+- `candidateHooksConsidered`
+- `selectedHook`
+- `selectedHookWhy`
+- `proofClaimsUsed`
+- `proofClaimSources`
+- `storyFilesConsulted`
+- `goldStandardsConsulted`
+- `voiceRulesApplied`
+- `linkedinPreviewAudit`
+- `simplifierConcreteLanguageAudit`
+- `antiAiAudit`
+- `outboundAiTellAudit`
+- `finalizerChanges`
+- `blockedReasons`
+- `retryNeededReasons`
+- `readyStatus`
+
+## Candidate Set
+
+Generate multiple hook candidates before drafting. Do not lock onto the first draft.
+
+Each candidate should include:
+
+- hook text
+- source pattern
+- score
+- char count and first-line / first-two-line preview measurements
+- mobile and desktop preview fit
+- proof/story dependency
+- AI-tell risk
+- why it should win or lose
+
+## Finalizer Pass
+
+After the first draft:
+
+1. remove unsupported claims
+2. tighten the hook
+3. simplify abstract phrasing
+4. replace generic language with concrete words only when supported
+5. preserve the user's actual story and point
+6. remove AI tells
+7. re-check LinkedIn preview fit after edits
+
+## LinkedIn Preview Audit
+
+Audit the selected hook and top candidates against conservative LinkedIn preview budgets:
+
+- mobile first line: 35-45 chars
+- mobile first two lines: 80-100 chars
+- desktop first line: 70-90 chars
+- desktop first two lines: 140-180 chars
+
+Record:
+
+- `charCount`
+- `firstLineChars`
+- `firstTwoLinesChars`
+- `mobilePreviewFit`
+- `desktopPreviewFit`
+- `lineCountEstimate`
+- `truncationRisk`
+- `rewriteIfTruncated`
+
+LinkedIn rendering varies by device and line break, so this is a planning audit. If the hook only works after likely truncation, rewrite it.
+
+## Simplifier / Concrete-Language Audit
+
+Flag and rewrite:
+
+- vague abstraction
+- fake profundity
+- broad claims without proof
+- corporate phrasing
+- lines that sound polished but unsupported
+- needless meta commentary
+
+Do not make language concrete by inventing new facts.
+
+## Anti-AI Audit
+
+Start with the Outbound Base AI-Tell Layer from the message pipeline, adapted for public posts. This is a starter smell detector, not permission to run outbound workflows or force outbound copy style.
+
+Reject or rewrite outbound-derived tells when they appear in a post:
+
+- body-level self-introductions that add no story context
+- source-citation phrasing such as "your bio says", "your profile shows", or "saw on LinkedIn"
+- explicit date or duration precision that feels scraped
+- block quotes of another person's phrasing longer than 4 words
+- parenthetical stack or feature dumps
+- over-precise numerics without a traceable source
+- hardcoded signoffs
+- vague proof brags such as "trusted by leaders" without named or sourced proof
+- formal CTA phrasing
+- reusable openers that could fit any topic
+- em dashes in the draft body unless the user's post rules explicitly allow them
+- resume-recap or scraped-personalization bridges
+- flattened "worth sending" bridges
+
+Also reject or rewrite post-native AI tells:
+
+- "game-changing"
+- "leverage"
+- "synergy"
+- "this is key"
+- "let that sink in"
+- "read that again"
+- "here's the thing"
+- "unpopular opinion" without a specific argument
+- generic lessons without a story
+- tidy three-part frameworks that were not in the source material
+- fabricated numbers or examples
+- contrarian bait without proof
+- lead-magnet bait when the user did not ask for a lead magnet
+
+## Proof And Voice Gates
+
+Every claim must trace to at least one of:
+
+- raw idea
+- current user answer
+- `core/proof-ledger.md`
+- `core/wins-ledger.md`
+- `core/story-bank.md`
+- `core/answer-bank.md`
+- approved reference material
+
+Gold standards can guide structure, rhythm, and judgment. They cannot create new
+claims. If an outside gold standard is used, verify the draft copied no outside
+wording unless the user explicitly approved quotation.
+
+If the necessary proof or story is missing, ask the user or return blocked/retry-needed.
+
+## Ready Status
+
+Use:
+
+- `ready` only when proof, voice, anti-AI, and concrete-language 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

package/skills/interview/SKILL.md

@@ -32,6 +32,25 @@ Load only the references needed for the current run:
   legacy workflow.
   </reference_loading>
 
+<content_bridge>
+This interview owns durable core memory. Keep identity, company truth, proof,
+stories, answer-bank entries, transcript entries, references, anti-AI rules,
+context modes, decision rules, and change-log updates under
+`~/.sellable/configs/core/**` and raw archives under `~/.sellable/interviews/**`.
+
+If the run captures a content-specific LinkedIn post idea, hook/taste
+correction, draft-first post calibration note, or voice-note transcript meant
+as a post idea, offer to bridge that item into the content library with
+`mcp__sellable__capture_post_idea` under
+`~/.sellable/content/linkedin/ideas/**`.
+
+Do not move or mirror core identity/proof/story material into
+`~/.sellable/content/**`. The content bridge is only for post ideas and
+content-specific calibration notes. `story-bank.md`, `proof-ledger.md`,
+`answer-bank.md`, transcripts, references, and raw interview archives remain
+the source of truth for stories and proof.
+</content_bridge>
+
 <modes>
 Choose the lightest mode that can produce useful memory.
 

package/skills/interview/references/reference-curation.md

@@ -66,3 +66,30 @@ Personal LinkedIn posts and inspiration examples deserve especially clear
 notes: explain whether the lesson is voice, hook shape, proof handling,
 argument structure, audience fit, or a pattern to avoid. Do not mix admiration
 with permission to copy; many inspiration examples should be structural only.
+
+## LinkedIn Post Gold Standards
+
+The approved LinkedIn post gold-standard pack lives in
+`~/.sellable/configs/core/references/linkedin-posts/` and is capped at 20
+approved examples. User-owned examples can be personal best posts or
+user-approved space benchmarks researched from high-performing posts in the
+space.
+
+Do not add researched outside posts directly to the approved pack. First show a
+candidate list and ask which examples the user wants to add, skip, mark as
+anti-examples, or use to replace an existing item when the pack is full.
+
+Each approved post reference should split the lesson into:
+
+- hook mechanism
+- content/body mechanism
+- rhythm and pacing
+- sentence structure
+- proof/story use
+- voice fit
+- risks and allowed use
+
+Outside examples are structure/taste references only unless the user explicitly
+approves quotation. Personal posts can be stronger voice references, but still
+record whether to quote, imitate structure, summarize, keep private, or treat as
+an anti-example.

package/skills/load-voice/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: load-voice
-description: Load Sellable voice/company memory before answering questions, writing posts, applications, replies, or other copy in the user's voice.
-visibility: public
+description: Internal utility for loading Sellable voice/company memory before generic writing tasks that are not covered by create-post or create-campaign.
+visibility: internal
 allowed-tools:
   - Read
   - Glob
@@ -18,6 +18,12 @@ answering, rewriting, reviewing, or calibrating copy in the user's voice.
 This is a read-only usage workflow. Do not interview by default, do not write
 memory files, and do not update `~/.sellable/**` unless the user explicitly
 asks to switch into `$sellable:interview`.
+
+This is no longer a normal public command. Use `$sellable:create-post` for
+LinkedIn posts; that workflow loads voice internally. Use
+`$sellable:create-campaign` for campaign/outbound work; that workflow loads its
+own campaign/sender context. This prompt remains available as a direct MCP
+utility for generic writing and review surfaces.
 </role>
 
 <default_use_cases>