Prd V09 Cold Outreach Tiered logo

Prd V09 Cold Outreach Tiered

Community
mattgierhart
prd-v09-cold-outreach-tiered

Build Tier 1/2/3 cold outreach sequences differentiated by personalization depth and research signal strength during PRD v0.9 Go-to-Market. Triggers on requests to plan cold outreach, founder-led sales, or when user asks "cold email sequence", "outbound campaign", "founder outreach", "LinkedIn outreach", "Tier 1 personalization", "predictable revenue", "sales cadence", "BDR sequence". Outputs GTM-OUT-* sequence entries and lead-list references.

Overview

Publishermattgierhart
RepositoryPRD-driven-context-engineering
Skill nameprd-v09-cold-outreach-tiered
Stars
179
Forks
11
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by mattgierhart on GitHub. Read the source before you install it.

Installation

Install the Prd V09 Cold Outreach Tiered AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git /tmp/PRD-driven-context-engineering
mkdir -p .claude/skills
cp -r /tmp/PRD-driven-context-engineering/plugins/prd-ce/skills/prd-v09-cold-outreach-tiered .claude/skills/prd-v09-cold-outreach-tiered
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Prd V09 Cold Outreach Tiered in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Prd V09 Cold Outreach Tiered on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Prd V09 Cold Outreach Tiered is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Cold Outreach (Tiered: 1:1 / 1:few / 1:many)

Position in workflow: v0.9 Offer Construction → v0.9 Cold Outreach (Tiered) → v0.9 Launch Metrics

Execution Mode

Default is standard. See .claude/rules/08-skill-execution-modes.md for selection logic.

ModeWhat this skill produces
quickOne tier (typically Tier 2); 3-touch sequence; lead-list scoring rubric
standardAll three tiers; 3–5 touches each; lead-list scoring + tier-assignment logic; reply-handling guide
deepAll tiers + A/B subject lines per tier; channel mix (email + LinkedIn + voicemail); reply-rate baselines; objection library

What This Does

Builds three differentiated cold-outreach sequences, each calibrated to a different ratio of research-per-lead:

  • Tier 1 (1:1, founder-led) — Hand-researched. Highly personalized. Each touch references something specific. Volume: 10–30 contacts.
  • Tier 2 (1:few, semi-automated) — Segment-personalized. Template with 3–5 dynamic variables per recipient. Volume: 100–500 contacts.
  • Tier 3 (1:many, automated) — Broad-fit. Template only, minimal personalization. Volume: 1,000–10,000+ contacts.

The tiers are not "good/better/best" — each has its place. Tier 3 fills the top of the funnel cheaply. Tier 2 carries the bulk. Tier 1 closes the highest-value targets that templates can never reach.

How It Works

  1. Source lead lists from ICP — Pull from the Positioning best-fit characteristics. Use enrichment tools (Apollo, Clay, Clearbit) or LinkedIn Sales Nav search anchored on firmographic + behavioral signals from PER-.
  2. Score each lead's signal strength (1–5):
    • Trigger signal — Recent funding, hiring, product launch, public pain (5)
    • Fit signal — Strong firmographic/behavioral match without specific trigger (3–4)
    • Cold signal — Broad-fit only; no specific signal (1–2)
  3. Tier assignment:
    • Signal 4–5 + opportunity size ≥ threshold → Tier 1
    • Signal 3–4 → Tier 2
    • Signal 1–2 → Tier 3 (or drop if list is large enough)
  4. Build per-tier sequences — Each tier gets its own template structure (see Output Template). Tier 1 is hand-drafted; Tier 2 is template + variables; Tier 3 is template only.
  5. End every sequence on the guarantee — The guarantee from prd-v09-offer-construction-hormozi is the reply-friction killer. Don't ask for a meeting cold; ask them to invoke the guarantee.
  6. Plan reply handling — Define what counts as a reply (positive, ask, objection, unsubscribe), and have a response cadence for each. Tier 1 replies go to founder immediately. Tier 3 replies route through a templatized objection library.

