Input Traceability
-
SKILL
cold-email-copywriter/SKILL.md.claude/skills/cold-email-copywriter/SKILL.md
-
REF
Framework definitions (3 variants + worked examples).claude/skills/cold-email-copywriter/references/frameworks.md
-
REF
Rules, constraints, tone philosophy, quality gates.claude/skills/cold-email-copywriter/references/rules-and-constraints.md
-
ICP
LeadGrow self-campaign ICP profile (Series B SaaS founders)clients/gtm-client-leadgrow/icp-profile.yaml
-
RULE
No em-dashes in copy (workspace rule from MEMORY.md)MEMORY.md content rule
Email Sequence
Email 1 // Signal Observation
Formula: Implied situation without naming it -> their lived reality -> specific proof
-> casual CTA
Raising a round and still running your own demos is a very specific kind of
bottleneck.
The board wants pipeline numbers. You want to stop being the only person who can close. And the gap between those two things gets wider every week you don't have outbound working.
We've helped a few founders in that exact window go from doing it all themselves to having qualified meetings showing up on their calendar without hiring. Worth a quick look at how one of them set it up?
The board wants pipeline numbers. You want to stop being the only person who can close. And the gap between those two things gets wider every week you don't have outbound working.
We've helped a few founders in that exact window go from doing it all themselves to having qualified meetings showing up on their calendar without hiring. Worth a quick look at how one of them set it up?
{Pipeline bottleneck, [First Name]|Your demos, [First Name]|Quick founder question}
Email 2 // Poke the Bear
[threaded -- no new subject]
How many of the meetings on your calendar this week did you source yourself?
Most Series B founders we talk to are still the top pipeline source on their own team. Not because they want to be, but because nothing else is producing consistently enough to hand off.
We build the outbound motion that replaces the founder as the pipeline engine. 2,000+ qualified meetings booked last year across B2B SaaS. Happy to share a 2 minute breakdown of what the handoff looks like.
Most Series B founders we talk to are still the top pipeline source on their own team. Not because they want to be, but because nothing else is producing consistently enough to hand off.
We build the outbound motion that replaces the founder as the pipeline engine. 2,000+ qualified meetings booked last year across B2B SaaS. Happy to share a 2 minute breakdown of what the handoff looks like.
Email 3 // Permissionless Value
[threaded -- no new subject]
Quick data point since it came up in a few founder conversations this month: Series B
SaaS companies that launch outbound within 90 days of close see 2.3x more pipeline
sourced in the first two quarters vs those who wait to hire an SDR team first.
The bottleneck is almost never headcount. It is having a system that works before the hire starts.
We build that system for B2B SaaS founders. Just wanted to leave that with you.
The bottleneck is almost never headcount. It is having a system that works before the hire starts.
We build that system for B2B SaaS founders. Just wanted to leave that with you.
QA Checklist
No em dashesPASS
4 lines max per emailPASS (4/4/3)
60-100 words per emailPASS (87/82/78) No links in bodyPASS No signaturePASS No "I wanted to reach out" etcPASS Signal not named directly (E1)PASS Subject line 4 words max (E1)PASS (3/3/3)
Emails 2+3 threaded (no subject)PASS Bar test -- say this out loud?REVIEW
Permissionless value usable today?WEAK Cialdini subtle?PASS
Self-Critique
- 1. E3 permissionless value is weak. "2.3x more pipeline" is a stat, not something they can use in a meeting today. Should be named accounts with signals or a specific diagnostic.
- 2. E1 might be too long. 4 lines but dense. Could trim the middle paragraph.
- 3. E2 "2,000+ qualified meetings" is a flex, not proof. Would land better as a specific founder story or timeframe.
- 4. All 3 emails lean on the same "founder doing sales" pain. Could diversify E2 or E3 to hit a different angle.
- 5. "Worth a quick look" CTA in E1 might be too close to asking for a meeting. "Comparing notes" is softer.
