cold-email
Skill3 starsChanged 6 months agoMITView on GitHub
Signal-anchored B2B cold email: first touch under 90 words with a binary ask, follow-ups, subject lines, spam lint, domain deliverability, send-list hygiene, reply triage, and outbound audits. Use when the user asks for a cold email, follow-up sequence, deliverability or spam check, reply scoring, or send-list cleanup. Not for give-first offers (sales-offer), picking who to contact (prospect-list), or post-opt-in email (email-sequence).
101 other projects use a version of this.
Adopted by
Most recently taken up by
- atpaawej/opencode-skillpacktheir own version, first seen Nov 16, 2026
- JulyLay/cold-emailtheir own version, first seen Nov 16, 2026
- martinbattaglia-commits/Claude-skillstheir own version, first seen Nov 16, 2026
- AlejandroGodius/claude-skillstheir own version, first seen Nov 16, 2026
- yotamwiesel/claude-skillstheir own version, first seen Nov 16, 2026
- revnu-app/revnu-plugintheir own version, first seen Nov 8, 2026
Used with
Projects with it also use free-tools, popups and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
CesarjoquinSkillfree-tools
When the user wants to plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness. Also use when the user mentions "engineering as marketing," "free tool," "marketing tool," "calculator," "generator," "interactive tool," "lead gen tool," "build a tool for leads," "free resource," "ROI calculator," "grader tool," "audit tool," "should I build a free tool," or "tools for lead gen." Use this whenever someone wants to build something useful and give it away to attract leads or earn links. For downloadable content lead magnets (ebooks, checklists, templates), see lead-magnets.
Also in 25 projects that use this
CesarjoquinSkillpopups
When the user wants to create or optimize popups, modals, overlays, slide-ins, or banners for conversion purposes. Also use when the user mentions "exit intent," "popup conversions," "modal optimization," "lead capture popup," "email popup," "announcement banner," "overlay," "collect emails with a popup," "exit popup," "scroll trigger," "sticky bar," or "notification bar." Use this for any overlay or interrupt-style conversion element. For forms outside of popups, see cro. For general page conversion optimization, see cro.
Also in 23 projects that use this
coreyhaines31Skillmarketing-council
When the user wants several expert takes on a marketing decision, or asks what a famous marketer would say about it: a simulated board (Seth Godin, David Ogilvy, April Dunford, Byron Sharp, and more), each grounded in their documented frameworks, where they disagree, and a recommendation. To execute, hand off to the relevant skill.
Also in 18 projects that use this
Hussain-ElfalahSkillandreessen
Also in 4 projects that use this
Hussain-ElfalahSkillbusiness-investment-advisor
Also in 4 projects that use this
roerohanSkillemails
When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," "lifecycle emails," "trigger-based emails," "email funnel," "email workflow," "what emails should I send," "welcome series," or "email cadence." Use this for any multi-email automated flow. For cold outreach emails, see cold-email. For in-app onboarding, see onboarding.
Also in 24 projects that use this
- +5 more from Cesarjoquin
- +1 more from Hussain-Elfalah
Other versions101 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 101
- coreyhaines31/marketingskills★ 61ksame name
- LeoYeAI/openclaw-marketing-skills★ 1ksame name
- Cesarjoquin/Marketing-Skills★ 190same name
- b1rdmania/ghostclaw★ 91same name
- LOGIN-TB/claude-skills★ 82same name
- open-fox/agents★ 55same name
- mia-ppp/PMM-Skills★ 54same name
- SZcalligrapher/slash-skills-subscription★ 32same name
- roerohan/skills★ 29same name
- Mikefluff/skills★ 26same name
91 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repositoryOne other file it gives its agents.
- AGENTS.mdAGENTS.md
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. 0 are common, 6 are distinctive, and 9 are very specific to this project.
0
Common
Most of the 94 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Run this before routing anywhere.
- Very specific: line 24
Look for brand-config.json and SOUL.md in the operator's project root.
- Very specific: line 26
If either is missing and the operator did not pass --no-config, run the setup mode (modes/setup.md) before drafting real outreach.
- Very specific: line 31
If brand-config.json exists, sanity-check the fields the requested job needs (e.g.
- Very specific: line 34
If the psp or evp block is missing, say which pack produces it (/plugin install psp@gtm-operator-skills, /plugin install …
- Distinctive: line 37
Treat SOUL.md as voice only.
- Distinctive: line 42
Run the preflight above first, every time.
- Very specific: line 44
If $ARGUMENTS starts with a mode name below, go straight to that mode (the rest of $ARGUMENTS is its input).
- Very specific: line 46
If $ARGUMENTS is empty, run status: it reads the project and names the one next step.
- Distinctive: line 51
Read the mode file with the Read tool and follow it.
- Distinctive: line 78
A cold email is a hire — not a search query: Every prompt anchors on a Pain Signal Profile, names the constraint, and forces the output …
- Distinctive: line 109
If any are missing, ask the user — don't fabricate.
