@sellable/mcp 0.1.213 → 0.1.214

package/skills/create-campaign-v2/references/gold-standard-message-patterns.md

@@ -1,6 +1,6 @@
 # Gold-Standard Message Patterns
 
-Use these patterns when validating or drafting messages for `create-campaign-v2`.
+Use these patterns when validating or drafting Sellable campaign messages.
 
 The priority is not "write generally good outbound." The priority is:
 
@@ -193,14 +193,15 @@ Shape:
 - plain signal mention first
 - one line that makes the relevance feel honest
 - simple product framing
-- binary options
+- specific low-friction next step
 - optional short `PS` with proof as the final line
 
 Prefer:
 
 - lowercase or casual casing when the motion supports it
-- an honest line like "hope this is relevant" or "so hopefully relevant"
-- two clean options instead of a long CTA paragraph
+- an honest line like "hope this is relevant" or "so may be off, but this seemed relevant"
+- a concrete CTA that names the useful conversation or asset
+- binary options only when the brief explicitly supports two real next steps
 - direct wording over polished marketing language
 
 Avoid:
@@ -229,11 +230,11 @@ Use only when event, signal, and hiring hooks are unavailable.
 
 This is the fallback most likely to drift into bland copy, so keep it tight.
 
-**Exemplar:** Example 2 in `gold-standard-message-examples.md` (Stack-Replacement
-Operator Diagnostic). It is the default proof-led fallback exemplar. Its
-rhythm — observed current-state → what breaks → product-name-first mechanism →
-PS for credibility — generalizes across proof-led fallbacks even when the
-category isn't literally stack-replacement.
+Use the proof-led fallback logic below directly. Do not retrieve a deleted
+stack-replacement archive example as copy. The useful rhythm is: observed
+current-state → what breaks → product-name-first mechanism → strongest true
+proof or useful CTA. That rhythm generalizes across proof-led fallbacks even
+when the category is not literally stack replacement.
 
 Shape:
 
@@ -277,6 +278,9 @@ Prefer:
 - product-name-first mechanism lines when the product can be named cleanly
 - a short `PS` for social proof, backing, prior-company proof, or category-first
   proof when that proof is real and would otherwise bloat the main body
+- backing proof in a `PS` must translate into buyer value, not seller focus:
+  `backed by [X] to help [buyer segment] [buyer outcome]` beats
+  `backed by [X] and focused on [category/problem]`
 - if a `PS` is used, keep it to the final line of the message
 - short words and plain sentences a busy buyer can scan fast
 - one sentence per line in the final draft when the channel is InMail or email

package/skills/create-campaign-v2/references/gold-standard-message-validation-example.md

@@ -19,7 +19,7 @@ Status: confirmed
 Mode: DRY MODE (no DB mutation)
 Template Used: event-led canonical template
 Primary Example: Example 1 — Revvix / Spektion Event-Led Security
-Secondary Influence: Example 7 — Useful CTA Shapes (binary option)
+Secondary Influence: Example 6 — Useful CTA Shapes (binary option)
 Lead Sample Basis: 3 validated leads (Dana Patel — VP Security Eng at Arco;
 Mariko Stein — Head of AppSec at Fernway; Ben Oduya — Director, Vuln Mgmt
 at Plantform)
@@ -52,7 +52,7 @@ No other tokens are allowed in this campaign.
 