Input Traceability
-
SKILL
cold-email-copywriter/SKILL.md (v1.1 with QA validation section).claude/skills/cold-email-copywriter/SKILL.md
-
REF
Framework definitions (3 variants + worked examples, {FIRST_NAME} format).claude/skills/cold-email-copywriter/references/frameworks.md
-
REF
Rules v1.1: tone, constraints + spacing rules + variable format rules.claude/skills/cold-email-copywriter/references/rules-and-constraints.md
-
ICP
LeadGrow self-campaign ICP profile (Series B SaaS founders)clients/gtm-client-leadgrow/icp-profile.yaml
-
RULE
No em-dashes in copy (workspace rule from MEMORY.md)MEMORY.md content rule
-
NEW
QA validator script (post-write validation loop).claude/skills/cold-email-copywriter/scripts/qa_validate.py
Email Sequence
Email 1 // Signal Observation
Formula: Implied situation without naming it -> their lived reality -> specific proof
-> casual CTA
Somewhere between closing the round and the first board meeting after, most founders
realize the pipeline that got them here was basically them and a few warm intros.
The board wants a scalable revenue engine. You want to stop being the entire sales team. Both of those are the same problem.
We've helped a handful of Series B teams build outbound from zero before that conversation got uncomfortable. Happy to share how one of them structured it, no deck.
The board wants a scalable revenue engine. You want to stop being the entire sales team. Both of those are the same problem.
We've helped a handful of Series B teams build outbound from zero before that conversation got uncomfortable. Happy to share how one of them structured it, no deck.
{Post-raise pipeline|Outbound from zero|Pipeline question, {FIRST_NAME}}
Email 2 // Poke the Bear
[threaded - no new subject]
Quick question, is the plan to hire your first SDR before or after the board asks why
outbound pipeline is still at zero?
Most founders at your stage try to solve it by hiring, but an SDR with no playbook, no sequences, and no list just burns 6 months figuring out what you could have handed them on day one.
We build that playbook before the hire so the first rep actually has something to run. Want me to send over what that usually looks like?
Most founders at your stage try to solve it by hiring, but an SDR with no playbook, no sequences, and no list just burns 6 months figuring out what you could have handed them on day one.
We build that playbook before the hire so the first rep actually has something to run. Want me to send over what that usually looks like?
Email 3 // Permissionless Value
[threaded - no new subject]
Three outbound plays that have worked for post-Series B SaaS teams in the 30-80
headcount range, since most don't have this yet: One, target accounts showing hiring
intent in your category before they go to market. Two, re-engage closed lost from
inbound with a new angle tied to a recent trigger. Three, build a founder-branded
sequence that converts 3x a generic SDR intro.
We build this kind of motion for teams at your stage. Just wanted to leave that with you.
We build this kind of motion for teams at your stage. Just wanted to leave that with you.
QA Results (automated)
qa_validate.py output: 31 checks, 0 failures, 0 warnings. PASS
No em dashesPASS
4 lines max per emailPASS (4/4/3)
60-100 words per emailPASS (79/86/81) No links in bodyPASS No signaturePASS No banned phrasesPASS Subject line 4 words max (E1)PASS
Subject spintax 3 variants (E1)PASS
Emails 2+3 threaded (no subject)PASS
Variable format ({FIRST_NAME} only)PASS
Line spacing between idea blocksPASS
Skill Changes (v1 -> v1.1)
-
1.
QA Validation Loop — New Python script
(
scripts/qa_validate.py) runs automated checks against copy before output. 11 check categories. Sub-agent spawns it during skill invocation. - 2. Spacing Rules — Every idea block gets blank line separator. Visual rhythm = breathing, not wall of text.
-
3.
Variable Format — Strict
{FIRST_NAME}format only.[First Name]and{{name}}banned. Allowed:{FIRST_NAME},{LAST_NAME},{COMPANY},{TITLE}.
v1 Retroactive Validation
Ran v1.1 validator against v1 copy. 30 checks, 1 failure.
Variable format (E1 subject lines)FAIL — used [First Name] not {FIRST_NAME}
All other checks (29)PASS
Feedback
Mitchell (trigger for v1.1)
Build a verification loop that QA's for obvious scriptable things via sub-agent. Add
clear spacing rules. Variable format: only {FIRST_NAME} style.