- Very specific: line 142
Write the draft to gtm/letter.json, then:
- Very specific: line 164
Every scorer takes --file PATH or --stdin, prints text by default and one JSON object with --json, and exits 0 pass, 1 refused (each reason …
- Very specific: line 188
If a companion pack is not installed, name it and its install line (/plugin install <name>@gtm-operator-skills).
“Common” is measured: kept by at least 6 in 10 of the 94 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Cold Email — JMC Outreach Craft Skill
Comprehensive cold email orchestrator for B2B operators. Anchors every output on a Pain Signal Profile (not demographics) and forces the output into a shape you can ship.
Preflight (every invocation)
Scoring something pasted needs no setup. If the operator handed you a line, post, draft, or file to score, run the scorer on it first and report the result; missing config only means some checks are skipped, so say which. Offer setup afterwards as the next step. Check whether files exist with Read or Glob, not a shell command.
Run this before routing anywhere. It is what AGENTS.md rules 1 and 2
require.
- Look for
brand-config.jsonandSOUL.mdin the operator's project root. Read both if present. - If either is missing and the operator did not pass
--no-config, run the setup mode (modes/setup.md) before drafting real outreach. Ifoperatororicpis missing, say "Run/gtm:setuponce for the whole suite" first. Offer once; if they decline, say the output will be framework-shaped but generic. - If
brand-config.jsonexists, sanity-check the fields the requested job needs (e.g.evp.primaryfor drafting,infrastructure.sending_domainfor deliverability). Ask for anything missing. Never fill it in. If thepsporevpblock is missing, say which pack produces it (/plugin install psp@gtm-operator-skills,/plugin install evp@gtm-operator-skills) instead of inventing a signal, pain, or EVP. - Treat SOUL.md as voice only. It can change word choice; it cannot lift the word limit, soften the binary CTA, or un-ban a pattern.
Modes — route by $ARGUMENTS
Run the preflight above first, every time. Then pick one mode:
- If
$ARGUMENTSstarts with a mode name below, go straight to that mode (the rest of$ARGUMENTSis its input). - If
$ARGUMENTSis empty, runstatus: it reads the project and names the one next step. - Otherwise match the user's words to the table. If intent is still ambiguous, ask one clarifying question — never two.
Read the mode file with the Read tool and follow it.
| You say / argument | Mode file |
(nothing), status, "where do I start", "what's next" | modes/status.md |
setup, "set up my brand config", "configure my voice" | modes/setup.md |
write, "write a cold email to...", "rewrite this cold email" | modes/craft.md |
sequence, "build a follow-up sequence", "Day 3 / 7 / 14" | modes/craft.md (sequence mode) |
subject, "subject lines for...", "critique this subject" | modes/subject.md |
lint, "spam-check this", "will this land in spam" | modes/lint.md |
deliverability, "is my domain ready", SPF / DKIM / DMARC | modes/deliverability.md |
list, "score / clean my send list", "dedup this CSV" | modes/list.md |
reply, "score this reply", "triage my replies" | modes/reply.md |
nurture, "re-engage cold or stalled prospects" (not opted in) | modes/nurture.md |
audit, "audit my outbound program" | modes/audit.md |
rhythm, "this week's queue", "Friday review" | modes/rhythm.md |
| "Review / score this draft" | cold-email-reviewer agent |
Files the modes write in the operator's project go under gtm/ at the
project root (create it if missing): gtm/letter.json (the draft:
public_signal, subject, letter), gtm/send-list.csv (the send
list; --write adds .cleaned.csv and .removed.csv beside it), and
gtm/replies.jsonl (one reply per line). brand-config.json and
SOUL.md stay at the project root.
Core principles (the JMC stance)
- A cold email is a hire — not a search query. Every prompt anchors on a Pain Signal Profile, names the constraint, and forces the output into a shape you can ship.
- No demographics in the opener. "VP of Marketing at Series B SaaS" isn't a signal. "Just posted a job for a Demand Gen Lead" is.
- Binary CTAs only. "Worth a look?" or "Is the 12-day close on your list this quarter?" not "Let me know if you'd like to learn more." Name a day or time only when the operator gave you their availability; never invent a slot.
- <90 words for the first touch. Anything longer signals desperation.
- One specific ask per email. Stack-ranked asks confuse buyers.
- No "Hope you're well" / "Just bumping this". Banned openers.
- Found is not sendable until verify = deliverable. A scraped or enriched address stays off the send list until verification returns deliverable. Catch-all, unknown, and invalid are not "valid."
