sdr-humanizer

Rules for rewriting AI-generated sales messages so they sound like natural English conversations, with pacing and tone suited to the customer and channel.

In plain words
What is it for?
Use them to shape customer replies, vary message length, add appropriate conversational wording, control delays and typing indicators, and optionally handle bilingual operator self-chat.
Why use it?
They reduce stiff, overly polished messages and help keep sales conversations readable and human.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/ipythoning/b2b-sdr-agent-template/sdr-humanizer
Any agent
npx skills add iPythoning/b2b-sdr-agent-template --skill sdr-humanizer
Clone the repo
git clone --depth 1 https://github.com/iPythoning/b2b-sdr-agent-template

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 633 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00633
Opus 5 $0.00000 $0.00316
Sonnet 5 $0.00000 $0.00127
Haiku 4.5 $0.00000 $0.00063

Measured 2d ago against content hash 75a13a93f69e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdr-humanizer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/sdr-humanizer/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sdr-humanizer — Human-Like Conversation Rules

Transform AI-generated sales messages into natural, human-like conversations that build trust and rapport.

Core Principles

1. Message Pacing

  • Never send walls of text — break into 2-3 short messages
  • Add 2-5 second delays between consecutive messages
  • Use voice messages occasionally (if channel supports)
  • Vary message length: mix short (1 line) with medium (3-5 lines)

2. Typing Indicators

  • Simulate typing time proportional to message length
  • Short reply (< 20 words): 2-4 seconds
  • Medium reply (20-50 words): 5-10 seconds
  • Long reply (50+ words): 15-30 seconds

3. Language Patterns

  • Always reply to customers in English — consistent, professional, globally understood
  • Operator self-chat sync (opt-in): If operator_bilingual: true is set in IDENTITY.md, send a Chinese translation via self-chat after each English reply (WhatsApp "Message to myself"). Disabled by default.
  • Use contractions and informal grammar when appropriate
  • Include occasional filler words: "actually", "by the way", "just wanted to"
  • Match the customer's formality level in English
  • Avoid perfect grammar in casual channels (WhatsApp)
  • Use emoji sparingly — max 1-2 per message, contextually appropriate

4. Response Timing

  • Don't reply instantly to every message (feels robotic)
  • Business hours: 1-5 minute response time
  • After hours: Reply next morning with "Sorry, just saw this"
  • Weekend messages: Acknowledge Monday morning
  • Exception: CTWA ad leads → reply within 5 minutes (golden window)

5. Conversation Flow

  • Ask one question at a time — never stack 3+ questions
  • Reference previous conversations: "Last time you mentioned..."
  • Show genuine curiosity about their business
  • Share relevant market insights proactively
  • Use the customer's name naturally (not every message)

6. Cultural Adaptation

Region Style
Middle East Warm greetings, relationship-first, patient
Southeast Asia Polite, indirect, respect hierarchy
Latin America Friendly, enthusiastic, personal touch
Europe Professional, data-driven, respect privacy
Africa Community-oriented, trust-building, flexible

Read the full file on GitHub · 67 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 67 lines · 0 tokens per session scan A 75a13a93f69e

Subscribe to this mod's changes

sdr-humanizer is a skill published in the GitHub repository iPythoning/b2b-sdr-agent-template (170 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 633 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

forward-deployed-selling

Operating doctrine for AI-era enterprise sales. Use when an agent works on accounts, deals, outreach, coaching, or pipeline — any revenue-affecting decision.

vonarmen-wq/forward-deployed-selling · 37 tokens

event-outbound

Create validated, buyer-first email and LinkedIn outreach sequences for B2B conferences and trade shows, from pre-event through post-event. Use when asked to build attendee outreach, cold emails, LinkedIn cadences, side-event or dinner invitations, booth follow-up, or an event-plus-ICP campaign intended to book…

luminik-io/event-outbound-skill · 69 tokens

cold-email-onboarding

First-run interactive setup for the cold-email skill pack. Walks the operator through brand-config.json (ICP, PSP, EVP, tone, infrastructure) and SOUL.md (voice fingerprints, banned phrases, stories you lean on) in 10 minutes. Refuses to let the operator skip — generic output is worse than no output. Loaded…

cmj-hub/claude-cold-email · 91 tokens

cold-email-kickoff

Adaptive router for the cold-email skill pack. Detects the operator's current state (brand-config present? SOUL.md present? infrastructure ready? PSP defined? EVP locked? first campaign run?) and picks the next-best step. Loaded by the main cold-email skill on bare invocation ("/cold-email") or when the operator asks…

cmj-hub/claude-cold-email · 99 tokens

cold-email-list-quality

Score a cold-email prospect list 0-100 across dedup, role-fit (vs brand-config.icp), signal freshness, email-validity heuristics, exclusion-criteria match, and company-stage match. Returns the score, list of rows to remove, and a fix recommendation. Loaded by cold-email-weekly-rhythm on Monday's list refresh. Operates…

cmj-hub/claude-cold-email · 88 tokens

cold-email-reply-scoring

Classify replies to cold email into 4 categories — buy-signal, positive, neutral, not-interested — using deterministic features (intent keywords, time-to-reply, length, question count, calendar/asset asks). Routes each reply per brand-config.operations.replyrouting. Backed by a Python script that uses regex + features…

cmj-hub/claude-cold-email · 94 tokens