response-drafting
Draft professional customer communications with empathy-first approach and clear next steps
Best use case
response-drafting is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Draft professional customer communications with empathy-first approach and clear next steps
Teams using response-drafting should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/response-drafting/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How response-drafting Compares
| Feature / Agent | response-drafting | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Draft professional customer communications with empathy-first approach and clear next steps
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Response Drafting Skill Summary
This guide teaches professional customer communication across various situations. The framework emphasizes **leading with empathy**, being direct and honest, and always closing with clear next steps.
## Core Framework
The recommended structure includes: acknowledgment of the situation, the core message with specifics, actionable next steps, and a warm closing. Length should match the channel -- chat needs just 1-4 sentences, while escalations can be longer if well-organized.
## Key Principles
The guidance stresses leading with empathy by acknowledging the customer's situation before jumping to solutions, and being specific by using concrete details, timelines, and names rather than vague language.
Tone should shift based on context -- celebratory for wins, urgent for outages, accountable for delays, and candid for bad news. The relationship stage matters too: new customers need more formality and context, while established ones warrant warmth and efficiency.
## Writing Standards
Use active voice and personal ownership ("we'll investigate"), avoid jargon, and never deflect blame. Include specific people and dates rather than vague language. The skill provides templates for common scenarios: bug reports, billing issues, rejected features, and outages.
## Escalation Guidance
Know when to escalate to managers (cancellation threats, policy exceptions) versus engineering teams (critical bugs, feature gaps). The document includes a structured escalation format for clarity and urgency tracking.Related Skills
parallel-plan-drafting-worktrees
Draft multiple follow-up GitHub issue plans in parallel using isolated git worktrees plus background Codex print-mode runs, while keeping governance-safe boundaries and avoiding shared-file contention.
canned-responses
Generate templated responses for common legal inquiries and identify when situations require individualized attention
core-context-management-response-format-rules
Sub-skill of core-context-management: Response Format Rules (+3).
rag-system-builder-streaming-responses
Sub-skill of rag-system-builder: Streaming Responses.
canned-responses-use-when
Sub-skill of canned-responses: Use When (+6).
canned-responses-escalation-triggers-all-categories
Sub-skill of canned-responses: Universal Escalation Triggers (Apply to All Categories) (+2).
canned-responses-template-organization
Sub-skill of canned-responses: Template Organization (+1).
canned-responses-step-1-define-the-use-case
Sub-skill of canned-responses: Step 1: Define the Use Case (+6).
canned-responses-required-customization
Sub-skill of canned-responses: Required Customization (+2).
canned-responses-1-data-subject-requests-dsrs
Sub-skill of canned-responses: 1. Data Subject Requests (DSRs) (+6).
prompt-engineering-response-format
Sub-skill of prompt-engineering: Response Format.
langchain-6-streaming-responses
Sub-skill of langchain: 6. Streaming Responses.