Skill Changes (v1.1 → v1.2)
- 1. SKILL.md restructure — Applied skill-creator progressive disclosure. Aggressive description with natural-language trigger phrases. Out of Scope section added (LinkedIn, warm nurture, deliverability, proposals, strategy). Lean body — detail pushed to reference files.
- 2. references/taste.md (new) — Synthesized preference rules for recurring judgment calls: permissionless value bar, authority specificity, signal subtlety, subject line register, pain angle rotation.
- 3. Sequence diversity constraint — Name E1's pain axis, pick different for E2. Name both, pick third for E3. Axis table: pipeline credibility / team performance / forecast accuracy / speed to first win / motion maturity.
- 4. Subject line voice test — Colleague-forward test added. Observation/fragment, not CTA or question. If a colleague wouldn't forward it with that subject, rewrite it.
- 5. Permissionless value bar sharpened — Stat ≠ value. Must pass "can they share this in a meeting tomorrow without any additional work?" Vague benchmark warning added with failing/passing examples.
- 6. Authority specificity — One specific anonymous story beats "a few revenue leaders." Anonymous is fine. Vague is not.
Eval Iteration-1 Results
3 evals: CRO 3-email sequence, VP Sales signal observation, permissionless value benchmarks. Full review →
with_skill pass rate100% (25/25)
without_skill pass rate15% (4/25)
Delta+0.85
E1 — CRO 3-email sequence11/11 PASS
E2 — VP Sales signal observation7/7 PASS
E3 — Permissionless benchmarks7/7 PASS
Copy Outputs — Eval Iteration-1 (with skill)
3 evals × with_skill. Eval inputs shown in label.
Eval 1 — CRO 3-Email Sequence
Newly hired CRO, Series B SaaS, announced on LinkedIn 2 weeks ago. Signal Observation
→ Poke the Bear → Permissionless Value.
Email 1 // Signal Observation
The first 90 days in a new revenue seat is mostly archaeology: figuring out what's
real, what the last person oversold to the board, and where you actually need to
build from scratch.
We helped a CRO at a Series B navigate that exact window and get outbound producing before Q1 became a board conversation.
Worth comparing notes?
We helped a CRO at a Series B navigate that exact window and get outbound producing before Q1 became a board conversation.
Worth comparing notes?
{The archaeology phase|Pipeline inherited, {FIRST_NAME}|New revenue seat}
Email 2 // Poke the Bear
[threaded — no new subject]
Do you know yet which reps are actually producing and which ones just look good on a
call?
Most incoming revenue leaders spend the first 60 days discovering that tenure has protected people who stopped producing two quarters ago.
A CRO at a Series B, six weeks in, had three reps with zero real opportunities logged in 45 days. We rebuilt the outbound motion in 30. Happy to share how they structured it, no deck.
Most incoming revenue leaders spend the first 60 days discovering that tenure has protected people who stopped producing two quarters ago.
A CRO at a Series B, six weeks in, had three reps with zero real opportunities logged in 45 days. We rebuilt the outbound motion in 30. Happy to share how they structured it, no deck.
Email 3 // Permissionless Value
[threaded — no new subject]
B2B SaaS outbound-sourced pipeline benchmarks by stage, since most handoff docs skip
this: early stage 60-70%, mid-market 40-50%, enterprise 25-35%.
If what you inherited is sitting below those numbers, the motion was built around inbound and no one said that out loud before you got there.
We build outbound for revenue teams under those benchmarks. Just wanted to leave that with you.
If what you inherited is sitting below those numbers, the motion was built around inbound and no one said that out loud before you got there.
We build outbound for revenue teams under those benchmarks. Just wanted to leave that with you.
Eval 2 — VP Sales Signal Observation
VP Sales, mid-market SaaS. 4 SDR job postings in 45 days, no AE hires. Single email,
Signal Observation framework.
Email 1 // Signal Observation
When a sales team loads up on SDRs before the outbound motion is proven, the
meetings land but the deals don't move. The signal behind them was activity, not
intent.
That gap is where most VP Sales quarters get decided.
