@sellable/mcp 0.1.203 → 0.1.205

package/skills/generate-messages/SKILL.md

@@ -133,35 +133,72 @@ hard failure and revise the output before returning it.
 
 Dry mode validates message quality before campaign mint.
 
-Read:
-
-- `.sellable/configs/core/about-me.md`
-- `.sellable/configs/core/my-company.md`
-- `.sellable/configs/core/context-modes.md`
-- `.sellable/configs/core/proof-ledger.md`
-- `.sellable/configs/core/wins-ledger.md`
-- `.sellable/configs/core/anti-ai-writing-style.md`
-- `.sellable/configs/writing/outbound.md` and legacy `styleguide-core.md` as fallback/source material when present
+Read these campaign inputs:
+
+- `~/.sellable/configs/core/about-me.md`
+- `~/.sellable/configs/core/my-company.md`
+- `~/.sellable/configs/core/context-modes.md`
+- `~/.sellable/configs/core/proof-ledger.md`
+- `~/.sellable/configs/core/wins-ledger.md`
+- `~/.sellable/configs/core/anti-ai-writing-style.md`
+- `~/.sellable/configs/writing/outbound.md` and legacy `styleguide-core.md` as fallback/source material when present
 - `brief.md`
 - `lead-sample.json` from the find-leads step; this is the only allowed sample
   source for dry-mode message generation
 - `lead-filter.md` when present. If it is absent because the caller launched
   post-lead workstreams in parallel, start the prep/candidate stages and then
   reconcile before final `message-validation.md`.
-- `mcp/sellable/skills/create-campaign/references/ai-native-tokens.md`
-- `mcp/sellable/skills/create-campaign/references/token-fill-examples.md`
-- `mcp/sellable/skills/create-campaign-brief/references/phase75-active-runtime-message-pack.md`
-- `mcp/sellable/skills/create-campaign-v2/references/validation-criteria.md`
-- `mcp/sellable/skills/create-campaign-v2/references/thomas-revision-filters.md`
-- `mcp/sellable/skills/create-campaign-v2/references/gold-standard-message-patterns.md`
-- `mcp/sellable/skills/create-campaign-v2/references/gold-standard-message-examples.md`
-- `mcp/sellable/skills/create-campaign-v2/references/gold-standard-message-validation-example.md`
+
+### Reference Asset Loading (do this before drafting)
+
+Do not draft from this prompt alone. The full `generate-messages` prompt is
+only the contract; the reference assets below are the evidence and examples
+that define the desired output. Before writing angle drafts, you MUST load the
+required pre-draft reference pack below with `mcp__sellable__get_subskill_asset`.
+This is a hard gate: if the four required pre-draft assets are not loaded,
+return `blocked` / `retry-needed` instead of drafting. Write a short
+`Reference Asset Loading` note naming each loaded asset and whether it was
+required pre-draft, final-pass, dry-mode-only, or token-rules-only. Do not
+bulk-load the conditional references unless their trigger applies or the caller
+explicitly asks for maximum context over speed.
+
+Use `mcp__sellable__get_subskill_asset` for packaged assets:
+
+| Group | Asset to load | Job |
+| --- | --- | --- |
+| Always load before drafting | `subskillName: "create-campaign-brief", assetPath: "references/phase75-active-runtime-message-pack.md"` | Active line-level gold pack: real approved examples, short-line rhythm, CTA blocks, lowercase/titlecase cues, and PS restraint. |
+| Always load before drafting | `subskillName: "create-campaign-v2", assetPath: "references/gold-standard-message-patterns.md"` | Strategy selector: event-led vs signal-led vs job-post-led vs proof-led fallback, proof inventory, candidate set, and Finalizer Pass. |
+| Always load before drafting | `subskillName: "create-campaign-v2", assetPath: "references/gold-standard-message-examples.md"` | Full archive quality bar: exact motion examples, hard rules, and transfer limits. Use it to choose 1 primary example, not to recolor copy. |
+| Always load before drafting (never optional) | `subskillName: "create-campaign-v2", assetPath: "references/ai-tells.md"` | Canonical anti-AI checklist: body self-intros, source citations, resume recaps, title-fit assumptions, em dashes, signoffs, weak proof brags, and flattened "worth sending" source bridges. |
+| Load before approval / final pass | `subskillName: "create-campaign-v2", assetPath: "references/thomas-revision-filters.md"` | Substance filters: earned-right, presumption, vague proof, read-as-1:1, founder-origin coherence, anti-talk-at, and AI-tell filter. |
+| Dry-mode artifact output only | `subskillName: "create-campaign-v2", assetPath: "references/gold-standard-message-validation-example.md"` | Fully worked example for proof inventory, candidate messages, Finalizer Pass, Selected Winner, findings, and recommendation. |
+| Dry-mode artifact output only | `subskillName: "create-campaign-v2", assetPath: "references/validation-criteria.md"` | Step-level acceptance criteria and dry-mode message validation expectations. |
+| Reusable token rules only | `subskillName: "create-campaign", assetPath: "references/ai-native-tokens.md"` | Token spec for rich judgment tokens, including required clauses and fallback behavior. |
+| Reusable token rules only | `subskillName: "create-campaign", assetPath: "references/token-fill-examples.md"` | Concrete good/bad token fills, interpolation guardrails, and product-noun substitution traps. |
+
+Default load order:
+
+1. Load the 4 **Always load before drafting** assets. Do not infer their
+   contents from this prompt; actually call `mcp__sellable__get_subskill_asset`
+   for each required asset.
+2. Draft and run the internal Finalizer Pass.
+3. Run the selected winner against `ai-tells.md`. This is never optional. If the
+   AI-tells catalog was not loaded or any `REJECT` tell matches, do not approve,
+   confirm, recommend, or show the template as ready; return `revise-message`.
+4. Load `thomas-revision-filters.md` before approval, `confirmed`, or template
+   recommendation.
+5. Load dry-mode artifact references only when writing `message-validation.md`.
+6. Load token-rule references only when creating reusable templates or Token
+   Fill Rules that need sentence-level personalization.
 
