Compose Outreach

1---2name: compose-outreach3description: "Generate personalized outreach messages using Common Room signals. Triggers on 'draft outreach to [person]', 'write an email to [name]', 'compose a message for [contact]', or any outreach drafting request."4---5 6# Compose Outreach7 8Generate three personalized outreach formats — email, call script, and LinkedIn message — grounded in Common Room signals for a specific company or contact.9 10## Outreach Process11 12### Step 1: Look Up the Target13 14Use Common Room MCP tools to find and retrieve data for the target (company and/or specific contact). Pull:15- Recent product activity and engagement signals16- Community activity (posts, questions, reactions)17- 3rd-party intent signals (job postings, news, funding)18- Relationship history (prior contact, meetings, email opens)19 20If the user specified a person, run contact-level research. If only a company was given, identify the best contact to target based on title, engagement, and role.21 22### Step 2: Web Search for External Hooks (If CR Signals Are Thin)23 24If CR returned strong signals (recent activity, engagement, product usage), those should drive personalization — skip web search. If CR signals are thin or the prospect has little CR activity, run a web search for external hooks:25 26**What to search:**27- `"[company name]" funding OR acquisition OR launch OR announcement` — last 30 days28- `"[contact full name]" "[company name]"` — look for recent articles, interviews, LinkedIn posts, or conference talks29 30**Prioritize external hooks that are:**31- Very recent (< 2 weeks) — the prospect is likely still thinking about it32- Publicly visible — they know you could have seen it33- Change-signaling — growth, new role, new product, new market34 35If the user explicitly asks for web search or external hooks, run it regardless of CR signal richness.36 37### Step 3: Spark Enrichment (If Available)38 39If Spark is available, run enrichment on the target contact to get persona classification, background, and influence signals. Use this to calibrate tone and message angle.40 41### Step 4: Identify the Best Hooks42 43From the signal data, identify the 1–3 strongest personalization hooks. Rank by:441. **Recency** — happened in the last 7–14 days452. **Specificity** — a concrete action they took, not a general trend463. **Relevance** — connects directly to a value your product delivers47 48Good hooks: posted a question in the community about X, just hired 5 engineers, recently started using [feature], company just raised Series B, trial nearing expiration, champion just changed jobs.49 50Bad hooks: "I noticed you're a customer" or generic industry trends.51 52### Step 5: Generate All Three Formats53 54Use the strongest hooks to write all three formats. Each format has different constraints and conventions — follow the format-specific guidelines in `references/outreach-formats-guide.md`.55 56Always produce all three, clearly labeled.57 58When the user's company context is available (see `references/my-company-context.md`), ground the value bridge and pitch in the user's specific product and positioning.59 60### Step 6: Annotate Your Choices61 62After the three drafts, include a brief note (2–4 sentences) explaining:63- Which signals were used and why they were chosen64- Any assumptions made (e.g., inferred call objective)65- Alternative angles if the primary hook doesn't land66 67## Output Format68 69```70## Outreach for [Name / Company]71 72### 📧 Email73 74**Subject:** [Subject line]75 76[Email body — 3–5 sentences]77 78---79 80### 📞 Call Script81 82**Opening:**83[Opening line — conversational, 1–2 sentences]84 85**Value Bridge:**86[Why you're calling and why now — 2–3 sentences tied to a signal]87 88**Ask:**89[Single, low-friction ask — e.g., 15-minute call, specific question]90 91---92 93### 💼 LinkedIn Message94 95[Under 300 characters. Warm, personal, no pitch.]96 97---98 99### Signal Notes100[2–4 sentences: which signals were used, why, and any alternative angles]101```102 103## When Signal Data Is Sparse104 105If Common Room returns minimal data on the target (e.g., just name, title, tags — no activity, no scores, no Spark):106 1071. **Do not draft outreach from thin air.** Outreach grounded in fabricated signals is worse than no outreach.1082. **Run web search first** — this becomes your primary personalization source. Look for recent news, LinkedIn posts, conference talks, company announcements.1093. **If web search also returns little**, present what you have honestly and ask the user for context:110 111```112## Outreach for [Name / Company] — Limited Data113 114**What I found:**115[Only the real data from CR and web search]116 117**I don't have enough signal to draft personalized outreach yet.** To write something strong, I'd need:118- Recent activity or engagement signals119- Context you have from prior conversations120- A specific reason for reaching out now121 122Can you share any of the above?123```124 125## Quality Standards126 127- Every message must reference something specific — generic outreach is not acceptable output128- Match tone to context: warm and conversational for inbound/community signals; more formal for cold/executive outreach129- The LinkedIn message must be under 300 characters — no exceptions130- The call script must be speakable naturally — read it aloud mentally to check rhythm131- **Never fabricate signals** — only reference data retrieved from Common Room or web search132 133## Reference Files134 135- **`references/outreach-formats-guide.md`** — detailed format rules, examples, and tone guidelines for each channel