 ## Token Adherence Table
 
-| Sample | Supported Tokens Only | All Tokens Resolved | Proof Safe | Personalization Grounded | Thomas Filters | Result |
+| Sample | Supported Tokens Only | All Tokens Resolved | Proof Safe | Personalization Grounded | Sellable Cleanup Rules | Result |
 | ------ | --------------------- | ------------------- | ---------- | ------------------------ | -------------- | ------ |
 | Dana   | yes                   | yes                 | yes        | yes                      | pass           | pass   |
 | Mariko | yes                   | yes                 | yes        | yes                      | pass           | pass   |
@@ -135,7 +135,7 @@ No other tokens are allowed in this campaign.
 - Best bridge: **Candidate A** — single-line transition from pain to
   mechanism without editorializing.
 - Best CTA: **Candidate C** — "Happy to grab coffee or send a short
-  overview first" is the binary option from Example 7 and matches the
+  overview first" is the binary option from Example 6 and matches the
   low-pressure event motion better than A's open-ended close.
 - Assembly note: clean combination — opener from C, bridge + mechanism from
   A, CTA from C, plus a new short `PS` carrying the rank-5 founder proof
@@ -203,7 +203,7 @@ No other tokens are allowed in this campaign.
   generic credibility sentence."
 - Token fill rules are declared once, with source fields and fallbacks, and
   the adherence table reports pass/fail per lead.
-- The "What Good Looks Like" bar in `thomas-revision-filters.md` is met:
+- The "What Good Looks Like" bar in `sellable-cleanup-rules.md` is met:
   sharp voice, grounded personalization, motion-aligned structure, useful
   CTA proportional to signal.
 

package/skills/create-campaign-v2/references/lead-validation-preview.md

@@ -1,6 +1,6 @@
 # Lead Validation Preview
 
-This reference defines the Phase 84 `find leads` output contract.
+This reference defines the `find leads` output contract.
 
 ## Inputs
 

package/skills/create-campaign-v2/references/parallel-critique-protocol.md

@@ -1,14 +1,14 @@
 # Parallel Critique Protocol
 
-This reference governs the optional Step 15 critique pass introduced in
-Plan 85-03. Load this file whenever `messaging.critique.enabled === true`
+This reference governs the optional Step 15 critique pass. Load this file
+whenever `messaging.critique.enabled === true`
 in `core/auto-execute.yaml`. When the flag is `false`, the plain Step 15
 path runs unchanged and none of the protocol below applies.
 
 ## Principle
 
 Step 15 (`auto-execute-messaging`) already generates messages under the
-Phase 84 token contract. The critique pass is a bounded, opt-in quality
+offline-validation token contract. The critique pass is a bounded, opt-in quality
 lens on top of that output. It is NOT a second drafting pass. It never
 invents new tokens, new proof, or new personalization, and it never
 ships a rewrite that violates the token contract.
@@ -20,7 +20,7 @@ The critique pass is:
 - **Parallel.** Three fixed critic groups (targeting, copy, voice)
   run in parallel and return structured JSON.
 - **Synthesized.** One synthesis step merges the three voices into a
-  single rewrite and re-runs the Phase 84 finalizer pass.
+  single rewrite and re-runs the offline-validation finalizer pass.
 - **Budget-capped.** A trip on `budgetUsdCap` HALTS critique for the
   remaining sample and continues the plain tail. Cost never explodes
   silently.
@@ -47,8 +47,8 @@ calibration.
 - `lead-sample.json`, `lead-filter.md`, `brief.md` (read-only — these
   are the same artifacts the plain drafter used).
 - `messaging.critique.*` config values from `auto-execute.yaml`.
-- The Phase 84 token contract rules in
-  `references/thomas-revision-filters.md`.
+- The offline-validation token contract rules in
+  `references/sellable-cleanup-rules.md`.
 
 ## Step Shape
 
@@ -201,7 +201,7 @@ the protocol file).
 
 Rules:
 
-1. **Token contract first.** The synthesizer enforces the Phase 84
+1. **Token contract first.** The synthesizer enforces the offline-validation
    token contract verbatim:
 
    - Use only tokens documented in `brief.md` as supported fields.
@@ -216,7 +216,7 @@ Rules:
    voice. Do not blend two motions into one rewrite.
 
 3. **Finalizer pass last.** If `synthesis.enforceFinalizerPass` is
-   `true` (default), re-run the Phase 84 finalizer pass on the
+   `true` (default), re-run the offline-validation finalizer pass on the
    synthesis output. The finalizer is the last guardrail against
    critic-introduced token drift. A finalizer failure falls back to
    the plain message for that row.
@@ -346,14 +346,14 @@ passes.
 