Example

B2B SaaS founder launching, ICP = Series A SaaS PMs.

Tier 1 (20 hand-picked targets):

  • Touch 1 (Day 0, email): Reference specific recent blog post + offer specific insight on their problem
  • Touch 2 (Day 4, LinkedIn): Connect with a one-line follow-up referencing the email
  • Touch 3 (Day 10, email): Share a relevant case study from a similar company; mention the guarantee
  • Touch 4 (Day 18, email): Soft breakup — "want me to circle back in a quarter?"

Tier 2 (200 mid-signal leads):

  • Touch 1 (Day 0, email): Template with 3 variables ({company}, {pain point}, {peer company}). 6–10 sentences max.
  • Touch 2 (Day 3, email): One-line bump
  • Touch 3 (Day 7, email): Case study + guarantee mention
  • Touch 4 (Day 14, email): Breakup

Tier 3 (2,000 broad-fit leads):

  • Touch 1 (Day 0, email): Template only. 4–6 sentences. Lead with category insight, not pitch.
  • Touch 2 (Day 5, email): Case study
  • Touch 3 (Day 12, email): Breakup ("last note from me")

Expected reply rates: Tier 1 = 30–50%; Tier 2 = 8–15%; Tier 3 = 1–3%.

What You Get Back

  • GTM-OUT-* entries (one per tier sequence) — Tier metadata, per-touch templates, channel mix, timing
  • GTM-OUT-touch-* entries — Individual touch templates with subject line, body, channel
  • Lead-list scoring rubric (single GTM-*) — How to assign tier
  • Reply-handling guide — What counts as a reply; routing rules

When to Use It

TriggerMode
B2B / founder-led sales motionstandard
Post-launch acquisition pushstandard
Paid channels too expensive (high CAC)standard
Specific ABM-style campaign against named accountsdeep, Tier 1 only
Mass-market consumer product with no individual-buyer relationshipdo not use — wrong channel

Consumes

  • GTM-* positioning + PER-* best-fit characteristics — Source for ICP and message anchoring
  • GTM-* offer card + GTM-* guarantee (from v0.9 Offer Construction) — Sequences end on the guarantee, not a meeting ask
  • CFD-* customer stories (from v0.1–v0.4 + post-launch) — Case studies for touch 3
  • BR-POS-* constraints — Tier targeting must honor "not for" rules
  • KPI-* targets (from v0.3 + v0.9 Launch Metrics) — Reply rate and meeting-booked targets per tier

Produces

  • GTM-OUT-* tier entries — One per tier with sequence metadata
  • GTM-OUT-touch-* entries — Per-touch templates (subject, body, channel, timing)
  • GTM-* lead-list scoring rubric
  • CFD-* gaps — When sequences reveal objections we can't answer, log as CFD- research gaps

Output Template

GTM-OUT-XXX: Tier [1 | 2 | 3] Sequence
Type: Outreach
Tier: [1 | 2 | 3]
Volume: [target lead count]
Owner: [Person / role]
Status: [Planned | Active | Paused]

Lead profile:
  Signal strength: [4–5 | 3–4 | 1–2]
  Source: [Apollo | LinkedIn Sales Nav | Clay | Manual]
  Best-fit criteria: [Anchored in PER- characteristics]

Sequence:
  Touch 1: GTM-OUT-touch-AAA — Day 0, [channel]
  Touch 2: GTM-OUT-touch-BBB — Day [N], [channel]
  Touch 3: GTM-OUT-touch-CCC — Day [N], [channel]
  Touch 4: GTM-OUT-touch-DDD — Day [N], [channel]

Reply handling:
  Positive: [Routing]
  Ask: [Routing]
  Objection: [Routing — point to objection library]
  Unsubscribe: [Action]

KPI targets:
  Reply rate: [Tier 1: 30–50% | Tier 2: 8–15% | Tier 3: 1–3%]
  Meeting-booked rate: [varies]

