
Compose Outreach
- 2.2k installs
- 23.1k repo stars
- Updated July 28, 2026
- anthropics/knowledge-work-plugins
compose-outreach is an agent skill that Generate personalized outreach messages using Common Room signals. Triggers on 'draft outreach to [person]', 'write an e.
About
Generate three personalized outreach formats email call script and LinkedIn message grounded in Common Room signals for a specific company or contact Use Common Room MCP tools to find and retrieve data for the target company and or specific contact Pull Recent product activity and engagement signals Community activity posts questions reactions 3rd party intent signals job postings news funding Relationship history prior contact meetings email opens If 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 Step 2 Web Search for External Hooks If CR Signals Are Thin If 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
- description: "Generate personalized outreach messages using Common Room signals. Triggers on 'draft outreach to [person]
- Generate three personalized outreach formats — email, call script, and LinkedIn message — grounded in Common Room signal
- Use Common Room MCP tools to find and retrieve data for the target (company and/or specific contact). Pull:
- Follow compose-outreach SKILL.md steps and documented constraints.
- Follow compose-outreach SKILL.md steps and documented constraints.
Compose Outreach by the numbers
- 2,178 all-time installs (skills.sh)
- +93 installs in the week ending Jul 28, 2026 (Skillselion tracking)
- Ranked #464 of 16,659 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: MEDIUM risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
compose-outreach capabilities & compatibility
- Capabilities
- description: "generate personalized outreach mes · generate three personalized outreach formats — e · use common room mcp tools to find and retrieve d · follow compose outreach skill.md steps and docum
- Use cases
- orchestration
What compose-outreach says it does
description: "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 outreac
Generate three personalized outreach formats — email, call script, and LinkedIn message — grounded in Common Room signals for a specific company or contact.
Use Common Room MCP tools to find and retrieve data for the target (company and/or specific contact). Pull:
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill compose-outreachAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 2.2k |
|---|---|
| repo stars | ★ 23.1k |
| Security audit | 2 / 3 scanners passed |
| Last updated | July 28, 2026 |
| Repository | anthropics/knowledge-work-plugins ↗ |
When should an agent use compose-outreach and what problem does it solve?
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 req
Who is it for?
Developers invoking compose-outreach as documented in the skill source.
Skip if: Skip when requirements fall outside compose-outreach documented scope.
When should I use this skill?
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 req
What you get
Outputs aligned with the compose-outreach SKILL.md workflow and stated deliverables.
- cold email draft
- call script
- LinkedIn message
Files
Compose Outreach
Generate three personalized outreach formats — email, call script, and LinkedIn message — grounded in Common Room signals for a specific company or contact.
Outreach Process
Step 1: Look Up the Target
Use Common Room MCP tools to find and retrieve data for the target (company and/or specific contact). Pull:
- Recent product activity and engagement signals
- Community activity (posts, questions, reactions)
- 3rd-party intent signals (job postings, news, funding)
- Relationship history (prior contact, meetings, email opens)
If 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.
Step 2: Web Search for External Hooks (If CR Signals Are Thin)
If 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:
What to search:
"[company name]" funding OR acquisition OR launch OR announcement— last 30 days"[contact full name]" "[company name]"— look for recent articles, interviews, LinkedIn posts, or conference talks
Prioritize external hooks that are:
- Very recent (< 2 weeks) — the prospect is likely still thinking about it
- Publicly visible — they know you could have seen it
- Change-signaling — growth, new role, new product, new market
If the user explicitly asks for web search or external hooks, run it regardless of CR signal richness.
Step 3: Spark Enrichment (If Available)
If 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.
Step 4: Identify the Best Hooks
From the signal data, identify the 1–3 strongest personalization hooks. Rank by: 1. Recency — happened in the last 7–14 days 2. Specificity — a concrete action they took, not a general trend 3. Relevance — connects directly to a value your product delivers
Good 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.
Bad hooks: "I noticed you're a customer" or generic industry trends.
Step 5: Generate All Three Formats
Use 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.
Always produce all three, clearly labeled.
When 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.
