Cold email write
HARD RULE: ColdIQ/Braun/Voss + company research for personalization; mandatory humanizer then outbound-qc-gate before any Instantly/outbound send; always use…
Skill by 10xcoldleads
Chalk Labs
Need help deploying Cold email write?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/10xcoldleads-cold-email-write
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing, sales, research, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/cold-email-write
What's inside
- Skill name
Cold email write- Description
- HARD RULE: ColdIQ/Braun/Voss + company research for personalization; mandatory humanizer then outbound-qc-gate before any Instantly/outbound send; always use blank-line Instantly formatting; critique bans mail-merge/pitchy/CRM-only/AI-tell/bunched openers.
- License
- MIT
- Instructions
- 71 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: only lowercase letters, digits and single hyphens allowed
- name: "Cold email write" does not match folder "cold-email-write"
Files (1)
- SKILL.md
SKILL.md (first lines)
# Cold email write (ColdIQ + Braun + Voss)
## HARD RULE (no exceptions unless the operator explicitly overrides)
Always follow proven frameworks. Frameworks beat speed.
1. **ColdIQ / Michel Lieben** — Trigger → Pain → Value → CTA; Short-Trigger; unique E1/E2/E3; shell under ~75–100 words; colleague subjects; no links in E1.
2. **Josh Braun** — Line 1 after greeting = **Think / poke QUESTION** with why-them-why-now. Conversational peer tone. Not pitchy.
3. **Chris Voss** — "If more sales calls isn't a bad outcome for you, I can show you the exact roadmap sometime next week?"
4. **Company research required** — ListKit/CRM fields alone are NOT enough. Research site/news/LinkedIn/interviews/rankings for a specific hook before writing `{{personalization}}`.
5. **Segment proof** — Josh/Plumber SEO only on confirmed 7FA.
6. **Mandatory send stack** — Before any guest/prospect/public Instantly or outbound send: run [humanizer](sand-workflow:humanizer), then [Outbound QC gate](sand-workflow:outbound-qc-gate), then send (plus [Instantly no double-send](sand-workflow:instantly-no-double-send) on replies). Humanizer is not optional. AI tells like "stands out" are fails.
7. **Line spacing (ALL cold emails, always)** — Never ship bunched text. Every paragraph / sentence beat gets its own block with a blank line between. Instantly HTML uses `<div>line</div><div><br /></div><div>next</div>` (never smash into one div or one newline-less string). Plain text uses real blank lines (`\\n\\n`). Signature lines can stack without a blank between name and company, but there MUST be a blank line before the signature block. Fail QC if the body looks like a single wall of text.
## Critique checklist (run on every E1 before ship)
Fail and rewrite if any:
1. **Mail-merge line 1** — swapping company+industry still works (no unique researched hook).
2. **Bio/statement opener** — "Company is the world's largest..." or about-page paste.
3. **CRM-only hook** — only used Industry/Keywords/employees with no public company research.
4. **Stale contact** — research shows person left / wrong title; remove or replace lead.
5. **Pitchy early** — "We built..." / feature dump before soft value + CTA.
6. **Framework narration** — "That gap shows up a lot for X agencies..." as scaffolding.
7. **Not conversational** — sounds like sequence software, not a peer note.
8. **Redundant lines** — line 2 only restates line 1.
9. **Vanity** — world's largest, cutting edge, first-to-market as the hook.
10. **Empty personalization**.
11. **AI stamp phrases** — stands out, stuck with me, delve, landscape, testament, pivotal, in today's world, it's not just, more than just, at its core, etc. (full list in outbound-qc-gate).
12. **Bunched formatting** — missing blank lines / smashed Instantly divs.
## Opener rule
Line 1 after `Hey {{firstName}},` MUST:
- End with `?`
- Include a **specific researched hook** (news, hire, launch, ranking, quote, handoff) inside the question
- Name the company or a fact only true for them
- Sound like something you'd send one peer, not 313
## Conversational E1 shape (ListKit / non-7FA)
Hey {{firstName}},
{{personalization}} ← researched poke question ONLY
One short peer implication (optional, not category lecture).
Soft value without "we built" (what it does for their calendar, plain).
Voss CTA (sometime next week).
Sig: use the operator-configured sender signature for this campaign.
## Instantly format
- Prefer HTML div paragraphs with `<div><br /></div>` between beats even when `text_only` is true (Instantly often stores HTML under the hood).
- Subject exact as specified; no accidental HTML in subject.
- Never paste a single multi-sentence paragraph without breaks when the beats are meant to breathe.
## E2 / E3
E2 = new angle before/after (never bump).
E3 = delegation / breakup.