A VP of Sales at a mid-market SaaS hit that exact wall. We rebuilt the motion so the meetings SDRs booked had actual buying signal behind them, and closed the gap in one quarter. Worth a quick conversation?
That gap is where most VP Sales quarters get decided.
A VP of Sales at a mid-market SaaS hit that exact wall. We rebuilt the motion so the meetings SDRs booked had actual buying signal behind them, and closed the gap in one quarter. Worth a quick conversation?
{SDR pipeline gap|The pipeline math, {FIRST_NAME}|Outbound motion question}
Eval 3 — Permissionless Value (Benchmarks Variant)
Newly promoted internal CRO (from VP Sales). No named accounts available — benchmarks
variant.
Email 1 // Permissionless Value
B2B SaaS outbound-sourced pipeline benchmarks, since most handoff docs skip this:
Early stage 60-70%, mid-market 40-50%, enterprise 25-35%.
If what you inherited is sitting below those numbers, the motion was built around inbound. The VP who handed it to you probably never said that out loud.
We build outbound for revenue teams that are under those benchmarks. Just wanted to leave that with you.
If what you inherited is sitting below those numbers, the motion was built around inbound. The VP who handed it to you probably never said that out loud.
We build outbound for revenue teams that are under those benchmarks. Just wanted to leave that with you.
{Pipeline mix|Outbound benchmark inherited|The pipeline you inherited}
Top Baseline Failure Modes
Signal named directlyFAIL baseline
Wrong variable format ({{name}})FAIL baseline No spintax on subjectFAIL baseline
Word count blown (150+ words)FAIL baseline
Em-dashes in subject linesFAIL baseline
Meeting ask in permissionless valueFAIL baseline
Generic non-quotable benchmarksFAIL baseline
Feedback
Mitchell (trigger for v1.2)
Restructure using Matt Pocock skill-creator methodology. Version control in git. Label
each iteration loop.
What Changed (v2.0)
-
+KG Scout phase searches
clients/gtm-client-{client}/dynamically — no hardcoded paths - +Auto-selects EDP most relevant to prompt context (not just top-scored)
- +Benchmarks now sourced from real EDP intel (5.3x/1.6x from Gradient Works 2025 via edp-framework.md)
- +QA loop includes qualitative rubric (qa-agent.md) — EDP grounding, PQS grounding, signal subtlety, persona fit
-
+trace.json now includes
edp_selectedfield with selection rationale
Input Traceability
-
SKILL
cold-email-copywriter/SKILL.md (v2.0 — 4-phase architecture).claude/skills/cold-email-copywriter/SKILL.md
-
REF
KG Scout instructions — dynamic client folder search.claude/skills/cold-email-copywriter/references/kg-scout.md
-
REF
QA Agent — qualitative rubric (EDP grounding, persona fit, bar test).claude/skills/cold-email-copywriter/references/qa-agent.md
-
ICP
EDP framework — 7 EDPs ranked by score (leadgrow CRO campaign)clients/gtm-client-leadgrow/research/edp-framework.md
-
ICP
Buyer personas — Vanessa (S1 CRO), Jordan (PLG CRO), Marcus (Founder)clients/gtm-client-leadgrow/research/buyer-persona.md
-
ICP
EDP discovery — industry data, CRO tenure stats, PQS signalsclients/gtm-client-leadgrow/research/edp-discovery.md
Eval 1 — CRO Sequence (3 emails)
Newly hired CRO, Series B SaaS, announced 2 weeks ago. EDP selected: EDP-1 (Pipeline
Coverage Vacuum) + EDP-2 (CRO Tenure Clock). Score: 13/13.
Email 1 // Signal Observation
Implied situation without naming it -> their lived reality in their words -> specific
proof -> casual CTA
The first 90 days in a new revenue seat is mostly archaeology: figuring out what's
real, what the last person talked the board into believing, and where you need to
build from scratch before anyone notices the gap.
We helped a CRO at a Series B do exactly that and get outbound producing before it became a Q2 conversation.
Worth comparing notes?
We helped a CRO at a Series B do exactly that and get outbound producing before it became a Q2 conversation.
Worth comparing notes?