 ### Rich Personalization Contract
 
 `mcp/sellable/skills/create-campaign/references/ai-native-tokens.md` is the
 canonical spec for personalization that requires judgment. Load it before
 writing the Token Fill Rules or any reusable template notes.
+When token fill wording is material, use
+`mcp/sellable/skills/create-campaign/references/token-fill-examples.md` as the
+conditional good/bad fill reference.
 
 - Sentence-level personalization must use AI-native bracket tokens in the
   reusable template / token plan, not old-school field substitution. Field
@@ -198,7 +235,7 @@ winner gate**.
 
 ### Retrieval & motion
 
-- treat `phase75-active-runtime-message-pack.md` as the **real line-level
+- treat `gold-standard-runtime-message-pack.md` as the **real line-level
   gold pack** for active clients and proven live message shapes
 - retrieve against the full archived gold-standard library and pick the closest 2-4 examples for consideration
 - use the runtime pack first for concrete formatting cues that the
@@ -328,6 +365,8 @@ artifact.**
    - `saw you on {{recent_signal}}`
    - `saw you around {{recent_signal}}`
    - `saw you engaging with {{recent_signal}}`
+   - `saw you raise your hand for {{signal_topic}}, so figured this was worth sending`
+   - `figured this was worth sending`
 
    Safer shapes:
 
@@ -339,8 +378,9 @@ artifact.**
    - `if {{workflow_signal}} is nowhere near your lane, ignore me`
    - `figured this might matter if {{workflow_signal}} is live at {{company}}`
    - `thought of {{company}} because {{observable_signal}} points at {{problem_context}}`
-   - `saw you raise your hand for {{signal_topic}}, so figured this was (hopefully) worth sending` only when the engagement signal is the actual source
-   - `saw you raise your hand for {{signal_topic}} (creepy to reach out based on that, i know) - but this felt too on the nose to ignore` only when the engagement signal is the actual source and the sender's voice can carry the cheekier aside
+   - `found you in a thread about {{signal_topic}}, so may be off, but this seemed relevant`
+   - `saw you raise your hand for {{signal_topic}}, so figured this was (hopefully) worth sending` only when the source was an explicit lead-magnet comment, reply, or opt-in. The parenthetical uncertainty is load-bearing; do not flatten it to `so figured this was worth sending`.
+   - `saw you raise your hand for {{signal_topic}} (creepy to reach out based on that, i know) - but this felt too on the nose to ignore` only when the source was an explicit lead-magnet comment, reply, or opt-in and the sender's voice can carry the cheekier aside
 
    For LinkedIn-post-sourced campaigns (commenters, reactors, lead magnet
    replies, or scraped conversations), it is acceptable to reference the
@@ -348,7 +388,10 @@ artifact.**
    activity-log-level: `saw you in a few conversations around
    {{signal_topic}}, so hope this is relevant` is acceptable; `saw you
    commented on {{post_context}}` and `your LinkedIn activity around...` are
-   not.
+   not. Reserve `raise your hand` phrasing for explicit lead-magnet comments,
+   replies, or opt-ins. For ordinary thread discovery, use `saw you in a few
+   conversations around {{signal_topic}}...` or `found you in a thread about
+   {{signal_topic}}...`.
 