 ## Hard Rules
 
-- Critique is OFF by default. Plan 85-02 never flips the flag.
+- Critique is OFF by default. The plain campaign tail never flips the flag.
 - Sample size is bounded by `messaging.critique.sampleSize`. The
   pass NEVER runs against the full cohort.
 - Three critic groups only: targeting, copy, voice. Do NOT add a
   fourth.
 - Every critic returns the structured JSON envelope above. Free-form
   critic output is discarded.
-- The synthesizer enforces the Phase 84 token contract verbatim.
+- The synthesizer enforces the offline-validation token contract verbatim.
 - The synthesis step MUST re-run the finalizer pass when
   `enforceFinalizerPass === true` (default).
 - Opus is reserved for the highest-value subset only and gated

package/skills/create-campaign-v2/references/sample-validation-loop.md

@@ -1,6 +1,6 @@
 # Sample Validation Loop
 
-This reference governs Step 14 (`validate-sample`) of the Plan 85-02
+This reference governs Step 14 (`validate-sample`) of the
 autonomous tail. Load this file before enriching + scoring the sample, and
 on every revision round.
 
@@ -243,9 +243,9 @@ Action: autonomous `update_campaign_brief` with the specific diagnostic
 (e.g. "add case-study proof for pain point Y"). Rerun sample. Increment
 revisionRound.
 
-#### Worked example — horizontal-SaaS seniority drift (Plan 95-03 Ambral)
+#### Worked example — horizontal-SaaS seniority drift
 
-Symptom observed during Plan 95-03 Ambral walkthrough: 14/30 (47%)
+Symptom observed during an Ambral walkthrough: 14/30 (47%)
 sample was FIT+MAYBE, but the MAYBE cluster was driven by sub-D-round
 "VP Customer Success" titles. These rows match the title whitelist but
 likely don't own budget at that stage.

package/skills/create-campaign-v2/references/{thomas-revision-filters.md → sellable-cleanup-rules.md}

@@ -1,6 +1,6 @@
-# Thomas Revision Filters
+# Sellable Cleanup Rules
 
-Use these filters before Phase 84 message validation is marked `confirmed`.
+Use these filters before offline message validation is marked `confirmed`.
 
 Read "What Good Looks Like" first. These are the positive targets. Use
 "Automatic Revisions" as the rejection backstop, not the primary lens.
@@ -99,6 +99,7 @@ Revise or reject the sample when any of these happen.
 - **full titles in the PS when the bare role word would read more natural** — "our CEO [did X]" reads more natural than "CEO Alex, 2x founder, [did X]". Drop titles unless the title itself is the proof
 - more than two proof beats in the PS (three or more reads as a resume dump)
 - a proof beat that is not tied to the buyer's situation — proof should explain why this sender gets the buyer's pain, not just list credentials
+- **backing proof ends in seller-focus copy** — reject `backed by [X] and focused on [category/problem]`. Keep the backing only if the same line turns into buyer value, e.g. `backed by [X] to help [buyer segment] [buyer outcome]`; otherwise cut the PS
 
 **Motion alignment**
 
@@ -453,17 +454,17 @@ Tell #8 hardcoded signoff, Tell #10 vague-proof) overlap with
 Filters 3 and 6. This is intentional — the catalog is the canonical
 enumeration; Filter 8 is the catalog-driven check. Filters 3 and 6
 remain as human-readable explanations of specific high-priority
-tell classes, but the actual detection logic in Phase-84 reads from
+tell classes, but the actual detection logic in offline validation reads from
 `ai-tells.md`.
 
 **Adding new tells.** When UAT surfaces a new AI-tell pattern, add
 it as `Tell #N` in `ai-tells.md` with Pattern / Why / Allowed
-alternative / Severity. The next Phase-84 run picks it up
+alternative / Severity. The next offline validation run picks it up
 automatically. Update
 `tests/scripts/skill-references-substance-filters.test.ts` if the
 new tell needs regression coverage.
 
-**Example of a violation** (Plan 05 Patientdesk winner, pre-catalog —
+**Example of a violation** (Patientdesk regression example, pre-catalog —
 Tell #1 body-level self-introduction):
 
 > "Hey Bonnie — Oncel here. My co-founders and I ran our own dental
@@ -519,7 +520,7 @@ Do not patch a weak message by inventing stronger personalization.
 
