Menu
Defines the AE's personal communication voice, email formatting, vocabulary substitutions, and the 7-point voice check
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Fires on any operation that reads or writes deal, company, contact, call note, or task data. Provides: file schemas, write protocol (entity + index + cross-references + ops.log), account name resolution (fuzzy matching), read-time validation, duplicate detection rules. Output contract: every data write follows the standard protocol and produces a FILES UPDATED block.
Fires when a user asks about deal strategy, how to approach a stalled deal, or needs a business case. Produces: Five-Lens Prism analysis (stakeholder psychology, political capital, competitive dynamics, hidden leverage, temporal dynamics), Three Paths recommendation (velocity/diagnostic/protective), 5-Component POV model. Output contract: three distinct strategic options with evidence grading, never a single recommendation.
Fires on meeting prep, outreach, research, deck creation, and business case building. Provides: company overview, product portfolio, market position, differentiators, pricing context, case studies by vertical, key selling metrics, voice & language patterns, pain signal mapping, and prism insights. Output contract: company-specific context that makes outputs relevant to the prospect's actual situation. When a Platform Document exists (from /research), loads enriched voice, pain, and strategic intelligence.
Fires when a competitor is mentioned, a competitive situation arises, or the user asks how to beat/displace/win against a specific vendor. Produces: per-competitor displacement playbook with strengths, weaknesses, talk tracks, proof points, trap questions, and landmine responses. Triggers on: handle-competition, think-about-deal (competitive lens), battle analysis.
Fires on any written output — emails, outreach, LinkedIn posts, business cases, follow-ups. Provides: voice rules, email formatting, vocabulary substitutions, banned phrases, sign-off, and 7-point voice check. Output contract: all written content matches the user's calibrated tone and style.
Fires when a call transcript is pasted or the user says they finished a call. Produces: 6 structured outputs — MEDDPICC scoring with evidence, task extraction with owners and dates, coaching feedback on 5 dimensions, follow-up email in 3 tones, risk signals with mitigation actions, competitive intel. Output contract: every output is actionable, not just analytical.
| name | brand-voice |
| description | Defines the AE's personal communication voice, email formatting, vocabulary substitutions, and the 7-point voice check |
| tier | 3 (regenerated) |
| auto-fire | Any communication output — /email, /outreach, /draft-post, /closeout (follow-up email) |
| user-invocable | false |
Tier 3 — This entire file is regenerated during /setup Phase 4 based on the AE's communication preferences and writing samples.
Defines the AE's personal communication voice for all written outputs. Contains voice rules, email formatting standards, vocabulary substitutions, banned phrases, and the 7-point voice check. Ensures every email, outreach, LinkedIn post, and follow-up sounds like the AE — not like generic AI.
Communication style: {{COMMUNICATION_STYLE}}
Default voice (pre-/setup):
After /setup, these rules are rewritten based on the AE's actual communication preferences and writing samples.
| Rule | Standard |
|---|---|
| Subject lines | Lowercase unless proper nouns. Under 6 words. Specific, not clickbait. |
| Length | Under 200 words. If it's longer, it should be a document, not an email. |
| Structure | Context (1 sentence) → Purpose (1-2 sentences) → Ask (1 sentence) |
| Sign-off | {{EMAIL_SIGN_OFF}} |
| Tone | Varies by recipient — see Tone Matching below |
| CTA | One clear call-to-action per email. Never more than one. |
Match communication tone to the recipient's role and relationship:
| Audience | Tone | Example |
|---|---|---|
| Champion | Warm, collaborative, insider language | "Hey Sarah — quick update on the POC timeline..." |
| Economic Buyer | Professional, business-outcome focused | "Following up on our conversation about the projected ROI..." |
| Technical Evaluator | Concise, specific, data-driven | "Here are the integration specs you requested..." |
| New Contact | Respectful, value-first, no assumptions | "Reaching out because I noticed [specific observation]..." |
| Internal (manager) | Structured, metrics-focused, brief | "Pipeline update: 3 deals moved this week..." |
After /setup, this section contains the AE's specific vocabulary preferences.
Default substitutions (pre-/setup):
| Instead of | Use |
|---|---|
| "Reach out" | "Contact" or "get in touch" |
| "Circle back" | "Follow up" or "revisit" |
| "Touch base" | "Connect" or "check in" |
| "Synergy" | [delete — don't replace, just remove] |
| "Leverage" | "Use" or "apply" |
| "Bandwidth" | "Capacity" or "time" |
| "Deep dive" | "Detailed review" or "analysis" |
| "Ping" | "Message" or "email" |
| "Loop in" | "Include" or "add" |
| "Take offline" | "Discuss separately" |
| "Ideate" | "Brainstorm" or "think through" |
| "Socialize" | "Share" or "discuss" |
These phrases are NEVER used in any communication, regardless of context:
Default banned list (pre-/setup):
After /setup, this list is customized with the AE's personal banned phrases and may add phrases they never want AI to generate.
Run this check on every communication output before presenting:
| # | Check | Question |
|---|---|---|
| 1 | Authenticity | Does this sound like {{AE_NAME}} wrote it, or like a robot? |
| 2 | Vocabulary | Are all vocabulary substitutions applied? No banned phrases? |
| 3 | Length | Is the email under 200 words? Is the LinkedIn post 150-300 words? |
| 4 | Structure | One clear purpose? One clear CTA? |
| 5 | Tone match | Is the tone appropriate for the recipient and relationship? |
| 6 | Sign-off | Using {{EMAIL_SIGN_OFF}} (or appropriate LinkedIn close)? |
| 7 | Filler check | Zero filler phrases? No "I hope," "just wanted to," "I'd love to"? |
Passing score: 7/7 for emails and outreach. 5/7 acceptable for LinkedIn posts (length and sign-off rules differ).
LinkedIn voice differs from email voice:
On the first run of /outreach, the user is asked for their typical email tone and optionally provides a sample email. The calibration response is stored here as supplemental voice data:
This supplements the /setup voice profile. If /outreach runs before /setup, calibration data is stored here and merged into the full voice profile when /setup completes.