    Keep the apologetic nature, but aim it at uncertainty, not surveillance.
    Good: `saw you in a few conversations about outbound, so may be off, but
@@ -644,18 +687,17 @@ help...` or `built for [buyer] to...`. Do not overuse generic solved-state
   solved, or fail to connect to the specific sample row. Prefer a concrete
   row-fit line, a useful artifact, or a buyer-owned current-state observation
   that the recipient can understand without reading the brief.
-- if 3 adjacent mechanics, objection removers, proof points, or CTA
-  options are genuinely parallel and easier to understand as a short
-  `-` bullet stack, use the bullet stack in the winner. Do not reserve
-  this for cleanup. Use bullets when they make the buyer picture the offer
-  faster on mobile. If the product has 3+ plain mechanics such as pricing
-  control, take-rate/economics, malpractice, credentialing, billing, async
-  chat/photo care, or setup speed, prefer a compact bullet stack over
-  separate prose lines unless bullets would make the note feel like a
-  landing page. For data / intelligence products, if the buyer receives 3+
-  concrete output types (e.g. accounts, infrastructure, signals, alerts,
-  records, reports), prefer a short bullet stack over a dense mechanism
-  paragraph.
+- run the parallel action formatting check when the winner has 3 adjacent
+  product actions, outputs, mechanics, or objection removers. If the lines
+  repeat the same subject pattern (`It drafts...` / `It adapts...` /
+  `It helps...`) and each line is a discrete function with no narrative proof
+  clause, prefer a compact `-` bullet stack because it is easier to scan on
+  mobile. Example:
+  `It helps your team:` followed by `- Draft posts...`, `- Adapt them...`,
+  `- Keep showing up...`. Do not force bullets when there are only 1-2
+  actions, one line needs narrative context, the bullets feel like a landing
+  page, or the paragraph version is clearly more human and still scans cleanly.
+  This is a formatting preference, not a message-strategy gate.
 - if one finalist already holds the best of every piece, the winner may
   equal it — name which one and on which axis it won (relevance,
   distinctiveness, proof, coherence, readability)
@@ -724,8 +766,12 @@ Finalizer preference when multiple candidates are otherwise comparable:
   peer-call, compare-notes, or similar identity-call framing. Those CTAs
   are usually weaker than naming the useful thing the buyer gets. Use them
   only when the user explicitly chose that route or the brief makes that
-  peer-call motion the approved offer. Even then, the CTA must name the
-  useful return artifact, preview, teardown, or working session.
+  peer-call motion the approved offer. Even then, preserve the intent, not the
+  phrase. Translate `compare notes` into a concrete CTA that names the topic,
+  workflow, artifact, preview, teardown, or working session. Prefer shapes like
+  `Open to a quick call on how {{company_or_team}} might turn LinkedIn content
+  into pipeline?`. Do not use `Open to compare notes?` or `Open to comparing
+  notes on...`.
 - when the message is selling or introducing a product, make the product
   plain before asking for time, but do not make the opener sound like a
   homepage definition. The reader should be able to answer "what is this?"
@@ -935,7 +981,10 @@ Before drafting, answer these five questions explicitly:
 4. **What proof makes it believable?** Pick the one proof beat that
    answers the buyer's biggest skepticism.
 5. **What is the lowest-friction true next step?** Use only a next step
-   supported by the inputs.
+   supported by the inputs. If the campaign brief explicitly names a CTA
+   motion, preserve it unless it fails truth, clarity, pressure, or safety
+   gates. Improve the CTA by making the object concrete before replacing the
+   motion.
 
 Then choose the exact element pool that angle drafts are allowed to use:
 
@@ -986,6 +1035,23 @@ both choices are genuinely useful and supported:
 Do not add option B just to mimic a gold standard. If the second option
 is weak, use one CTA.
 