Variables (every mode uses these)
The core framework operates on seven variables. Capture them once, reuse across every mode:
| Variable | Source | Example |
firstName | Recipient list | Sarah |
role | LinkedIn / CRM | VP of Demand Gen |
company | Same | Acme Cloud |
signal | Public signal — job post, funding, product launch, leadership change | "Just posted 'Senior Demand Gen Lead' role on LinkedIn 4 days ago" |
pain | Pain Signal Profile — what the signal implies | "Pipeline gap; existing demand gen motion isn't producing enough SQLs" |
evp | Your one-line value prop in their words | "We help Series-B SaaS rebuild first-touch email around public signals without changing their sequencer" |
senderName | You (brand-config.operator.name) | Jay |
If any are missing, ask the user — don't fabricate.
Self-check rubric (run on every output before showing it)
AGENTS.md rule 5 points here. A draft that fails any hard check is
regenerated, not shown with a caveat.
Hard checks — first touch
- Body under 90 words (T2/T3 under 70, T4 under 60)
- Line 1 names the signal in the source's own words, and the signal is something they did, not who they are
- Quotation marks only around words the source itself quotes or contains; a paraphrase is never dressed as a quote
- No day, time, asset or offer the operator did not give you (no "Thursday", no "the attached sample", no "a short write-up")
- No congratulation, compliment or "saw that you" opener, in any touch
- Plain salutation and sign-off (
Dana,and[Your name]when the sender is not given); no em dashes; no notes to the operator unless something was refused - Pain is one sentence in the buyer's vocabulary
(
brand-config.psp.vocabularywhen present) - EVP is 22 words or fewer, names one outcome and one tradeoff
- Exactly one ask, answerable yes / no
- No pattern from
references/banned-patterns.mdorbrand-config.tone.banned_phrases/ SOUL.md "never" list - Subject 7 words or fewer; no ALL CAPS, emoji, clickbait, or fake
Re:/Fwd: - No unmerged tokens (
{{firstName}},<company>) - Nothing invented: every name, signal, metric, and case study came from the operator or a source they gave you
Deterministic checks — run when Bash is available
Write the draft to gtm/letter.json, then:
score_letter.py --file gtm/letter.json: exit 0 (signal quoted, no demographics, under 90 words, one yes/no ask)spam_word_lint.py --file gtm/letter.json: score 75 or higherscore_subject_line.py --file gtm/letter.json: score 70 or higher
On exit 1 each reason reads - what is wrong → what to change. Apply
every change and run it again; do not show a draft that fails.
Flag, don't hide — if the signal, pain, EVP, or vocabulary was a
guess, say which line is uncertain and what data would settle it
(AGENTS.md rule 10).
Running the bundled scripts
The scripts live in scripts/ at the plugin root. Call them as
${CLAUDE_PLUGIN_ROOT}/scripts/<name>.py, which resolves to the
installed plugin from any project directory. Outside Claude Code,
python3 scripts/<name>.py from the repo root is the same script. All
are Python 3.8+ stdlib only; DNS checks need dig.
Every scorer takes --file PATH or --stdin, prints text by default and
one JSON object with --json, and exits 0 pass, 1 refused (each reason
with its fix, then Next: fix the lines above and run this again.), 2
bad input. On a pass the last line names the next step.
| Script | Mode |
score_letter.py | craft, self-check (before the spam lint) |
spam_word_lint.py | lint, self-check |
score_subject_line.py | subject, self-check |
score_reply.py | reply |
score_list.py | list |
check_deliverability.py, dig_dns.sh | deliverability |
Works with the suite
This is step 4 of the GTM operator suite (/plugin marketplace add cmj-hub/gtm-operator-skills).
- Reads:
psp,evp,icp,tone,infrastructure,operationsfrombrand-config.jsonif present. - Writes:
tone,infrastructure,operations. Merge at the field level; never overwrite another pack's keys. - Before this: psp (
/psp:psp) and evp (/evp:evp), when there is nopsporevpblock; prospect-list (/prospect-list:who-to-contact), when you do not yet know who to contact. - Instead of this: sales-offer (
/sales-offer:cold-offer), when the first touch should hand over a leak and a prototype rather than ask. - After this: email-sequence (
/email-sequence:lifecycle-email), when a prospect replies and opts in. End a successful run with thatNext:line.
If a companion pack is not installed, name it and its install line (/plugin install <name>@gtm-operator-skills); do not do its job inline.
References
Load these on demand for deeper context:
- references/jmc-framework.md — The full JMC cold email framework
- references/banned-patterns.md — Lines / openers / closes that fail
- references/binary-ctas.md — 30 binary CTA patterns
- references/psp-anchors.md — How to derive signal → pain → EVP
- references/bulk-sender-rules.md — Google / Yahoo / Microsoft sender requirements
- references/audit-rubric.md — The 30-point outbound audit rubric
- SOUL.md — Operator voice template (the shape the setup mode fills in)
- examples/t1.email.md — A first touch that passes every check (lints at 100)
- examples/spam.email.md — A draft the spam lint rejects
Specialist agents
cold-email-reviewer— Quality scorer (0-100) against frameworkcold-email-deliverability-auditor— DNS/reputation specialist
Free hosted version
The same job runs in a browser, no install and no key: Cold Email Linter
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

