cold-outreach
Skill0 starsChanged 7 months agoMITView on GitHub
Complete cold outreach workflow: company selection from the database, target-region expansion research, contact population with the 3-element 'Why Right Person' formula, unique-insight development, and 70-90 word message drafting with individual file creation. Includes batch processing (50% time reduction) and Sales Pipeline + Interaction record creation. Use when starting outreach campaigns or processing multiple companies.
30 other projects use a version of this.
Adopted by
Most recently taken up by
- Marchenko-sales/ai-sales-skillstheir own version, first seen Nov 16, 2026
- superagi/skillstheir own version, first seen Nov 15, 2026
- aronhy/marketing-skill-hubtheir own version, first seen Nov 8, 2026
- brittanyslay/marketing-skillstheir own version, first seen Nov 5, 2026
- vijaysuperpositionist/skillstheir own version, first seen Nov 1, 2026
- Maudeunfledged834/startup-founder-skillstheir own version, first seen Oct 25, 2026
Used with
Projects with it also use lead-qualify, yt-search and 9 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.
kronus-techSkilllead-qualify
Score and qualify an inbound lead based on budget, timeline, technical fit, and engagement signals. Auto-invoked when user says "qualify this lead", "score this lead", "is this worth pursuing".
Also in 3 projects that use this
azuma520Skillyt-search
Search YouTube videos, get video metadata, and download subtitles/transcripts using yt-dlp. Use when the user wants to find videos, search YouTube, look up a YouTube channel, get video info, download captions, grab subtitles, or extract a transcript. Triggers include "找影片", "搜影片", "YouTube 搜尋", "抓字幕", "逐字稿", "search videos", "find videos on YouTube", "get subtitles", "video transcript", "youtube tutorial", "watch video about", "影片推薦", "有沒有影片", "教學影片". Make sure to use this skill whenever the user mentions YouTube, video search, subtitles, or transcripts — even if they don't explicitly say "yt-search".
Also in 3 projects that use this
aiskilloftheweekSkillproposal-generator
Turns raw notes from a client conversation (call notes, transcript, email thread, brief, voice memo) into a ready-to-send proposal, quote or offer, with the problem in the client's own words, clear scope and exclusions, a specific price, a risk reducer, an expiry date and one dated next step. Use whenever the user needs to write, draft, finish or review a proposal, quote, estimate, offer, bid, statement of work or "preventivo", or says things like "the client asked for a quote", "turn these notes into a proposal", "I need to send them an offer". Works for any industry, offer type and client type.
Also in 3 projects that use this
claude-office-skillsSkillemail-marketing
Email marketing automation - campaign creation, sequence building, A/B testing, deliverability optimization, and analytics
Also in 3 projects that use this
indranilbanerjeeSkillcontent-repurpose
Repurpose one content piece into 10+ channel formats with drafts and a calendar. \"repurpose this blog post\"
Also in 3 projects that use this
AnthropicSkillpitch-deck
Populates investment banking pitch deck templates with data from source files. Use when: user provides a PowerPoint template to fill in, user has source data (Excel/CSV) to populate into slides, user mentions populating or filling a pitch deck template, or user needs to transfer data into existing slide layouts. Not for creating presentations from scratch.
Also in 3 projects that use this
Other versions30 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 30
- shawnpang/startup-founder-skills★ 331same name
- aronhy/marketing-skill-hub★ 186same name
- runxhq/runx★ 97same name
- Infinite-Labs-AI/infinite-skills★ 43same name
- etrebels/claude-code-growth-os★ 23same name
- YannisKiefer/dark-psychology-skills★ 20same name
- duncan-buildroom/profit-room-skills★ 18same name
- SanketSapkal/founder-skills★ 10same name
- artguru-tech-team/claude-skills-public★ 9same name
- manfromtunis/melek-skills★ 9same name
20 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 repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- application-trackerSkill
- applySkill
- company-deep-diveSkill
- contact-populationSkill
- job-searchSkill
- meeting-prepSkill
- onboard-userSkill
- resume-tailorSkill
- session-checkpointSkill
- session-endSkill
- session-startSkill
- warm-followupSkill
The file
We split this skill into the rules it gives an agent
12 rules. 0 are common, 9 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 28 edited versions we read keep these.
9
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 76
Read why_strong_fit and recent_signals from the database.
- Very specific: line 77
Run 3-4 WebSearch queries (parametrise ${TARGET_REGION} from config/user-profile.yaml):
- Distinctive: line 82
Document insights BEFORE moving to contacts.
