Kai Sdr Reply Triage logo

Kai Sdr Reply Triage

Community
cgallic
kai-sdr-reply-triage

Triage SDR replies and turn inbound responses into safe next actions, CRM handoff notes, suppression updates, objection responses, referrals, and meeting prep triggers. Use when "SDR reply", "triage replies", "outbound replies", "interested reply", "objection reply", "not interested", "unsubscribe", "wrong person", "bounce", "sales follow-up", "booked meeting", or any request to classify and respond to sales development replies.

Overview

Publishercgallic
Repositorykai-cmo-harness
Skill namekai-sdr-reply-triage
Stars
61
Forks
8
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by cgallic on GitHub. Read the source before you install it.

Installation

Install the Kai Sdr Reply Triage AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/cgallic/kai-cmo-harness/tree/main/harness/skills-v2/kai-sdr-reply-triage
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/cgallic/kai-cmo-harness.git /tmp/kai-cmo-harness
mkdir -p .claude/skills
cp -r /tmp/kai-cmo-harness/harness/skills-v2/kai-sdr-reply-triage .claude/skills/kai-sdr-reply-triage
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kai Sdr Reply Triage in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Kai Sdr Reply Triage on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Kai Sdr Reply Triage is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

kai-sdr-reply-triage — Reply Loop

Kai root note: knowledge/, harness/, and scripts/ paths in this skill live in the Kai install, not the user's project. Resolve them against the first ancestor directory of this SKILL.md that contains a knowledge/ folder (the Kai plugin root, ~/.claude/kai, or the kai-cmo-harness repo). MARKETING.md, memory/, and any output files live in the current project. If a referenced scripts/ command is not available in this install, say so, skip it, and continue with the file-based guidance — never fabricate its output.

Objective

Every inbound reply ends up as a triage record that names exactly one category, the consent and suppression consequence, the next safe action with an owner, and — only where it is allowed — a drafted response. The record makes the state change explicit: what this reply did to consent, suppression, routing, meeting status, objection state, and CRM state.

The risk this skill exists to remove is a reply that gets answered when it should have been suppressed, escalated, or left alone.

Done when

Work type internal-research — floor E2/C2/O0 (harness/eco-floors.yaml). The triage record itself never leaves the workspace.

  • E2 — the reply record exists at its package path and satisfies harness/skill-contracts/sdr-reply-triage.yaml.
  • C2 — banned_word_check passes; category, risk tier, suppression action, and evidence fields are all populated.
  • O0 — no outcome obligation on the record.

Sending the drafted response is separate work at the cold-email floor E5/C4/O3: provider send receipt plus suppression-list reconciliation, and CAN-SPAM/GDPR/CASL identity, opt-out, and consent basis verified before send.

Constraints

  • Missing context means a hold, not a draft. Without sender identity, suppression list, message history, and source evidence for the contact, write a triage hold note instead of a send-ready response.
  • Honor opt-outs immediately. Suppress globally; draft nothing beyond an opt-out confirmation where one is required.
  • Do not argue with complaints. Stop the sequence, suppress, route to a human owner.
  • Do not reply to bounces. Mark the contact path invalid and block follow-up on that address.
  • No invented context — no prior relationship, no new claims without evidence.
  • Sensitive, legal, or regulated replies do not get routed without human review.
  • No CRM mutation. Notes, tasks, and field changes are proposals.
  • Under 120 words unless the user asks for a longer sales response. One CTA, one next action.
  • Memory candidates carry a Do not promote until condition and stay unpromoted until it is met.

Categories — classify exactly one primary:

CategoryAction
interestedPrepare meeting handoff and short response. Trigger /kai-sales-meeting-prep.
objectionIdentify objection type and draft one respectful response.
referralCapture referred person, source, and permission trail.
not_nowDraft low-pressure close and future reminder task.
wrong_personAsk for routing only when appropriate. Do not pressure.
opt_outSuppress globally. Do not draft further outreach except opt-out confirmation if required.
bounceMark invalid contact path and block follow-up on that address.
complaintStop sequence, suppress, and route to human owner.
unsubscribe_confirmedRecord suppression and no further action.
needs_human_reviewUse for legal, regulated, sensitive, hostile, ambiguous, or high-value replies.

Context

NeedLoad
Record structure, required fields, gate thresholdsharness/skill-contracts/sdr-reply-triage.yaml
Package schema, ledger status values, memory ledgerharness/skill-contracts/sdr-package.yaml
Opt-out, sender identity, consent, suppression lawharness/references/cold-email-rules.md
Account row, contact row, source evidence, message history, suppression stateworkspace/sdr-operator/<package-slug>/
Booked meeting or buying conversation follow-on/kai-sales-meeting-prep

Output goes to workspace/sdr-operator/<package-slug>/replies/<reply-id>.md. Same path as v1 — downstream tooling does not branch on version.

Trigger /kai-sales-meeting-prep when the reply implies a meeting, demo, call, referral intro, or buying conversation.

Escalate when

  • The reply is legal, regulated, sensitive, hostile, ambiguous, or high-value — category needs_human_review, no draft.
  • Consent basis or suppression state for the contact cannot be established.
  • The reply disputes a claim made in the original outbound message.
  • The safe next action requires a live send, CRM mutation, or calendar action and no approver is named.
  • Reply content contradicts the source evidence the account was built on.

Frequently asked questions

What does the Kai Sdr Reply Triage AI skill do?

Triage SDR replies and turn inbound responses into safe next actions, CRM handoff notes, suppression updates, objection responses, referrals, and meeting prep triggers. Use when "SDR reply", "triage replies", "outbound replies", "interested reply", "objection reply", "not interested", "unsubscribe", "wrong person", "bounce", "sales follow-up", "booked meeting", or any request to classify and respond to sales development replies.

Why use Kai Sdr Reply Triage on TypingMind?

Because you install it once and use it with any model. Kai Sdr Reply Triage is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Kai Sdr Reply Triage in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cgallic/kai-cmo-harness/tree/main/harness/skills-v2/kai-sdr-reply-triage. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Kai Sdr Reply Triage?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Kai Sdr Reply Triage?

As many as you like. As long as a model supports skills, you can use Kai Sdr Reply Triage with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Kai Sdr Reply Triage AI skill free?

It is published on GitHub by cgallic. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