@sellable/mcp 0.1.18 → 0.1.20

package/README.md

@@ -83,14 +83,14 @@ The token is provided when you generate it. Use `list_workspaces` +
 For customer/package installs, use the public installer:
 
 ```bash
-npx -y @sellable/install@0.1.18 --host codex --token skt_live_your_token_here --workspace-id your_workspace_id
+npx -y @sellable/install@0.1.20 --host codex --token skt_live_your_token_here --workspace-id your_workspace_id
 ```
 
 If you already have `~/.sellable/config.json`, rerun/verify without rewriting
 auth:
 
 ```bash
-npx -y @sellable/install@0.1.18 --host codex
+npx -y @sellable/install@0.1.20 --host codex
 sellable --verify-only --host codex
 ```
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/mcp",
-  "version": "0.1.18",
+  "version": "0.1.20",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",

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

@@ -120,6 +120,12 @@ Validated draft directory:
   or safe launch. Do not say "persist", "local draft folder", "artifact",
   "mkdir", "campaign thesis", or "same approved campaign thesis" in
   customer-facing progress copy.
+- Every approval gate must include artifact access after the readable inline
+  content. Show a short `Open artifacts:` line with clickable markdown links
+  using absolute paths when the host supports them, plus the plain path for CLI
+  users. Do this for brief approval, lead-source approval/review, message review,
+  and final approval packet. Do not use the links as a substitute for rendering
+  the content inline; links are for deeper inspection.
 - Do not treat the active Sellable workspace as the campaign subject. The
   workspace only tells you where the campaign will be saved. Before buyer, CTA,
   proof, or source questions, identify two things:
@@ -319,6 +325,9 @@ me`, `I’ll paste a different sender profile`, and `Other / custom`.
   user-facing choice should be approve/revise language, not "looks good".
   Approval options should refer to what the user just read, e.g. `Approve this
   brief`, `Revise target`, `Revise offer/proof`, and `Other / custom`.
+  Include `Open artifacts:` links to `brief-v1.md` and `brief.md` before the
+  approval question.
+
 - After the brief is approved or auto-confirmed, show the next progress line:
   `Cool. Now I'm going to find people who are both a good fit and likely to
 reply on LinkedIn. I'll compare source paths by expected volume, likely
@@ -517,6 +526,17 @@ Required behavior:
   keyword lanes; it does not mean 492 prospects. The source decision must name
   the actual posts we would use, show why they won, and estimate usable engagers
   from those posts after headline/sample filtering
+- user-facing source logic must use numbers, not vibes. Never write a percentage
+  such as `73% match` without the numerator, denominator, and sample basis, e.g.
+  `8 of 11 sampled engagers fit the ICP (73%)`. If the sample is small, say it is
+  directional. If an estimate depends on assumptions, show the math: `5 selected
+posts x ~40-80 reachable engagers/post x 25-40% expected fit = ~50-160 likely
+usable leads`.
+- source progress updates should expose the confidence-building numbers as soon
+  as they exist: keyword lanes searched, timeframe used, post results by lane,
+  finalist posts reviewed, engagers fetched, sampled engagers, sampled fits,
+  estimated usable leads, and what is still unknown. Do not wait until the final
+  approval packet to show those numbers.
 - Signals source decisions should prefer fresh posts. Default to posts from the
   last 30 days, prefer the last 7-14 days when quality is comparable, and call
   out any older post as a deliberate tradeoff. Do not hide post age inside the
@@ -545,12 +565,14 @@ Required behavior:
 - validation status: `confirmed`, `rejected`, or `unclear`
 - confidence
 - provider path used
+- search lanes tested, with keyword/filter names and the timeframe used
+- post/result counts by lane for discovery sources
 - supplied source type when applicable (`normal-discovery`,
   `supplied-linkedin-profiles`, `supplied-domains`, or `existing-lead-list`)
 - row/domain counts, invalid counts, duplicate counts, and sample method for
   supplied sources
 - preview count
-- ICP match rate
+- ICP match rate with numerator/denominator and sample basis; never percent-only
 - volume comparison
 - expected LinkedIn funnel: likely connection acceptance range, likely reply
   range, and whether the estimate is sample-backed, historical, founder-supplied,
@@ -560,6 +582,11 @@ Required behavior:
   sampled engager count per selected post, sampled fit count per selected post,
   estimated usable engagers per selected post, and why each selected post is
   better than discarded posts
+- for Signals-first paths: total raw post results by lane, number of finalist
+  posts reviewed, number of selected posts, total engagers fetched, deduped
+  sampled people count, sampled fit count, and the estimated likely usable people
+  range. Explicitly distinguish `posts found`, `engagers sampled`, and `usable
+people estimated`.
 - source decision: best path, why it won, pros, cons/tradeoffs, and discarded
   source paths with the reason each lost
 - repeated false-positive patterns
@@ -571,6 +598,7 @@ For normal LinkedIn discovery, `lead-review.md` must include these
 customer-visible sections with literal headings:
 