- Distinctive: line 84
Update the Target Companies record:
- Distinctive: line 112
Use WebSearch as the primary tool:
- Distinctive: line 133
Create all 15 Sales Pipeline + 15 Interaction records.
- Distinctive: line 157
Use the company insight from Phase 2.
- Distinctive: line 165
Create an INDIVIDUAL FILE (CRITICAL):
- Very specific: line 169
Use the message file structure from 05-file-organization-rules.md.
- Distinctive: line 171
NEVER create batch files. Each person gets their own file.
- Distinctive: line 185
Create ALL Pipeline records in ONE bulk_insert (Phase 4)
- Distinctive: line 186
Create ALL Interaction records in ONE bulk_insert (Phase 4)
“Common” is measured: kept by at least 6 in 10 of the 28 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Cold Outreach
Automated cold-outreach workflow for value-first messaging in the user's target region.
What This Skill Does
Automates the complete cold-outreach process from company selection through message creation:
- Company selection — find uncontacted companies in the database
- Target-region expansion research — WebSearch for recent partnerships/expansions
- Contact population — add 9-10 high-quality contacts per company
- Insight development — counter-intuitive insights in 15 minutes (see
operating-procedures/QUICK-INSIGHT-DEVELOPMENT-GUIDE.md) - Message drafting — 70-90 word messages with unique insights
- Database integration — create Sales Pipeline + Interaction records
- Batch processing — process 15 contacts in 45 minutes (50% time reduction)
- Individual files — ONE FILE PER PERSON (
outreach/{user-slug}/messages/company-firstname-lastname.md)
Prerequisites
Required:
- Database access via configured MCP (default
mcp__nocodb__*, base id${NOCODB_BASE_ID}). - Active user's master-experience YAML at
applications/resumes/data/{user-slug}/master-experience.yaml. - Active user's user-config YAML at
applications/resumes/data/{user-slug}/user-config.yaml. - Operating procedures at
operating-procedures/. - Multi-user: load the active user from
JOB_HUNT_USER(env var). Filter all DB queries by(user_id,eq,{active_user_id}).
MCP tools:
mcp__nocodb__*(database operations) — or whateverNOCODB_MCP_PREFIXyou set.WebSearch(company research).
Quick Start
Process 5 companies with 3 contacts each:
"Run cold outreach for 5 companies"With specific companies:
"Run cold outreach for: Acme Renewables, Globex Power, Initech AI"Complete Workflow
Phase 1: Company Selection (~5 min)
Find 5 uncontacted companies from the database.
mcp__nocodb__list_records({
base_id: "${NOCODB_BASE_ID}",
table_name: "target_companies",
where: "(sales_pipelines,eq,0)~and(user_id,eq,${ACTIVE_USER_ID})"
})Filter further by:
- Recent news (last 2 weeks)
- Strong fit with the user's
credibility_anchors[](fromconfig/user-profile.yaml) - Target region focus (from
config/user-profile.yamltarget_regions[])
Select 5 companies.
Phase 2: Target-Region Expansion Research (~20 min for all 5)
Research all companies BEFORE proceeding (batch approach).
For each company:
- Read
why_strong_fitandrecent_signalsfrom the database. - Run 3-4 WebSearch queries (parametrise
${TARGET_REGION}fromconfig/user-profile.yaml):"[Company] ${TARGET_REGION} expansion 2025 2026""[Company] ${TARGET_REGION_COUNTRIES} partnership""[Company] ${TARGET_REGION} announcement"
- Develop a counter-intuitive insight using
QUICK-INSIGHT-DEVELOPMENT-GUIDE.md. - Document insights BEFORE moving to contacts.
Update the Target Companies record:
mcp__nocodb__update_record({
base_id: "${NOCODB_BASE_ID}",
table_name: "target_companies",
record_id: "<company_id>",
data: {
why_strong_fit: "[user background + company target-region context + strategic alignment]",
recent_signals: "[date-specific expansions, Month YYYY format]",
industry: "<from config/industries.yaml>",
research_date: "2026-MM-DD"
}
})Phase 3: Contact Selection (~10 min)
Find the best 3 contacts per company (15 total).