 ## Dry-Mode Discipline
 
-Phase 84 dry mode is validation, not production drafting.
+Offline dry mode is validation, not production drafting.
 
 - use only `brief.md`, `lead-filter.md`, and `lead-sample.json`
 - do not fetch new research
@@ -530,19 +531,18 @@ Phase 84 dry mode is validation, not production drafting.
 - retrieve broadly, but preserve one primary example and borrow from at most one
   narrow secondary influence
 
-## Plan 85-03 Critique Addendum
+## Critique Rewrite Addendum
 
 These filters are also the gate on any critique rewrite shipped by the
-Plan 85-03 parallel critique protocol (see
-`references/parallel-critique-protocol.md`). When the critique flag is
-on, a rewritten message must still clear:
+parallel critique protocol (see `references/parallel-critique-protocol.md`).
+When the critique flag is on, a rewritten message must still clear:
 
 - every "Automatic Revisions" check above (jargon, resume-list PS, stacked
   sentences, weak hooks, etc.)
-- the Phase 84 token contract: only supported tokens from the brief, no
+- the offline-validation token contract: only supported tokens from the brief, no
   unresolved `{{token}}`, no invented proof, no personalization that can't
   be traced to `lead-sample.json`
-- the Phase 84 finalizer pass when `synthesis.enforceFinalizerPass` is
+- the offline-validation finalizer pass when `synthesis.enforceFinalizerPass` is
   `true` (default)
 
 If a rewrite fails any of these, the critique pass falls back to the

package/skills/create-campaign-v2/references/step-15-re-cascade.md

@@ -63,7 +63,7 @@ rows graduated.
      })
 
 5. re-check token contract on the cascaded subset (strict mode default)
-   — see references/thomas-revision-filters.md + gold-standard-message-patterns.md
+   — see references/sellable-cleanup-rules.md + gold-standard-message-patterns.md
 