+CTA precedence:
+
+1. If the campaign brief explicitly names a CTA motion, preserve the intent of
+   that motion unless it is unsupported, too high-pressure, unsafe, or too vague
+   to make concrete.
+2. If preserving it, make the object specific in the same line so the buyer
+   knows what they are agreeing to discuss, see, or get.
+3. Replace it only when the brief CTA cannot pass truth, clarity, pressure, or
+   safety gates.
+
+Treat `compare notes` as shorthand for a peer conversation, not as buyer-facing
+copy. The phrase itself is blocked in selected winners, including `Open to
+compare notes?`, `Founder-to-founder compare notes?`, and `Open to comparing
+notes on...`. If the brief selected that intent, translate it into a concrete
+quick-call or working-session CTA, e.g. `Open to a quick call on how
+{{company_or_team}} might turn LinkedIn content into pipeline?`.
+
 For artifact/sample offers, the CTA should usually be one self-contained
 yes/no question that names the concrete thing the buyer gets. Do not split
 the ask into a setup sentence plus a vague question.
@@ -1564,6 +1630,13 @@ teardown`, `record a video`, or similar assets are BLOCKED unless the
   input says that exact next step exists. When unsure, ask for the
   lowest-friction true next step from the brief, such as sending the
   setup link, next step, or a short walkthrough.
+- **Brief CTA obedience:** if the brief explicitly names a CTA motion, the
+  selected winner must either preserve that motion's intent with concrete
+  specificity or explain why truth, clarity, pressure, or safety gates forced a
+  replacement.
+  If the brief uses `compare notes`, do not put that phrase in buyer-facing copy.
+  Translate it into a concrete quick-call or working-session CTA that names the
+  topic or workflow.
 - **CTA clarity:** if the product category is unfamiliar, the CTA must
   make the preview easy to imagine in one short phrase. Avoid vague asks
   like `send the setup link` unless the message has already made that
@@ -1578,8 +1651,11 @@ teardown`, `record a video`, or similar assets are BLOCKED unless the
 artifact / preview] you can [use/check/compare]?`.
 - **CTA specificity:** generic CTAs like `compare notes`, `worth a chat`,
   `open to a call`, or `quick walkthrough` are BLOCKED unless the same
-  line names the specific thing the buyer will compare, see, or get. The
-  next step must be easy to picture.
+  line names the specific thing the buyer will discuss, see, or get. The
+  next step must be easy to picture. `Open to a quick call on how
+  {{company_or_team}} might turn LinkedIn content into pipeline?` passes
+  because the topic is concrete; `Open to compare notes?` fails because the
+  object is missing and the phrase is stale.
 - **Preview CTA wording:** when the CTA is a preview, prefer `open to
 seeing...` over `worth seeing...` unless the chosen gold motion strongly
   supports `worth`. `Open to seeing what this would look like for your own
@@ -1668,8 +1744,11 @@ led to it. Acceptable openers:
 - `Hey {{first_name}}, hope this is relevant if [buyer context] is still on your plate.`
 - `Hey {{first_name}}, saw you might be interested in [topic], so hope this is relevant.`
 - `Hey {{first_name}}, saw you in a few conversations around [topic], so hope this is relevant.`
-- `Hey {{first_name}}, saw you raise your hand for [topic], so figured this was (hopefully) worth sending.`
-- `Hey {{first_name}}, saw you raise your hand for [topic] (creepy to reach out based on that, i know) - but this felt too on the nose to ignore.`
+- `Hey {{first_name}}, found you in a thread about [topic], so may be off, but this seemed relevant.`
+- `Hey {{first_name}}, saw you raise your hand for [topic], so figured this was (hopefully) worth sending.` Only use this for explicit lead-magnet comments, replies, or opt-ins.
+- `Hey {{first_name}}, saw you raise your hand for [topic] (creepy to reach out based on that, i know) - but this felt too on the nose to ignore.` Only use this for explicit lead-magnet comments, replies, or opt-ins.
+- Do not use the flattened line `so figured this was worth sending`; either keep
+  `(hopefully)` or use `so hope this is relevant`.
 - `Hey {{first_name}}, pre-[product], we [did the operator-reality
 thing] for [X] years; [one-line consequence].`
 - `Hey {{first_name}}, building a thing for [segment] I think you'd
@@ -1880,10 +1959,18 @@ Flow skeleton (apply even when motion varies):
 2. Pain — what's breaking now
 3. **What the product IS** — one crisp sentence naming the product and what category of work it takes on. Example shape: `[Product] is [a category-noun] that [takes a specific class of work off the buyer's plate]`. When the offer is for the buyer's exact role/credential, prefer `lets you...` or `[role]s like you...` over `lets a [role]...` so the buyer does not feel treated like an outsider. Archive-anchored illustrations: Galley's "AI that reads the messiest BEOs and turns them into production-ready plans"; Revvix's "shows what's actually exploitable on your endpoints based on runtime activity".
 4. **What the product DOES** — one action per line. Three actions maximum. Choose the rendering by a **concrete test**, not a feeling:
-   - **Use bullets when the action lines are maximally parallel**: each starts with the same subject (e.g. `It X` / `It Y` / `It Z`), each is a discrete product function, none carries narrative context. This is the default case.
-     - Example shape: `- [Verb] [concrete object from the buyer's workflow].`
-   - **Use one-line paragraphs only when at least one action carries a short narrative clause** that wouldn't fit cleanly in a bullet.
-   - "Conversational motion" is **not** a reason to prefer paragraphs. If the three actions all start with `It X`, they are parallel by definition and should render as bullets.
+   - **Prefer bullets when 3 adjacent action lines are maximally parallel**:
+     each starts with the same subject pattern (e.g. `It drafts...` /
+     `It adapts...` / `It helps...`), each is a discrete product function,
+     and none carries narrative context or proof. Use a setup line plus short
+     `-` bullets, e.g. `It helps your team:` then `- Draft posts...`,
+     `- Adapt them...`, `- Keep showing up...`.
+   - **Use one-line paragraphs** when there are only 1-2 actions, at least one
+     action carries a short narrative clause, bullets would feel like a landing
+     page, or the paragraph version is clearly more human and still scans
+     cleanly.
+   - "Conversational motion" alone is **not** a reason to avoid bullets when
+     all 3 action lines repeat the same `It X` structure.
    - Never stack the three actions into one glued comma-list sentence.
 5. Deployment ease — one short paragraph
 6. CTA — useful next step, binary when the brief supports it
@@ -1892,7 +1979,9 @@ Flow skeleton (apply even when motion varies):
 Rules within the flow:
 