For each company:
- Search Target Contacts:
mcp__nocodb__search_records({ base_id: "${NOCODB_BASE_ID}", table_name: "target_contacts", query: "Company Name" }) - Use WebSearch as the primary tool:
"[Company] director operations LinkedIn""[Company] engineering manager LinkedIn ${TARGET_CITY}""[Company] senior manager [technology] LinkedIn"
- Prioritise per
04-contact-selection-priorities.md:- Large (5,000+): 70-90% Directors / Senior Managers
- Medium (500-5,000): 60-80% operational roles
- Small (<500): co-founders + early hires
Batch duplicate check (ONE query for all 15):
mcp__nocodb__list_records({
base_id: "${NOCODB_BASE_ID}",
table_name: "sales_pipeline",
where: "(pipeline_name,like,%Contact1%)~or(pipeline_name,like,%Contact2%)~or...~or(pipeline_name,like,%Contact15%)",
limit: 20
})Phase 4: Database Record Creation (~10 min)
Create all 15 Sales Pipeline + 15 Interaction records.
Step 1 — bulk_insert all 15 Pipeline records (single message):
mcp__nocodb__bulk_insert({
base_id: "${NOCODB_BASE_ID}",
table_name: "sales_pipeline",
records: [ /* 15 records */ ]
})
// Capture all returned record IDs.Step 2 — bulk_insert all 15 Interaction records (single message):
mcp__nocodb__bulk_insert({
base_id: "${NOCODB_BASE_ID}",
table_name: "interactions",
records: [ /* 15 records, with target_contact_id and pipeline_entry_id from Step 1 */ ]
})Phase 5: Message Drafting + File Creation (~15 min)
For each of the 15 contacts:
- Use the company insight from Phase 2.
- Apply the 70-90 word formula (
02-message-quality-standards.md):- News Hook (5-10 words)
- Unique Insight (20-30 words)
- Evidence/Pattern (10-15 words)
- Your Credibility (10-15 words) — pull from
config/user-profile.yamlcredibility_anchors[] - Geographic Flexibility (5-10 words) — pull from
config/user-profile.yamllocationandtarget_regions[] - Soft Ask (10-15 words)
- Create an INDIVIDUAL FILE (CRITICAL):
- Location:
outreach/{user-slug}/messages/ - Format:
company-firstname-lastname.md - Example:
acme-renewables-jane-smith.md
- Location:
- Use the message file structure from
05-file-organization-rules.md.
NEVER create batch files. Each person gets their own file.
Batch Processing Optimisation
Time comparison:
- Sequential: 90-120 min for 15 contacts
- Batch: 45 min for 15 contacts
- Savings: 50%
Key efficiency rules:
- Research ALL companies first (Phase 2)
- Select ALL contacts, then batch duplicate check (Phase 3)
- Create ALL Pipeline records in ONE bulk_insert (Phase 4)
- Create ALL Interaction records in ONE bulk_insert (Phase 4)
- Draft messages together, save to individual files (Phase 5)
Quality Checkpoints
After Phase 2 (Research):
- All 5 companies have
why_strong_fitupdated - All 5 have
recent_signalswith dates - All 5 have counter-intuitive insights documented
After Phase 3 (Contacts):
- 15 contacts selected (3 per company)
- Batch duplicate check completed (no duplicates)
- Mix of Primary / Secondary priorities
After Phase 4 (Database):
- 15 Sales Pipeline records created
- 15 Interaction records created
- All linked properly (Company, Contact, Pipeline)
- All
why_right_personentries use the 3-element formula
After Phase 5 (Messages):
- 15 individual files created (NOT batch file)
- All files named:
company-firstname-lastname.md - All messages 70-90 words
- All messages include unique insights
Reference Documentation
- Full workflow:
operating-procedures/OUTREACH-OPERATING-PROCEDURE-v4.md - Insight development:
operating-procedures/QUICK-INSIGHT-DEVELOPMENT-GUIDE.md - Message examples:
operating-procedures/UNIQUE-INSIGHT-MESSAGE-EXAMPLES.md - Contact population:
operating-procedures/contact-population-plan-v3.md
Rules automatically enforced:
.claude/rules/01-database-standards.md.claude/rules/02-message-quality-standards.md.claude/rules/03-batch-operations-rules.md.claude/rules/04-contact-selection-priorities.md.claude/rules/05-file-organization-rules.md
Troubleshooting
| Issue | Solution |
| Database token-limit errors | Use search_records for target_contacts, not list_records |
Missing why_right_person context | Ensure Target Companies updated FIRST in Phase 2 |
| Created batch file instead of individual files | Create 15 separate Write calls, one per contact |
| Messages too long (>90 words) | Trim fluff, combine sentences, remove redundancy |
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.