## Research process before personalization
1. Open company site + recent news/LinkedIn.
2. Confirm contact still valid.
3. Pick one hook; kill vanity.
4. Write poke question; run critique checklist.
5. Humanizer → outbound-qc-gate → only then patch Instantly.
## Living rules
Update this skill same turn when the operator criticizes copy. On any quality miss: fix live artifact, then skillize via [Skillize after every miss](sand-workflow:skillize-after-every-miss).From 10xcoldleads/listkit-wizard, MIT.
More from 10xcoldleads/listkit-wizard
- 0.521score
humanizer
10xcoldleads
Use before any prospect, client, guest, public, Instantly, Slack, email, or agent-to-agent message ships.
SkillBFreshness: BClaude Code +9 - 0.516score
ListKit Zapier webhook bridge
10xcoldleads
Use when wiring ListKit replies.
SkillBFreshness: BClaude Code +9 - 0.516score
ListKit now-positive follow-up
10xcoldleads
Use when weekday ListKit follow-ups on true now-positive leads need a 3-then-4-day NEPQ cadence with full-thread context before every send.
SkillBFreshness: BClaude Code +9 - 0.516score
ListKit account audit
10xcoldleads
Use this when a new ListKit user already has an account — analyze campaigns, copy, leads, inbox, and reply path before taking over.
SkillBFreshness: BClaude Code +9 - 0.516score
ListKit campaign launch
10xcoldleads
Use when creating or extending a ListKit campaign: first-import custom-field mapping, QC, subjects/threading, and launch checklist.
SkillBFreshness: BClaude Code +9 - 0.516score
ListKit reply handler
10xcoldleads
Use when a ListKit reply lands: full-thread context, no double-send, recategorize, and reply in-product as the campaign sender.
SkillBFreshness: BClaude Code +9 - 0.513score
Outbound QC gate
10xcoldleads
Use before any prospect, client, guest, or public-facing upload/send: requires humanizer first; blocks AI stamp phrases, leaks, template mail-merge, spam, and…
SkillBFreshness: BClaude Code +9 - 0.513score
ListKit bot getting started
10xcoldleads
Use on first run: ListKit + Zapier login, paste Grok Bot webhook URL/Bearer, wire ListKit Manage webhooks (Lead category updated) to Zapier Catch Hook then…
SkillBFreshness: BClaude Code +9 - 0.513score
ListKit platform docs
10xcoldleads
Use at startup and whenever ListKit product behavior is unclear — scan official docs.listkit.io and keep platform knowledge current.
SkillBFreshness: BClaude Code +9 - 0.513score
ListKit process skillization
10xcoldleads
Use whenever running or improving ListKit work: convert recurring processes into skills, skillize after every miss, and keep recipes optimized so quality does…
SkillBFreshness: BClaude Code +9 - 0.512score
ListKit cold email personalization
10xcoldleads
Use when enriching a ListKit/CSV lead list with website-researched personalization lines via the bundled personalize.py tool (Anthropic + scrape), then QC…
SkillBFreshness: BClaude Code +9 - 0.511score
ListKit category hygiene
10xcoldleads
Use this when a ListKit lead category does not match the actual reply content, including during catcher runs and inbox sweeps.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Sep 10, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/10xcoldleads/listkit-wizard
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from 10xcoldleads
- 0.521score
humanizer
10xcoldleads
Use before any prospect, client, guest, public, Instantly, Slack, email, or agent-to-agent message ships.
SkillBFreshness: BClaude Code +9 - 0.516score
ListKit now-positive follow-up
10xcoldleads
Use when weekday ListKit follow-ups on true now-positive leads need a 3-then-4-day NEPQ cadence with full-thread context before every send.
SkillBFreshness: BClaude Code +9 - 0.516score
ListKit reply handler
10xcoldleads
Use when a ListKit reply lands: full-thread context, no double-send, recategorize, and reply in-product as the campaign sender.
SkillBFreshness: BClaude Code +9 - 0.516score
ListKit campaign launch
10xcoldleads
Use when creating or extending a ListKit campaign: first-import custom-field mapping, QC, subjects/threading, and launch checklist.
SkillBFreshness: BClaude Code +9 - 0.516score
ListKit account audit
10xcoldleads
Use this when a new ListKit user already has an account — analyze campaigns, copy, leads, inbox, and reply path before taking over.
SkillBFreshness: BClaude Code +9 - 0.516score
ListKit Zapier webhook bridge
10xcoldleads
Use when wiring ListKit replies.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Cold email write running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Cold email write skill. Agent Mart. https://agentmart.dev/skills/10xcoldleads-cold-email-write (last updated 2026-10-24)