create-image-fal
Generate or edit an image via any FAL image model (nano-banana edit, gpt-image, flux, ...), ROUTED THROUGH THE fal-proxy so it bills the Ads agent. image_urls…
Write high-converting cold emails using structured frameworks, personalization tiers, and patterns from real campaigns. Pure reasoning skill — no scripts. Auto-loads when any task requires outreach copy.
$ npx -y skills add gooseworks-ai/goose-skills --skill email-drafting --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/email-draftingContext preview
The summary Claude sees to decide when to auto-load this skill.
Write high-converting cold emails using structured frameworks, personalization tiers, and patterns from real campaigns. Pure reasoning skill — no scripts. Auto-loads when any task requires outreach copy.
name: email-drafting description: > Write high-converting cold emails using structured frameworks, personalization tiers, and patterns from real campaigns. Pure reasoning skill — no scripts. Auto-loads when any task requires outreach copy. tags: [outreach]
Pure reasoning skill for writing cold emails. No scripts, no tools — just frameworks, patterns, and examples from real campaigns that consistently generate replies.
Use this skill when:
Collect campaign context before writing anything. Ask all questions at once, organized by category. Skip any the user has already answered.
1. What product/service are you selling? 2. What problem does it solve? Who feels this pain most acutely? 3. What's the campaign angle? (hiring signal, competitor displacement, pain-based, event-triggered, etc.) 4. Is there a specific signal or trigger? (job posting, G2 review, LinkedIn engagement, funding round, etc.)
5. Who is the recipient? (title, seniority, department) 6. What keeps them up at night? (daily frustrations relevant to your product) 7. What objections will they have? (budget, switching cost, "we already have X", timing)
8. What social proof do you have? (customer logos, case studies, metrics) 9. Name 2-3 peer companies the recipient would recognize as similar to them 10. Any hard metrics? (cost savings, speed improvement, % lift)
11. What tone fits? (casual-direct, professional-sharp, provocative, empathetic) 12. Who is the sender? (founder, AE, SDR — this affects voice) 13. Any brand guidelines or words to avoid?
14. How many touches? (default: 3) 15. What's the desired CTA? (call, demo, reply, resource download) 16. Email-only or multi-channel? (email + LinkedIn, email + phone)
Every cold email follows this skeleton:
Hook (1 sentence) → Evidence (1-2 sentences) → Offer (1 sentence)
**Word count targets:**
Pick the framework that matches the campaign angle:
| Framework | Structure | Best For | |-----------|-----------|----------| | **PAS** | Problem → Agitate → Solve | Pain-based signals (complaint posts, operational friction) | | **BAB** | Before → After → Bridge | Aspirational buyers (growth-stage, scaling companies) | | **AIDA** | Attention → Interest → Desire → Action | Cold database outreach (no specific signal) | | **Signal-Proof-Ask** | Signal → Proof → Soft ask | Signal-based campaigns (hiring, engagement, events) |
Choose based on campaign size and expected ROI per lead:
| Tier | What It Means | Lead Volume | Expected Reply Rate | |------|---------------|-------------|-------------------| | **Tier 1 (Generic)** | Merge fields only (`{first_name}`, `{company}`). Same template for everyone. | 500+ leads | 1-3% | | **Tier 2 (Segment)** | Industry/role-specific pain points + proof swaps. One template per segment. | 50-500 leads | 3-7% | | **Tier 3 (Deep)** | Reference a specific signal (their post, comment, job posting, news). Unique per lead. | 1-50 leads | 8-20% |
8 proven patterns from real campaigns:
| # | Pattern | Example | |---|---------|---------| | 1 | **Signal reference** | "Before you fill that [role] role" | | 2 | **Peer framing** | "What TIA members are doing with AI workers" | | 3 | **Question** | "Is [Company] still [doing thing product fixes]?" | | 4 | **Replacement** | "Looking for a [competitor] replacement?" | | 5 | **Data hook** | "$150K agency study → $8K. 48 hours." | | 6 | **Empathy** | "When [event that affected them]" | | 7 | **Direct** | "[Topic] for [Company]" | | 8 | **Curiosity** | "How [peer company] did [interesting thing]" |
**Rules for subject lines:**
| Tone | When to Use | Voice Example | |------|-------------|---------------| | **Casual-Direct** | SDR sending to peers, startup-to-startup | "Hey — saw your post. We work on the same problem." | | **Professional-Sharp** | Enterprise outreach, VP+ recipients | "I wanted to reach out because [specific reason]." | | **Provocative** | Competitive displacement, challenger positioning | "Your current tool is costing you more than you think." | | **Empathetic** | Orphan capture, pain-based outreach | "I know switching platforms mid-cycle is brutal." |
| Touch | Timing | Purpose | Length | Notes | |-------|--------|---------|--------|-------| | **Touch 1** | Day 1 | Hook + proof + soft CTA | 50-90 words | The only email that can be longer | | **Touch 2** | Day 3-5 | New angle or asset | 30-50 words | Different proof point, not a "bump" | | **Touch 3** | Day 7-10 | Different proof point or social | 20-40 words | Shorter = better this late | | **Touch 4** | Day 14-21 | Breakup (optional) | 20-30 words | Remove pressure, leave door open |
**Sequence rules:**
These are non-negotiable. Every email must pass all 10:
1. **No filler openers.** Never "I hope this finds you well", "I hope you're having a great week", "just reaching out" 2. **No "just checking in" follow-ups.** Every touch adds a new reason to reply 3. **Max 4 paragraphs per email.** Most should be 2-3 4. **Every email references something specific to the recipient.** Title, company, signal, industry — nev
Put your AI agent on the growth team. Research customers and competitors, analyze what is working, create the next campaign, and learn from the result.
Repo: gooseworks-ai/goose-skills
Generate or edit an image via any FAL image model (nano-banana edit, gpt-image, flux, ...), ROUTED THROUGH THE fal-proxy so it bills the Ads agent. image_urls…
Generate a single photoreal or designed image with OpenAI gpt-image via fal.ai. Supports gpt-image-1 (default, fixed sizes — the FAL fallback for Higgsfield's…
Generate an instrumental music bed via ElevenLabs Music, ROUTED THROUGH THE elevenlabs-proxy so it bills the Ads agent. Trims any sparse intro, loudnorm, fades…
Image-to-video (or text-to-video) via any FAL video model (Kling, Seedance, Veo), ROUTED THROUGH THE GooseWorks fal-proxy so the call bills the Ads agent. The…
Generate a voiceover (VO) clip via ElevenLabs text-to-speech, ROUTED THROUGH THE elevenlabs-proxy so it bills the Ads agent. Voice id + script text come from…
Scrape competitor ads from Google Ads by domain. Returns ad creatives, formats, and campaign details. Use for competitive ad research and messaging analysis.