 - **banned**: comma-stacking three actions into one glued sentence (e.g. `"order intake, inventory sync, and reorder timing"` glued together). Split into one action per line.
-- **preferred**: one action per line — as one-line paragraphs or as a bullet list, whichever reads cleaner (see below)
+- **preferred**: one action per line — as one-line paragraphs or as a bullet
+  list, whichever reads cleaner. Use bullets as a mobile readability preference
+  for 3 repeated-subject product actions, not as a blanket hard gate.
 - the "what the product IS" sentence comes **before** the action breakdown — skipping it makes the actions feel disconnected
 - if the brief does not support three distinct actions, drop to two or one. Do not pad.
 - if a proof sentence gets long, split the metric and the explanation into separate one-line paragraphs rather than chaining them together
@@ -1910,10 +1999,11 @@ Rules:
   - `"Saw you might be interested in [topic], so hope this is relevant."`
   - `"Saw you in a few conversations around [topic], so hope this is relevant."`
   - `"Saw you in a few conversations about [topic], so may be off, but this seemed relevant."`
+  - `"Found you in a thread about [topic], so may be off, but this seemed relevant."`
   - `"Thought of {{company}} because [observable signal] points at [problem]."`
   - `"Figured this might matter if [workflow] is live at {{company}}."`
-  - `"Saw you raise your hand for [topic], so figured this was (hopefully) worth sending."`
-  - `"Saw you raise your hand for [topic] (creepy to reach out based on that, i know) - but this felt too on the nose to ignore."`
+  - `"Saw you raise your hand for [topic], so figured this was (hopefully) worth sending."` Only for explicit lead-magnet comments, replies, or opt-ins.
+  - `"Saw you raise your hand for [topic] (creepy to reach out based on that, i know) - but this felt too on the nose to ignore."` Only for explicit lead-magnet comments, replies, or opt-ins.
 - blocked signal use:
   - `"AI-GTM stack is clearly on your mind."`
   - `"You're clearly focused on [area]."`
@@ -1922,7 +2012,9 @@ Rules:
   - `"Saw you on [topic]."`
   - `"Saw you around [topic]."`
   - `"Saw you engaging with [topic]."`
-- signal-led opener shape is a **special case**, not the default. Use it only when the archived motion truly depends on it and the line can stay natural. For LinkedIn-post-sourced campaigns, prefer `"saw you in a few conversations around [topic], so hope this is relevant"` when referencing the source makes the outreach feel less random. Avoid activity-log phrasing such as `"you commented on..."`, `"you reacted to..."`, or `"your LinkedIn activity..."` unless the approved motion is the deliberately self-aware raise-hand line.
+  - `"Saw you raise your hand for [topic], so figured this was worth sending."`
+  - `"Figured this was worth sending."`
+- signal-led opener shape is a **special case**, not the default. Use it only when the archived motion truly depends on it and the line can stay natural. For LinkedIn-post-sourced campaigns, prefer `"saw you in a few conversations around [topic], so hope this is relevant"` or `"found you in a thread about [topic], so may be off, but this seemed relevant"` when referencing the source makes the outreach feel less random. Avoid activity-log phrasing such as `"you commented on..."`, `"you reacted to..."`, or `"your LinkedIn activity..."` unless the approved motion is the deliberately self-aware raise-hand line for an explicit lead-magnet comment, reply, or opt-in.
 - tokenized engagement-source opener shape is BLOCKED by default:
   `{{first_name}}, saw you {{engagement_context}} on {{post_context}}` reads
   like surveillance unless the filled line is explicitly self-aware and
@@ -1930,11 +2022,12 @@ Rules:
 [topic] is part of the plan`, `saw you might be interested in [topic], so hope
 this is relevant`, `saw you in a few conversations around [topic], so hope this
 is relevant`, `saw you in a few conversations about [topic], so may be off,
-but this seemed relevant`, or one of the self-aware raise-hand shapes when the source is the
-actual reason for the note: `saw you raise your hand for [topic], so figured
-this was (hopefully) worth sending` or `saw you raise your hand for [topic]
-(creepy to reach out based on that, i know) - but this felt too on the nose to
-ignore`. Do not use the longer `you might not remember the thread...` shape;
+but this seemed relevant`, or `found you in a thread about [topic], so may be
+off, but this seemed relevant`. Use the self-aware raise-hand shapes only when
+the source was an explicit lead-magnet comment, reply, or opt-in: `saw you raise
+your hand for [topic], so figured this was (hopefully) worth sending` or `saw you
+raise your hand for [topic] (creepy to reach out based on that, i know) - but
+this felt too on the nose to ignore`. Do not use the longer `you might not remember the thread...` shape;
 if the concise source bridge still feels awkward, omit the engagement reference.
 - do not describe the sender/client in third person inside the outbound message.
   `p.s. Saju's angle is...`, `Christian's angle is...`, `[sender]'s approach
@@ -2368,7 +2461,7 @@ hiring for`
 - Best CTA: Candidate [A|B|C] — reason
 - Best PS / no-PS decision: Candidate [A|B|C] — reason
 - Element edits made by finalizer: ...
-- Bullet-stack decision: used | rejected | not applicable — reason
+- Parallel action formatting: bullets used | paragraphs kept | not applicable — reason
 - Style consistency check: PASS | BLOCKED — reason
 - Assembly note: clean combination or one candidate swept
 
@@ -2377,7 +2470,7 @@ hiring for`
 - Original winner: ...
 - Simplified candidate: ...
 - Simplifier edits: combined lines | split dense line | preserved bullet stack | added bullet stack | none
-- Bullet-stack decision: preserved | added | rejected | not applicable — reason
+- Parallel action formatting: preserved bullets | added bullets | paragraphs kept | not applicable — reason
 - Robustness check: PASS | BLOCKED — reason
 - Decision: applied | rejected
 
@@ -2400,6 +2493,7 @@ hiring for`
 - Jargon / acronym exactness: PASS | BLOCKED — reason
 - Style consistency: PASS | BLOCKED — reason
 - CTA truth: PASS | BLOCKED — reason
+- Brief CTA obedience: PASS | BLOCKED | NOT APPLICABLE — reason
 - CTA clarity: PASS | BLOCKED — reason
 - PS restraint: PASS | BLOCKED | OMITTED — reason
 - YC / backing PS: PASS | BLOCKED | OMITTED — reason
@@ -2520,22 +2614,28 @@ too generic, diagnose the gap precisely:
 
 Then tighten the brief or calibration notes before scaling.
 