 - `## Source Decision`
+- `## Evidence Snapshot`
 - `## Selected Signal Posts` for Signals-first campaigns
 - `## Expected LinkedIn Funnel`
 - `## Sample Leads` for Signals-first campaigns
@@ -591,6 +619,17 @@ table with one row per selected or finalist post:
 - estimated usable leads
 - why use / why discard
 
+`## Evidence Snapshot` must include a compact numbers-first table:
+
+- source lane / keyword or filter
+- timeframe searched
+- raw results found
+- finalist posts or preview rows reviewed
+- sampled people
+- sampled fits, shown as `n/N (%)`
+- estimated usable people
+- confidence note (`sample-backed`, `directional`, or `needs more sample`)
+
 For Signals-first campaigns, `## Sample Leads` must group representative sample
 rows by source post when possible, so the user can see not just that the search
 found posts, but which posts produce believable prospects.
@@ -602,10 +641,12 @@ directional range and label it `directional`, not definitive.
 
 When showing `lead-review.md` to the user, render the customer-visible sections
 inline. Do not compress it to a short summary or artifact links only. The
-visible response must include `## Source Decision`, `## Expected LinkedIn
-Funnel`, `## Pros`, `## Tradeoffs`, and `## Discarded Paths`. For
-Signals-first campaigns it must also include `## Selected Signal Posts` and
-`## Sample Leads`.
+visible response must include `## Source Decision`, `## Evidence Snapshot`,
+`## Expected LinkedIn Funnel`, `## Pros`, `## Tradeoffs`, and `## Discarded
+Paths`. For Signals-first campaigns it must also include `## Selected Signal
+Posts` and `## Sample Leads`.
+Include `Open artifacts:` links to `lead-review.md` and `lead-sample.json`
+before moving to filter/message drafting or asking for any source revision.
 
 For supplied profile CSVs and existing lead lists, `lead-review.md` must not
 describe a generic TAM estimate or pretend the rows came from Sales Nav/Prospeo
@@ -829,6 +870,16 @@ Orchestration requirements:
   `My take: ...`, `Suggested adjustment: ...`,
   `Question: approve-message or revise-messaging?`, `Recommendation:
 approve-message|revise-messaging`.
+- Never ask the message approval question until the full message review is
+  visible in the chat. A summary like `Message review is ready` or `the draft
+  avoids a generic pitch` is not enough. The user must see the actual subject,
+  the actual tokenized message template, at least one good filled example, one
+  good omit example, token notes, your take, and the suggested adjustment before
+  any `approve-message` / `revise-messaging` question appears. If you catch
+  yourself wanting to offer `show me message` as a choice, stop: render the
+  message review first, then ask only `approve-message` or `revise-messaging`.
+  Include `Open artifacts:` links to `message-review.md` and
+  `message-validation.md` before the approval question.
 - `My take:` and `Suggested adjustment:` are mandatory customer-facing decision
   fields, not optional summary text. They must appear after `Token notes:` and
   before the question in every rendered message review. They must each be
@@ -950,6 +1001,9 @@ proof:`, `p.s. useful proof:`, `p.s. proof:`, or `p.s. social proof:`.
   summarize the customer checkpoint from `message-review.md` and preserve the
   same literal `My take:`, `Suggested adjustment:`, and `Recommendation:`
   labels.
+  Include `Open artifacts:` links to `approval-packet.md`,
+  `message-review.md`, `lead-review.md`, and `brief.md` before the commit-gate
+  question.
 - if `message-validation.md` contains an extractable `Selected Winner`, use
   that exact winner as the `## Approved Message Template` in
   `approval-packet.md` and in the campaign brief passed to `create_campaign`.

package/skills/create-campaign-v2/SOUL.md

@@ -59,6 +59,15 @@ Approvals only feel safe when the user can see what they are approving. Before
 any approve/revise question, show the relevant decision in plain language. For a
 brief approval, render the brief itself, not just a direction summary.
 