 6. go back to step 1 until selectedCellCount == 0
 ```

package/skills/create-campaign-v2/references/thomas-variant-selection.md

@@ -1,6 +1,6 @@
 # Thomas Variant Selection
 
-This reference governs which rows in a Plan 85-03 critique sample earn
+This reference governs which rows in a critique sample earn
 an Opus refinement rewrite. Load this file only when
 `messaging.critique.enabled === true` AND
 `messaging.critique.opus.enabled === true` in

package/skills/create-campaign-v2/references/validation-criteria.md

@@ -1,8 +1,8 @@
 # Validation Criteria
 
-Phase 84 is a chained-artifact validation pass over the Phase 83 brief. The
-goal is to preserve the brief thesis while proving that leads, filters, and
-message direction hold up against real preview evidence.
+Offline validation is a chained-artifact validation pass over the approved
+campaign brief. The goal is to preserve the brief thesis while proving that
+leads, filters, and message direction hold up against real preview evidence.
 
 ## Primary Contract
 
@@ -10,7 +10,7 @@ message direction hold up against real preview evidence.
 - validation/debug artifacts are optional debug/UAT diagnostics, not durable campaign state.
 - normal customer runs should not expose local draft files.
 - resume and handoff read campaign state before debug files.
-- `CampaignOffer.campaignBrief` is the durable Phase 83 thesis input;
+- `CampaignOffer.campaignBrief` is the durable campaign thesis input;
   `brief.md` is its debug copy
 - `lead-review.md` and `lead-sample.json` are the required outputs of lead preview
 - `lead-filter.md` is the primary output of the middle step
@@ -28,7 +28,7 @@ Allowed:
 
 Not allowed:
 
-- rewrite the Phase 83 thesis in `brief.md`
+- rewrite the approved campaign thesis in `brief.md`
 - create `lead-filter.md`
 - create `message-validation.md`
 - mutate campaign state
@@ -87,13 +87,12 @@ Required:
   the brief justifies absence with reference to a specific archived winner.
   If a candidate uses `two options:`, option `a)` and option `b)` must be
   separated by a blank line so the CTA scans cleanly on mobile.
-- **All 5 Substance Filters from `thomas-revision-filters.md` MUST
-  PASS per candidate.** A candidate that fails any substance filter
-  (Earned-right, Presumption, Vague-proof, Read-as-1:1, Founder-origin
-  coherence) is BLOCKED. The Finalizer Pass CANNOT select a blocked
-  candidate. If all 3 candidates fail, route to `revise-message` with
-  the failure reasons enumerated per candidate (cite the filter name and
-  the offending line).
+- **All Sellable cleanup rules, including all 8 substance filters from
+  `sellable-cleanup-rules.md`, MUST PASS per candidate.** A candidate that fails
+  any cleanup rule or substance filter is BLOCKED. The Finalizer Pass CANNOT
+  select a blocked candidate. If all 3 candidates fail, route to
+  `revise-message` with the failure reasons enumerated per candidate (cite the
+  rule/filter name and the offending line).
 
 ## Lead Preview Expectations
 
@@ -254,7 +253,7 @@ The sample set must:
 - contain no invented proof, metrics, logos, or customer names
 - keep proof claims inside the brief's safe-claims boundary
 - reject personalization that cannot be traced back to `lead-sample.json`
-- apply Thomas revision filters before the step is marked `confirmed`
+- apply Sellable cleanup rules before the step is marked `confirmed`
 - choose the highest-specificity validated strategy available in this order:
   event-led, signal-led, job-post-led, then proof-led specialist fallback
 - retrieve against the full archived gold-standard library and choose a
@@ -328,6 +327,10 @@ that does Y` anchor sentence before any action breakdown, then one action
   with no anchor. Use "I" voice if the sender is the founder; "our CEO",
   "our team", or "we" otherwise. At most two proof beats. No three-credential
   resume lists
+- reject backing PS lines that describe the seller's focus instead of the
+  buyer's outcome, such as `backed by [X] and focused on [category/problem]`.
+  Backing proof only survives when the same line translates to buyer value,
+  e.g. `backed by [X] to help [buyer segment] [buyer outcome]`
 - samples in one set must read like siblings from one campaign, not three
   experiments
 - reject fallback drafts that lead with generic "most teams..." copy without a

package/skills/create-campaign-v2-tail/SKILL.md

@@ -379,7 +379,7 @@ templateRevision: "current" })` until the first current-revision generated
    Generate Message cell, and do not add "one more wait" for a stronger sample.
    Remaining review/process sample rows can continue processing in the background.
 4. Read the first ready generated message back via `get_rows` (full) and
-   sanity-check that sample against the Phase 84 token contract: no unresolved
+   sanity-check that sample against the offline-validation token contract: no unresolved
    `{{tokens}}`, no invented proof, one sentence per line, etc.
 5. If the sample fails the token contract, diagnose brief-vs-list
    (same revision loop as Step 14) and escalate if over
@@ -403,17 +403,17 @@ strings, which is why Step 16 requires Step 15 to be complete.
 
 1. Observe the review-sample messages on the same sample that passed
    validation.
-2. If `messaging.critique.enabled` is true (Plan 85-03), run the
+2. If `messaging.critique.enabled` is true, run the
    bounded critique pass on the sample output per