-Use the example bank as the primary strategy source even when the brief does
-not already contain winning examples. Do not default to generic REPLY-style
-copy when the motion clearly matches a tighter archived pattern. Strong
-references include:
+Use the v2 runtime gold pack as the primary line-level source even when the
+brief does not already contain winning examples. Do not default to generic
+REPLY-style copy when the motion clearly matches a tighter approved pattern.
+Primary approved references are:
 
-- Sellable.dev
+- sellable.dev
+- Hey Digital / HeyDigital
 - Galley
-- Gelee
-- HeyDigital
-- Revvix / Spektion
-- Superposition
-- Persona Digital
+- Clover
+- Persona
+
+Use Superpower only for benefits/healthcare mechanism language and cleaned
+low-certainty relevance bridges. Use Revvix / Spektion and Superposition only
+for explicit event/logistics or job-post/founder-hiring motions. Do not use
+Gelee, westpark villas, Amplify Security, or raw old-client archive examples as
+runtime inspiration unless the caller explicitly provides them as campaign
+calibration.
 
 When the brief is sparse but the motion clearly matches an archived winner,
-borrow the closest message shape from
-`gold-standard-message-examples.md` before inventing a new structure.
+borrow the closest approved shape from `gold-standard-runtime-message-pack.md`
+first, then use `gold-standard-message-examples.md` only for strategy skeletons
+before inventing a new structure.
 
 ### Single Row
 
@@ -2619,12 +2719,12 @@ research → condense → 10 angle agents in parallel → finalizer combines bes
 - Background: {1-2 lines}
 
