@sellable/mcp 0.1.203 → 0.1.205

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (33) hide show
  1. package/README.md +7 -7
  2. package/agents/post-find-leads-message-scout.md +16 -4
  3. package/dist/engage-memory.js +0 -5
  4. package/dist/identity-memory.js +0 -4
  5. package/dist/tools/engage-memory.js +2 -2
  6. package/dist/tools/prompts.js +3 -2
  7. package/package.json +1 -1
  8. package/skills/create-campaign/context/learnings.md +1 -1
  9. package/skills/create-campaign/references/brief-template.md +2 -2
  10. package/skills/create-campaign-brief/references/brief-template.md +2 -2
  11. package/skills/create-campaign-brief/references/draft-lifecycle.md +1 -1
  12. package/skills/create-campaign-brief/references/examples/briefs/gelee.md +2 -2
  13. package/skills/create-campaign-brief/references/examples/briefs/superpower.md +41 -28
  14. package/skills/create-campaign-brief/references/phase75-active-runtime-message-pack.md +12 -9
  15. package/skills/create-campaign-v2/references/ai-tells.md +35 -10
  16. package/skills/create-campaign-v2/references/approval-gate-framing.md +1 -1
  17. package/skills/create-campaign-v2/references/gold-standard-message-examples.md +30 -16
  18. package/skills/create-campaign-v2/references/gold-standard-message-patterns.md +1 -1
  19. package/skills/create-campaign-v2/references/gold-standard-runtime-message-pack.md +252 -0
  20. package/skills/create-campaign-v2/references/thomas-revision-filters.md +12 -3
  21. package/skills/create-campaign-v2/references/validation-criteria.md +8 -5
  22. package/skills/create-campaign-v2-validation/SKILL.md +1 -1
  23. package/skills/create-post/SKILL.md +27 -27
  24. package/skills/engage/SKILL.md +12 -12
  25. package/skills/engage/core/README.md +14 -14
  26. package/skills/find-leads/SKILL.md +1 -1
  27. package/skills/generate-messages/SKILL.md +171 -71
  28. package/skills/interview/SKILL.md +24 -24
  29. package/skills/interview/references/legacy-linkedin-interview.md +12 -12
  30. package/skills/interview/references/reference-curation.md +4 -4
  31. package/skills/interview/references/voice-capture-method.md +1 -1
  32. package/skills/load-voice/SKILL.md +21 -25
  33. package/skills/research/SKILL.md +1 -1
package/skills/load-voice/SKILL.md CHANGED
@@ -16,8 +16,8 @@ Sellable voice/company memory into the current thread before drafting,
16
16
  answering, rewriting, reviewing, or calibrating copy in the user's voice.
17
17
 
18
18
  This is a read-only usage workflow. Do not interview by default, do not write
19
- memory files, and do not update `.sellable/**` unless the user explicitly asks
20
- to switch into `$sellable:interview`.
19
+ memory files, and do not update `~/.sellable/**` unless the user explicitly
20
+ asks to switch into `$sellable:interview`.
21
21
  </role>
22
22
 
23
23
  <default_use_cases>
@@ -32,56 +32,52 @@ Use this workflow when the user asks to:
32
32
  </default_use_cases>
33
33
 
34
34
  <load_order>
35
- Read only relevant files. Start with the active `.sellable/configs` memory
36
- layer, not random repo docs.
37
-
38
- If `.sellable/configs` is not visible from the current working directory, use
39
- `Glob` to find `**/.sellable/configs/core/my-company.md`, excluding
40
- `node_modules`, `.next`, `dist`, and `.git`, then use the nearest parent as the
41
- Sellable memory root.
35
+ Read only relevant files. Start with the active home-level
36
+ `~/.sellable/configs` memory layer, not random repo docs or repo-local
37
+ `~/.sellable` folders.
42
38
 
43
39
  ## Core Voice And Judgment
44
40
 
45
41
  Read these when present:
46
42
 
47
- - `.sellable/configs/core/about-me.md`
48
- - `.sellable/configs/core/anti-ai-writing-style.md`
49
- - `.sellable/configs/core/decision-rules.md`
50
- - `.sellable/configs/core/context-modes.md`
43
+ - `~/.sellable/configs/core/about-me.md`
44
+ - `~/.sellable/configs/core/anti-ai-writing-style.md`
45
+ - `~/.sellable/configs/core/decision-rules.md`
46
+ - `~/.sellable/configs/core/context-modes.md`
51
47
 
52
48
  ## Company Truth And Proof
53
49
 
54
50
  Read these when present:
55
51
 
56
- - `.sellable/configs/core/my-company.md`
57
- - `.sellable/configs/core/answer-bank.md`
58
- - `.sellable/configs/core/proof-ledger.md`
59
- - `.sellable/configs/core/story-bank.md`
60
- - `.sellable/configs/core/wins-ledger.md`
52
+ - `~/.sellable/configs/core/my-company.md`
53
+ - `~/.sellable/configs/core/answer-bank.md`
54
+ - `~/.sellable/configs/core/proof-ledger.md`
55
+ - `~/.sellable/configs/core/story-bank.md`
56
+ - `~/.sellable/configs/core/wins-ledger.md`
61
57
 
62
58
  ## Writing-Specific Guidance
63
59
 
64
60
  Read these when present and relevant to the task:
65
61
 
66
- - `.sellable/configs/writing/styleguide-core.md`
67
- - `.sellable/configs/writing/comments.md`
62
+ - `~/.sellable/configs/writing/styleguide-core.md`
63
+ - `~/.sellable/configs/writing/comments.md`
68
64
 
69
65
  ## Transcript Or Topic Context
70
66
 
71
67
  Do not bulk-read raw transcripts. If the user asks about a specific topic,
72
68
  story, sales call, customer, market view, or correction, first read:
73
69
 
74
- - `.sellable/configs/core/transcripts/INDEX.md`
75
- - the most relevant file under `.sellable/configs/core/transcripts/topics/`
70
+ - `~/.sellable/configs/core/transcripts/INDEX.md`
71
+ - the most relevant file under `~/.sellable/configs/core/transcripts/topics/`
76
72
 
77
- Only read raw archives under `.sellable/interviews/**` when the index/topic file
78
- points to one and the current task needs that source detail.
73
+ Only read raw archives under `~/.sellable/interviews/**` when the index/topic
74
+ file points to one and the current task needs that source detail.
79
75
  </load_order>
80
76
 
81
77
  <operating_rules>
82
78
 
83
79
  - Keep the loader lightweight. The first pass should usually be 6-10 files, not
84
- every file under `.sellable`.
80
+ every file under `~/.sellable`.
85
81
  - Apply the loaded profile silently after a short confirmation. Do not paste a
86
82
  long summary of the memory unless the user asks for one.
87
83
  - If the user already gave a concrete writing task, load the memory and then do
package/skills/research/SKILL.md CHANGED
@@ -219,7 +219,7 @@ After all agents return, combine into a short Research Notes block. **Strip DEBU
219
219
 
220
220
  **If researchMode="prospect":**
221
221
 
222
- If the caller passed cross-skill insights (from `.sellable/insights/cross-skill.md`), use them to prioritize hooks — e.g., if engage sessions show "AI compute time" angles get high engagement, rank those hooks higher.
222
+ If the caller passed cross-skill insights (from `~/.sellable/insights/cross-skill.md`), use them to prioritize hooks — e.g., if engage sessions show "AI compute time" angles get high engagement, rank those hooks higher.
223
223
 
224
224
  ```markdown
225
225
  ## {Name} - {Title} at {Company}