Linked IDs: PER-XXX, GTM-YYY (positioning), GTM-ZZZ (offer), GTM-AAA (guarantee), KPI-BBB
GTM-OUT-touch-XXX: Touch [N] — Tier [1|2|3]
Channel: [Email | LinkedIn | Voicemail | SMS]
Subject: "[Subject line — A/B variants for deep mode]"

Body:
  [Template body, with {variable} markers for tiers 2 and 3]

Personalization tier:
  Tier 1: Hand-drafted; each touch references something specific
  Tier 2: Template + 3–5 variables — {company}, {pain_point}, {peer_company}
  Tier 3: Template only

Ends on: [Guarantee mention | Case study | Soft ask | Breakup]

Linked IDs: GTM-OUT-XXX (parent sequence), GTM-AAA (guarantee)

Anti-Patterns

PatternSignalFix
Same template for all tiersTier 1 reply rate < 10%Tier 1 must be hand-drafted; templates are the floor, not the ceiling
Fake personalization"{first_name}, I love what {company} is doing"Either personalize for real (Tier 1) or stop pretending (Tier 3)
Ask for meeting cold"Got 15 min next week?" in touch 1Lead with value; ask for guarantee invocation or content engagement instead
No breakupSequence runs forever, hurting deliverabilityAlways include a final-touch breakup
No tier assignment logicAll leads in same tierBuild the scoring rubric before sending anything
Outreach without offerSequence runs before Offer Construction is completeWait — without the guarantee, the sequence ends on weak CTAs
Outreach without positioningGeneric value claimsReply rates die; honor the Dunford positioning

Quality Gates

Before launching:

  • All three tiers defined (or quick-mode single tier with documented reason)
  • Per-touch templates exist and respect BR-POS-* constraints
  • Sequences end on the guarantee (or explicit reason why not)
  • Reply-handling rules documented
  • KPI- targets set per tier (reply rate + meeting-booked rate)
  • Unsubscribe path is one-click and honored
  • Spam-compliance check (CAN-SPAM, GDPR if applicable) done

Downstream Connections

ConsumerWhat it usesExample
Launch Channels (ORB)Cold outreach is a Borrowed channel; rolls into mix matrixTier 1 = Borrowed-time; Tier 2/3 = Borrowed-volume
Launch MetricsPer-tier reply rates become KPI- entriesKPI-tier1-reply-rate
Feedback Loop SetupReply objections feed CFD-"Why we passed" replies → CFD- pattern
v1.0 Continuous DiscoveryHigh-engagement Tier 1 replies = founder interviewsReply → CFD- interview with confidence ≥ 3/5

Detailed References

  • Aaron Ross, Predictable Revenue (2011) — Tier 2/3 outbound structure
  • Aaron Ross, From Impossible to Inevitable (2016) — Sequencing
  • BrianRWagner's cold-outreach-sequence skill (ai-marketing-claude-code-skills)
  • (No bundled references/ — sequences are templates, not theory)

Frequently asked questions

What does the Prd V09 Cold Outreach Tiered AI skill do?

Build Tier 1/2/3 cold outreach sequences differentiated by personalization depth and research signal strength during PRD v0.9 Go-to-Market. Triggers on requests to plan cold outreach, founder-led sales, or when user asks "cold email sequence", "outbound campaign", "founder outreach", "LinkedIn outreach", "Tier 1 personalization", "predictable revenue", "sales cadence", "BDR sequence". Outputs GTM-OUT-* sequence entries and lead-list references.

Why use Prd V09 Cold Outreach Tiered on TypingMind?

Because you install it once and use it with any model. Prd V09 Cold Outreach Tiered is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Prd V09 Cold Outreach Tiered in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/plugins/prd-ce/skills/prd-v09-cold-outreach-tiered. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Prd V09 Cold Outreach Tiered?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Prd V09 Cold Outreach Tiered?

As many as you like. As long as a model supports skills, you can use Prd V09 Cold Outreach Tiered with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Prd V09 Cold Outreach Tiered AI skill free?

Yes. It is published on GitHub by mattgierhart under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