 ## Voice + Outbound Rules (condensed — full files available via Read tool)
-- Use `.sellable/configs/core/context-modes.md` to choose the right context stance, then run an anti-AI audit against `.sellable/configs/core/anti-ai-writing-style.md` before returning copy.
-- Flow skeleton: opener → pain → **what the product IS** → **what it DOES** (one action per line, up to three) → deployment ease → CTA → optional PS
+- Use `~/.sellable/configs/core/context-modes.md` to choose the right context stance, then run an anti-AI audit against `~/.sellable/configs/core/anti-ai-writing-style.md` before returning copy.
+- Flow skeleton: opener → pain → **what the product IS** → **what it DOES** (one action per line, up to three; prefer short bullets for 3 repeated-subject product actions) → deployment ease → CTA → optional PS
 - A cold reader must be able to state what the product does in one sentence after reading. Require a crisp `Product is an X that does Y` anchor before any action breakdown. Do not gesture at "that chain" / "the stack" / "that work"
 - Blank line between every sentence in the body. The body renders as a sequence of one-line paragraphs separated by blank lines, not as multi-sentence paragraphs. Target 6-10 one-line paragraphs
 - 5th-grade reading level by default. Cut glue language (handoff, order-to-cash, rip-and-replace). Keep brief-native product/tool names (Shopify, HubSpot)
-- No bullet points, no "I noticed...", no compliment sandwiches, no em dashes unless the canonical example uses one
+- No feature/benefit marketing bullet lists, no "I noticed...", no compliment sandwiches, no em dashes unless the canonical example uses one. Exception: use a short bullet stack when 3 adjacent product actions repeat the same subject pattern and bullets improve mobile readability.
 - No synthesized framing ("at your stage", "in a setup like yours", "running X means...", "X means you're likely...")
 - 3 candidates then `Finalizer Pass` — pick best opener, proof sentence, bridge, CTA across them and assemble the winner
 - PS is optional; only include if it materially strengthens the fit case. When included, use `I` / `our CEO` / `our team` / `we` voice, never bare first names. At most two proof beats, tied to why the sender understands the buyer's pain. No three-credential resume lists
@@ -2686,7 +2786,7 @@ research → condense → 10 angle agents in parallel → finalizer combines bes
 8. Return: { success: true, message: "...", research: [...], anglesExplored: 10 }
 ```
 
-**IMPORTANT:** Load `.sellable/configs/core/about-me.md`, `.sellable/configs/core/my-company.md`, `.sellable/configs/core/context-modes.md`, `.sellable/configs/core/proof-ledger.md`, `.sellable/configs/core/wins-ledger.md`, `.sellable/configs/core/anti-ai-writing-style.md`, `.sellable/configs/writing/outbound.md`, and `.sellable/insights/cross-skill.md` once in the lead agent. Use the legacy style guide fallback when present. Pass condensed versions to workers so context stays focused.
+**IMPORTANT:** Load `~/.sellable/configs/core/about-me.md`, `~/.sellable/configs/core/my-company.md`, `~/.sellable/configs/core/context-modes.md`, `~/.sellable/configs/core/proof-ledger.md`, `~/.sellable/configs/core/wins-ledger.md`, `~/.sellable/configs/core/anti-ai-writing-style.md`, `~/.sellable/configs/writing/outbound.md`, and `~/.sellable/insights/cross-skill.md` once in the lead agent. Use the legacy style guide fallback when present. Pass condensed versions to workers so context stays focused.
 
 ## Batch Approval
 

package/skills/interview/SKILL.md

@@ -111,7 +111,7 @@ mark private before you ask a blank questionnaire.
 
 Prefill from whatever exists:
 
-- `.sellable/configs/**`, especially current writing, audience, FAQs, and
+- `~/.sellable/configs/**`, especially current writing, audience, FAQs, and
   discovery files.
 - `docs/funding/**`, `docs/business/**`, and `docs/content/**`.
 - User-supplied voice samples such as writing, posts, emails, meeting
@@ -151,9 +151,9 @@ Audio-friendly workflow:
 
 Every run writes a raw archive:
 
-- `.sellable/interviews/{date}-{slug}/raw.md`
-- `.sellable/interviews/{date}-{slug}/compiled.md`
-- `.sellable/interviews/{date}-{slug}/decisions.md`
+- `~/.sellable/interviews/{date}-{slug}/raw.md`
+- `~/.sellable/interviews/{date}-{slug}/compiled.md`
+- `~/.sellable/interviews/{date}-{slug}/decisions.md`
 
 Raw archives preserve the run. They are not the stable memory layer.
 
@@ -171,20 +171,20 @@ voice-faithful, reusable, or corrective, propose a candidate upsert:
 - derived updates
 
 Ask the user to approve, edit, reject, or mark private. Approved answers go to
-`.sellable/configs/core/answer-bank.md` using stable keys so repeat runs can
+`~/.sellable/configs/core/answer-bank.md` using stable keys so repeat runs can
 add, correct, merge, and avoid duplicates.
 
 ## 5. Register Transcript And Voice Samples
 
 Every interview or voice sample can register a curated transcript library entry
-under `.sellable/configs/core/transcripts/`. Keep the reusable index separate
+under `~/.sellable/configs/core/transcripts/`. Keep the reusable index separate
 from raw archives.
 
 Required transcript targets:
 
-- `.sellable/configs/core/transcripts/README.md`
-- `.sellable/configs/core/transcripts/INDEX.md`
-- `.sellable/configs/core/transcripts/topics/{topic}.md`
+- `~/.sellable/configs/core/transcripts/README.md`
+- `~/.sellable/configs/core/transcripts/INDEX.md`
+- `~/.sellable/configs/core/transcripts/topics/{topic}.md`
 
 Track source, date, speakers, target speaker, context mode, topic tags, quality
 notes, sensitivity, and derived memory links.
@@ -194,15 +194,15 @@ notes, sensitivity, and derived memory links.
 Use `references/compiler-schema.md` before writing compiled core files. Merge
 updates into the smallest relevant stable file:
 
-- `.sellable/configs/core/about-me.md`
-- `.sellable/configs/core/my-company.md`
-- `.sellable/configs/core/anti-ai-writing-style.md`
-- `.sellable/configs/core/proof-ledger.md`
-- `.sellable/configs/core/story-bank.md`
-- `.sellable/configs/core/answer-bank.md`
-- `.sellable/configs/core/context-modes.md`
-- `.sellable/configs/core/decision-rules.md`
-- `.sellable/configs/core/change-log.md`
+- `~/.sellable/configs/core/about-me.md`
+- `~/.sellable/configs/core/my-company.md`
+- `~/.sellable/configs/core/anti-ai-writing-style.md`
+- `~/.sellable/configs/core/proof-ledger.md`
+- `~/.sellable/configs/core/story-bank.md`