{The archaeology phase|Inherited pipeline, {FIRST_NAME}|New revenue seat}
Email 2 // Poke the Bear [threaded — no new subject]
Poke the bear question -> the career credibility pain -> specific anonymous proof ->
soft offer
Do you have anything concrete to show the board at day 90 that you actually built, not
what you walked in with?
Most new revenue leaders hit that review with inherited pipeline they've been managing down and zero outbound they can point to as theirs.
A CRO at a Series B, four weeks in, had the same problem. We got their outbound live and producing in 30 days. Happy to share how they structured it.
Most new revenue leaders hit that review with inherited pipeline they've been managing down and zero outbound they can point to as theirs.
A CRO at a Series B, four weeks in, had the same problem. We got their outbound live and producing in 30 days. Happy to share how they structured it.
Email 3 // Permissionless Value [threaded — no new subject]
Hand them the benchmark data -> connect it to their specific situation -> who we are
-> leave it
A number worth having before your next board prep: at a 19% win rate, you need 5.3x
pipeline coverage to hit your number. Most new CROs inherit closer to 1.6x.
That 3.3x gap is not closable by coaching reps or tightening qualification. It requires new pipeline, built fast.
We build outbound for revenue teams in exactly that gap. Just wanted to leave that with you.
That 3.3x gap is not closable by coaching reps or tightening qualification. It requires new pipeline, built fast.
We build outbound for revenue teams in exactly that gap. Just wanted to leave that with you.
Eval 2 — VP Sales Signal Observation
VP Sales, mid-market SaaS. 4 SDR postings in 45 days, no AE hires. EDP selected: EDP-3
(Infrastructure Build Gap). Score: 9/9.
Email 1 // Signal Observation
Implied SDR hiring velocity without naming it -> their lived reality -> specific proof
-> casual CTA
When a team starts scaling SDR headcount before the outbound playbook is proven, the
ramp math usually doesn't work out.
Most of the pipeline gap doesn't come from a people problem. It comes from infrastructure that wasn't built before the first hire landed.
A VP Sales at a $14M ARR SaaS had four SDRs onboarding with no sequence, no warmed domains, and a 90-day board review coming. We had first meetings on the calendar in 23 days.
Worth a quick conversation, {FIRST_NAME}?
Most of the pipeline gap doesn't come from a people problem. It comes from infrastructure that wasn't built before the first hire landed.
A VP Sales at a $14M ARR SaaS had four SDRs onboarding with no sequence, no warmed domains, and a 90-day board review coming. We had first meetings on the calendar in 23 days.
Worth a quick conversation, {FIRST_NAME}?
{SDR ramp math|Building before the playbook|Four hires, no pipeline}
Eval 3 — Permissionless Value (Benchmarks)
Internally promoted CRO (from VP Sales). No named accounts. EDP selected: EDP-1
(Pipeline Coverage Vacuum). Score: 9/9.
Email 1 // Permissionless Value
Drop the benchmark data -> connect it to their specific situation -> who we are ->
leave it
B2B SaaS pipeline benchmarks by stage, since board decks rarely include them:
Series A: you need 5.3x coverage at a 19% win rate to hit target. Most teams that relied on inbound operate closer to 1.6x. The gap is 3.3x, and it does not move by coaching reps.
We build outbound for revenue teams under those numbers. Just wanted to leave that with you.
Series A: you need 5.3x coverage at a 19% win rate to hit target. Most teams that relied on inbound operate closer to 1.6x. The gap is 3.3x, and it does not move by coaching reps.
We build outbound for revenue teams under those numbers. Just wanted to leave that with you.
{Pipeline math|Your coverage numbers|Series A benchmarks}
KG Scout EDP Selection Rationale
Eval 1 — EDP-1 + EDP-2 (newly hired external CRO, S5 dual-signal)CORRECT
Eval 2 — EDP-3 (VP Sales + SDR scaling before playbook proven)CORRECT
Eval 3 — EDP-1 over EDP-3 (internal promo already built infrastructure)CORRECT
All benchmarks traceable to edp-framework.md (Gradient Works 2025)VERIFIED
Feedback
v3 pending
Waiting for v2 feedback cycle.