+Every approval should also give the user a way to inspect the source artifact.
+After the readable inline content, include an `Open artifacts:` line with links
+or plain paths to the files behind the decision. The artifact links are a backup
+for inspection, not a replacement for showing the content in chat.
+
+This applies especially to message approvals. Never ask someone to approve a
+message they cannot see. Show the subject, message body/template, filled example,
+omit example, token notes, your take, and suggested adjustment first.
+
 ## Progress Updates
 
 Every customer-facing update should answer one of these:
@@ -79,6 +88,23 @@ Before a brief approval, the user should see:
 - risks / assumptions
 - what happens after approval
 
+For lead-source decisions, confidence comes from concrete counts. Do not say
+"strong sample", "73% match", or "meaningful concentration" without showing the
+sample size and what was counted. Prefer:
+
+```text
+I searched 4 signal lanes over the last 30 days. The best 5 posts produced 62
+sampled engagers; 31 looked like real ICP fits, so I’d treat this as directional
+50% sample fit, not a guaranteed audience. That gives us roughly 150-300 likely
+usable people if the remaining engagers behave similarly.
+```
+
+Avoid:
+
+```text
+The sample passed roughly 73% headline fit.
+```
+
 Good:
 
 ```text

package/skills/create-campaign-v2/core/flow.v2.json

@@ -227,6 +227,8 @@
             "then I will find good-fit leads"
           ],
           "minimumVisibleBriefDetail": "full_readable_brief_before_question",
+          "requiredArtifactLinks": ["brief-v1.md", "brief.md"],
+          "artifactLinkTiming": "before_approval_question",
           "avoidQuestionWhenOnlyUsefulAnswerIs": "looks good"
         },
         {
@@ -277,6 +279,10 @@
             "likely reply rate",
             "signal quality",
             "tradeoffs",
+            "search lanes",
+            "timeframe",
+            "sample size",
+            "estimated usable leads",
             "source decision + sample",
             "before anything goes live"
           ],
@@ -362,6 +368,7 @@
           "artifact": "lead-review.md",
           "renderInlineSections": [
             "## Source Decision",
+            "## Evidence Snapshot",
             "## Selected Signal Posts",
             "## Expected LinkedIn Funnel",
             "## Sample Leads",
@@ -377,9 +384,23 @@
             "engagement or estimated engagers",
             "sampled engagers",
             "sampled fits",
+            "sampled fits as n/N",
             "estimated usable leads",
             "why use or discard"
           ],
+          "evidenceSnapshotRequiredFields": [
+            "source lane or keyword",
+            "timeframe searched",
+            "raw results found",
+            "finalist posts or preview rows reviewed",
+            "sampled people",
+            "sampled fits as n/N (%)",
+            "estimated usable people",
+            "confidence note"
+          ],
+          "forbidPercentOnlyFitRates": true,
+          "requiredArtifactLinks": ["lead-review.md", "lead-sample.json"],
+          "artifactLinkTiming": "before_next_step_or_revision_question",
           "doNotCompressToSummaryOnly": true,
           "doNotRenderArtifactLinksOnly": true
         },
@@ -590,6 +611,13 @@
             "question",
             "recommendation"
           ],
+          "mustRenderInlineBeforeQuestion": true,
+          "minimumVisibleMessageDetail": "full_message_review_before_question",
+          "requiredArtifactLinks": [
+            "message-review.md",
+            "message-validation.md"
+          ],
+          "artifactLinkTiming": "before_approval_question",
           "requiredLabels": [
             "Subject:",
             "Message:",
@@ -627,6 +655,20 @@
         {
           "action": "ask_message_review_choice",
           "choices": ["approve-message", "revise-messaging"],
+          "questionPrerequisiteVisibleLabels": [
+            "Status: message-review",
+            "Subject:",
+            "Message:",
+            "Rendered examples:",
+            "Good token fill:",
+            "Good omit:",
+            "Token notes:",
+            "My take:",
+            "Suggested adjustment:",
+            "Recommendation:"
+          ],
+          "forbiddenWhenMissingVisibleMessage": true,
+          "doNotOfferShowMessageChoice": true,
           "stopAfterQuestion": true
         },
         {
@@ -709,6 +751,13 @@
             "messages",
             "risks and next action"
           ],
+          "requiredArtifactLinks": [
+            "approval-packet.md",
+            "message-review.md",
+            "lead-review.md",
+            "brief.md"
+          ],
+          "artifactLinkTiming": "before_commit_gate_question",
           "userFacing": true,
           "doNotUseWords": ["anchor", "validation anchor", "lane"]
         },
@@ -804,7 +853,14 @@
             "lead sample",
             "lead filter",
             "message validation"
-          ]
+          ],
+          "requiredArtifactLinks": [
+            "approval-packet.md",
+            "message-review.md",
+            "lead-review.md",
+            "brief.md"
+          ],
+          "artifactLinkTiming": "same_turn_before_commit_question"
         },
         {
           "action": "ask_commit_choice",