+- `~/.sellable/configs/core/answer-bank.md`
+- `~/.sellable/configs/core/context-modes.md`
+- `~/.sellable/configs/core/decision-rules.md`
+- `~/.sellable/configs/core/change-log.md`
 
 Repeat runs must preserve user edits. Only replace generated sections that are
 clearly marked as generated/mergeable. Otherwise append, patch the smallest
@@ -213,10 +213,10 @@ section, or add a dated correction in `change-log.md`.
 Use curated reference folders with `INDEX.md` manifests and copied or distilled
 examples where the example itself is useful context:
 
-- `.sellable/configs/core/references/linkedin-posts/`
-- `.sellable/configs/core/references/inspiration/`
-- `.sellable/configs/core/references/applications/`
-- `.sellable/configs/core/references/sales-copy/`
+- `~/.sellable/configs/core/references/linkedin-posts/`
+- `~/.sellable/configs/core/references/inspiration/`
+- `~/.sellable/configs/core/references/applications/`
+- `~/.sellable/configs/core/references/sales-copy/`
 
 Use `references/reference-curation.md` for manifest fields, duplicate keys, and
 when to copy versus index only.
@@ -226,7 +226,7 @@ when to copy versus index only.
 Before finalizing, run the silent audit pass in `references/anti-ai-audit.md`.
 Capture banned AI-ish patterns, user-authentic exceptions, context-only rules,
 negative-parallelism limits, proof hygiene, and anti-overfitting warnings in
-`.sellable/configs/core/anti-ai-writing-style.md`.
+`~/.sellable/configs/core/anti-ai-writing-style.md`.
 
 ## 9. Continue After Saves
 
@@ -248,7 +248,7 @@ Repeat runs are normal. They must add, correct, merge, and preserve user edits.
   references.
 - Merge into compiled core files instead of replacing whole documents.
 - Preserve manual sections unless the user explicitly asks to rewrite them.
-- Add downstream corrections to `.sellable/configs/core/change-log.md`, then
+- Add downstream corrections to `~/.sellable/configs/core/change-log.md`, then
   update the smallest affected rule, answer, claim, story, or context mode.
   </idempotency_rules>
 

package/skills/interview/references/legacy-linkedin-interview.md

@@ -21,16 +21,16 @@ Key principles:
 
 ## Original Objective
 
-Conduct a voice-first interview to populate `.sellable/configs/`:
+Conduct a voice-first interview to populate `~/.sellable/configs/`:
 
-1. Style guide -> `.sellable/configs/writing/styleguide-core.md` and persisted
+1. Style guide -> `~/.sellable/configs/writing/styleguide-core.md` and persisted
    via `set_engage_style_guide`.
-2. Comment rules -> `.sellable/configs/writing/comments.md`.
-3. ICP profile -> `.sellable/configs/audience/icp.md`.
-4. Tracked people -> `.sellable/configs/discovery/influencers.md` via
+2. Comment rules -> `~/.sellable/configs/writing/comments.md`.
+3. ICP profile -> `~/.sellable/configs/audience/icp.md`.
+4. Tracked people -> `~/.sellable/configs/discovery/influencers.md` via
    `upsert_engage_tracked_person`.
 
-The interview reads `.sellable/insights/` to ask smarter questions, such as
+The interview reads `~/.sellable/insights/` to ask smarter questions, such as
 which topics or hooks performed in the latest engage/post sessions. The
 interview should feel like a 5-minute conversation, not a form.
 
@@ -40,10 +40,10 @@ interview should feel like a 5-minute conversation, not a form.
 
 1. Load current configs via `get_engage_memory()` to check what is populated.
 2. Read lightweight insight files when they exist:
-   - `./.sellable/insights/engage-sessions.md`
-   - `./.sellable/insights/post-sessions.md`
-   - `./.sellable/insights/cross-skill.md`
-   - `./.sellable/configs/audience/icp.md`
+   - `~/.sellable/insights/engage-sessions.md`
+   - `~/.sellable/insights/post-sessions.md`
+   - `~/.sellable/insights/cross-skill.md`
+   - `~/.sellable/configs/audience/icp.md`
 3. Load the user's LinkedIn profile via `fetch_linkedin_profile`.
 4. Fetch 5-10 recent posts from 2-3 relevant thought leaders using
    `search_engagement_posts`.
@@ -95,7 +95,7 @@ corrections and rewrite the config files.
 
 ### Phase 5: ICP Profile
 
-If `.sellable/configs/audience/icp.md` is still a template or thin, ask who the
+If `~/.sellable/configs/audience/icp.md` is still a template or thin, ask who the
 user wants to reach with LinkedIn presence, then write the profile using
 `core/ICP.template.md`.
 
@@ -109,7 +109,7 @@ Ask which specific people the user wants to track, then call
 1. Never fabricate quotes or examples.
 2. Preserve the user's exact phrasing as blockquotes in the style guide.
 3. Keep the interview under 5 minutes of user effort.
-4. Always write results to `.sellable/configs/`.
+4. Always write results to `~/.sellable/configs/`.
 5. Persist the style guide via MCP.
 6. Anchor every question to a real post.
 7. Read business context first, including

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

@@ -7,13 +7,13 @@ sensitive, external, or only useful for provenance. Every folder uses INDEX.md m
 
 ## Folders
 
-- `.sellable/configs/core/references/linkedin-posts/` - personal best posts,
+- `~/.sellable/configs/core/references/linkedin-posts/` - personal best posts,
   comments, hooks, and thread patterns.
-- `.sellable/configs/core/references/inspiration/` - admired outside examples,
+- `~/.sellable/configs/core/references/inspiration/` - admired outside examples,
   anti-examples, voice-capture sources, and pattern notes.
-- `.sellable/configs/core/references/applications/` - accelerator, investor,
+- `~/.sellable/configs/core/references/applications/` - accelerator, investor,
   founder-profile, and answer-pack references.
-- `.sellable/configs/core/references/sales-copy/` - outbound, reply, website,
+- `~/.sellable/configs/core/references/sales-copy/` - outbound, reply, website,
   deck, objection, proof, and customer-language examples.
 
 Each folder should have an `INDEX.md`. A copied/distilled example should live

package/skills/interview/references/voice-capture-method.md

@@ -5,7 +5,7 @@ materials are provenance; do not expose them as separate user-facing workflows.
 
 ## Operating Loop
 
-1. Prefill from existing `.sellable/configs`, docs, posts, transcripts, emails,
+1. Prefill from existing `~/.sellable/configs`, docs, posts, transcripts, emails,
    call notes, and user-provided samples.
 2. Do evidence collection: collect source path/URL, date, author/speaker,
    context, audience, privacy, and whether the sample is natural speech, edited