    `references/parallel-critique-protocol.md`. The pass runs on at
    most `messaging.critique.sampleSize` rows, sends each row through
    three parallel critics (targeting / copy / voice) that return
    structured JSON, and merges the voices in a synthesis step that
-   enforces the Phase 84 token contract verbatim and re-runs the
+   enforces the offline-validation token contract verbatim and re-runs the
    finalizer pass. Any rewrite that invents proof or uses an
    unsupported token falls back to the plain generated message. A
    trip of `messaging.critique.budgetUsdCap` HALTS critique for the
-   remaining sample and continues the plain tail. Plan 85-02 reads
+   remaining sample and continues the plain tail. The plain campaign tail reads
    the flag but never flips it; critique stays off until the flag is
    deliberately enabled.
 3. If `messaging.critique.opus.enabled` is also true, route the
@@ -512,7 +512,7 @@ calling any mutating tool; if the campaign is already running, skip
 approve-batch / start_campaign / update_campaign and just confirm.
 
 Workspace/sender mismatch at greenlight time aborts the start with the
-same invariant Phase 84 enforces.
+same invariant offline validation enforces.
 
 ## Threshold Trips and Logging
 
@@ -546,7 +546,7 @@ runs.
 
 | File                                             | Load when                                                                 |
 | ------------------------------------------------ | ------------------------------------------------------------------------- |
-| `references/approval-gate-framing.md`            | Phase 85 commit gate, before showing the approval packet                  |
+| `references/approval-gate-framing.md`            | Approval gate, before showing the approval packet                         |
 | `references/watch-link-handoff.md`               | First brief handoff + explicit link recovery only                         |
 | `references/post-mint-source-materialization.md` | Step 13, before importing normal-discovery or legacy campaignless sources |
 | `references/sample-validation-loop.md`           | Step 14, before enriching + scoring the sample                            |
@@ -554,7 +554,7 @@ runs.
 | `references/final-handoff-contract.md`           | Step 16, and every Claude greenlight turn                                 |
 | `references/parallel-critique-protocol.md`       | Step 15 when `messaging.critique.enabled` is true                         |
 | `references/thomas-variant-selection.md`         | Step 15 when `messaging.critique.opus.enabled` is true                    |
-| `references/thomas-revision-filters.md`          | Any critique rewrite, before persisting                                   |
+| `references/sellable-cleanup-rules.md`          | Any critique rewrite, before persisting                                   |
 | `core/auto-execute.yaml`                         | Start of Step 13, load once; all tail steps read parsed values            |
 | `core/auto-execute.README.md`                    | When tuning `auto-execute.yaml` knobs or reviewing threshold-trip logs    |
 

package/skills/create-campaign-v2-validation/SKILL.md

@@ -1,14 +1,14 @@
 ---
 name: create-campaign-v2-validation
-description: Validate a Phase 83 `brief.md` through chained Phase 84 artifacts before any live campaign state exists.
+description: Validate an approved `brief.md` through chained offline artifacts before any live campaign state exists.
 visibility: internal
 ---
 
 # Create Campaign v2 Validation
 
 <role>
-You are the Phase 84 validation orchestrator for create-campaign-v2. Your job
-is to validate a Phase 83 `brief.md` through chained draft artifacts without
+You are the offline validation orchestrator for create-campaign-v2. Your job
+is to validate an approved `brief.md` through chained draft artifacts without
 creating live campaign state.
 </role>
 
@@ -41,7 +41,7 @@ Validated draft directory:
 
 <rules>
 
-- `brief.md` is the stable Phase 83 input and remains the thesis source.
+- `brief.md` is the stable approved input and remains the thesis source.
 - `lead-review.md` and `lead-sample.json` are the required outputs of `find leads`.
 - `lead-filter.md` is the primary output of `filter leads`.
 - `rubric.json` is optional and secondary to `lead-filter.md`.
@@ -49,7 +49,7 @@ Validated draft directory:
 - Run validation serially in this order: `find leads`, `filter leads`, `generate message`.
 - Resume state is based on the presence and completeness of the chained artifacts,
   not on inline validation blocks inside `brief.md`.
-- Preserve the Phase 83 thesis. Do not rewrite product, ICP, offer, or message
+- Preserve the approved thesis. Do not rewrite product, ICP, offer, or message
   hypothesis sections during preview validation.
 - Every artifact write uses `tmp + rename` so a failed write leaves the prior
   artifact intact.
@@ -222,7 +222,7 @@ Orchestration requirements:
   same company as the brief
 - draft 3 internal candidates and run a Finalizer Pass that combines the
   best opener, proof sentence, bridge, and CTA across them into one winner
-- pass the Thomas revision filters before writing findings
+- pass the Sellable cleanup rules before writing findings
 - pass the source-transition gate before writing findings. For sender-owned
   LinkedIn post sources where the sample proves a reaction/comment, a light
   first-person acknowledgment is allowed (`appreciate you showing some love on