Step 6: Annotate Your Choices
After the three drafts, include a brief note (2–4 sentences) explaining:
- Which signals were used and why they were chosen
- Any assumptions made (e.g., inferred call objective)
- Alternative angles if the primary hook doesn't land
Output Format
## Outreach for [Name / Company]
### 📧 Email
**Subject:** [Subject line]
[Email body — 3–5 sentences]
---
### 📞 Call Script
**Opening:**
[Opening line — conversational, 1–2 sentences]
**Value Bridge:**
[Why you're calling and why now — 2–3 sentences tied to a signal]
**Ask:**
[Single, low-friction ask — e.g., 15-minute call, specific question]
---
### 💼 LinkedIn Message
[Under 300 characters. Warm, personal, no pitch.]
---
### Signal Notes
[2–4 sentences: which signals were used, why, and any alternative angles]When Signal Data Is Sparse
If Common Room returns minimal data on the target (e.g., just name, title, tags — no activity, no scores, no Spark):
1. Do not draft outreach from thin air. Outreach grounded in fabricated signals is worse than no outreach. 2. Run web search first — this becomes your primary personalization source. Look for recent news, LinkedIn posts, conference talks, company announcements. 3. If web search also returns little, present what you have honestly and ask the user for context:
## Outreach for [Name / Company] — Limited Data
**What I found:**
[Only the real data from CR and web search]
**I don't have enough signal to draft personalized outreach yet.** To write something strong, I'd need:
- Recent activity or engagement signals
- Context you have from prior conversations
- A specific reason for reaching out now
Can you share any of the above?Quality Standards
- Every message must reference something specific — generic outreach is not acceptable output
- Match tone to context: warm and conversational for inbound/community signals; more formal for cold/executive outreach
- The LinkedIn message must be under 300 characters — no exceptions
- The call script must be speakable naturally — read it aloud mentally to check rhythm
- Never fabricate signals — only reference data retrieved from Common Room or web search
Reference Files
- `references/outreach-formats-guide.md` — detailed format rules, examples, and tone guidelines for each channel
Outreach Formats — Guidelines and Examples
Structure
- Subject line: 4-8 words, specific and curiosity-inducing. Reference the hook directly.
- Opening: Acknowledge the specific signal. Start with "You", "Your team", "Saw that", "Noticed" — not "I".
- Value Bridge: 1-2 sentences connecting their signal to something you can help with. Be concrete.
- Ask: Single, specific, low-friction next step.
- Total length: 3-5 sentences max. No paragraphs.
Example
Subject: Question about your [feature] usage
>
Noticed your team has been deep in [feature] recently — you've hit [usage metric] in the last two weeks. That usually means teams are running into [common blocker] around this stage. Happy to walk through how [similar company] handled it if useful. 15 minutes this week?
---
Call Script
Three parts — a guide, not a word-for-word read:
Opening (10-15 seconds): State your name and company, then reference the specific hook immediately.
Value Bridge (20-30 seconds): Explain why this is worth their time right now, tied to a concrete outcome.
Ask (10 seconds): Single, specific, low-friction — e.g., "Do you have 15 minutes to explore if that's relevant?"
---
LinkedIn Message
Constraints
- 300 characters maximum (platform limit is 400 — we target 300 to prevent overruns)
- No attachments, no links in the first message
- No pitch — just open a door
Structure
- Personal acknowledgment (what you noticed about them)
- One brief sentence on why you reached out
- Soft invitation to connect or respond
Example
Saw your post about [topic] in [community] — our team has been thinking about the same problem. Would love to share what we've learned. Open to a quick chat?
---
Tone Calibration by Context
| Context | Tone | Approach |
|---|---|---|
| Inbound / trial / active community member | Warm, helpful, collaborative | Lead with their activity, offer help |
| Cold outreach (no prior relationship) | Professional, respectful, brief | Lead with signal, be direct about why now |
| Re-engagement (went dark) | Casual, low-pressure | Short, acknowledge the gap, easy ask |
| Executive outreach | Formal, concise, outcome-focused | Lead with business impact, not product |
| Champion job change | Warm, congratulatory | Celebrate them, then gently explore new opportunity |
---
What to Avoid (All Channels)
- Starting with filler ("I hope this email finds you well") or defensive language ("I know you're busy but...")
- Multi-paragraph messages with multiple asks
- Vague subject lines like "Following up" or "Quick question"
- Fabricated familiarity ("I've been following your company for a while...")
Related skills
FAQ
What is compose-outreach?
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 o
When should I use compose-outreach?
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 o
Is compose-outreach safe to install?
Review the Security Audits panel on this page before production use.