customer-reply
Compose professional, empathetic customer-facing messages tailored to context, channel, and urgency. Activate when writing support ticket replies, outage notifications, bug acknowledgments, feature request responses, billing communications, follow-up emails, escalation updates, or any external customer correspondence that needs the right tone and structure.
What this skill does
## Foundational Communication Principles
1. **Acknowledge before solving.** Validate what the customer is experiencing before presenting answers or next steps.
2. **Front-load the key point.** Busy people skim -- put the most important information in the opening lines.
3. **Tell the truth.** Never promise what you cannot deliver, obscure problems behind jargon, or bury bad news.
4. **Be concrete.** Replace vague language with specific names, dates, and measurable commitments.
5. **Accept responsibility.** Use first-person ownership ("we caused" / "I will") rather than passive deflection ("an error occurred").
6. **End with clarity.** Every message must leave the customer knowing exactly what happens next.
7. **Mirror their emotional register.** Meet frustration with empathy; match enthusiasm with energy.
## Message Architecture
Most customer-facing replies follow four building blocks:
```
1. Recognition (1-2 sentences)
Show you understand their situation or question.
2. Substance (1-3 short paragraphs)
Deliver the answer, update, or resolution.
Be precise and include supporting details.
3. Action Items (1-3 bullets)
- Steps YOU are taking and by when
- Steps THEY may need to take
- When they will next hear from you
4. Sign-off (1 sentence)
Warm, professional close with an open door.
```
## Channel-Appropriate Sizing
- **Live chat / instant message:** 1-4 sentences. Immediate, conversational, no filler.
- **Ticket reply:** 1-3 compact paragraphs. Easy to scan with clear structure.
- **Email:** Up to 5 paragraphs. Respect their inbox -- omit anything non-essential.
- **Escalation correspondence:** Thorough as needed, but organized under headings for navigation.
- **Executive-level communication:** Concise above all else. 2-3 paragraphs, data-forward.
## Tone Calibration
| Scenario | Register | Characteristics |
|----------|----------|-----------------|
| Positive news | Warm | Congratulatory, forward-looking, genuine |
| Standard update | Friendly-professional | Informative, efficient, approachable |
| Technical explanation | Patient-precise | Structured, detailed, jargon-free |
| Delayed resolution | Accountable | Honest about the delay, specific about new timeline |
| Negative outcome | Straightforward | Direct delivery, empathetic framing, solution-oriented |
| Service interruption | Transparent-urgent | Immediate, factual, calming, action-focused |
| High-stakes escalation | Composed-executive | Ownership-forward, plan-oriented, confident |
| Financial matter | Careful-factual | Precise amounts, clear explanations, empathetic |
### Adjusting for Relationship Maturity
**Early-stage customer (first 90 days):**
- Lean toward formality and thoroughness
- Provide extra context rather than assuming familiarity
- Proactively surface helpful resources
- Prioritize responsiveness to build confidence
**Long-standing customer:**
- Warmer, more conversational register
- Reference shared context and past interactions
- Communicate more directly and efficiently
- Demonstrate awareness of their business objectives
**Upset or escalated customer:**
- Lead with genuine empathy and validation
- Respond with urgency in both speed and substance
- Provide specific, time-bound action plans
- Shorten the feedback loop between updates
## Language Standards
**Prefer:**
- Active voice: "We are investigating" rather than "This is being investigated"
- Personal pronouns: "I" for individual commitments, "we" for team actions
- Named individuals: "Jordan on our infrastructure team will..." builds trust
- Customer vocabulary: adopt their terminology instead of internal labels
- Absolute dates: "by Wednesday March 18" instead of "in a few days"
- Visual structure: headers and bullet points in longer messages
**Avoid:**
- Corporate filler: "synergy," "leverage," "circle back," "paradigm"
- Blame redirection: never point fingers at other departments, vendors, or "the system"
- Ownership-dodging passive voice: "mistakes were made" hides accountability
- Excessive hedging: too many qualifiers erode confidence
- Unnecessary recipients: only loop in people who need to participate
- Overuse of exclamation marks: one per message at most
## Situational Message Frameworks
### Acknowledging a Defect Report
```
Hi [Name],
Thanks for flagging this -- I understand that [concrete impact] is
disrupting your work.
I have confirmed the problem and raised it with our engineering team
at [severity]. Here is what we know at this point:
- [Current understanding of the behavior]
- [Root cause, if identified]
- [Workaround, if one exists]
I will follow up by [date/time] with a timeline for the fix.
[Workaround details if applicable.]
Please reach out if you notice any additional effects.
Best,
[Name]
```
### Addressing a Billing or Account Problem
```
Hi [Name],
Thanks for getting in touch -- I understand that billing concerns
deserve fast answers.
After reviewing your account, here is what I found:
- [Factual summary of what occurred]
- [How it affected charges, access, or service]
To correct this, I am taking these steps:
- [Remediation action with expected timeline]
- [Additional action if needed]
[If already resolved: "The adjustment is complete and should appear
within [window]."]
[If still in progress: "I have escalated this to our billing team
and will update you by [date]."]
Sorry for the hassle. Let me know if anything else on your account
looks off.
Best,
[Name]
```
### Declining a Feature Request
```
Hi [Name],
Thanks for this suggestion -- I see why [capability] would be
useful for [their scenario].
After discussing with our product team, this is not on our near-term
roadmap. The main reason is [straightforward, respectful rationale].
That said, here are some paths that might get you close to your goal:
- [Alternative 1]
- [Alternative 2]
- [API/integration option if relevant]
Your request is captured in our feedback pipeline, and I will let you
know if our plans shift.
Would any of these alternatives work for your team? Happy to explore
them further.
Best,
[Name]
```
### Communicating During an Incident
```
Hi [Name],
I am reaching out because an issue with [affected service/feature]
is impacting functionality your team depends on.
**What is happening:** [Plain-language explanation]
**Effect on your usage:** [Their specific impact]
**Current status:** [Investigating / Cause identified / Fix deploying / Resolved]
**Expected resolution:** [Time estimate or update cadence]
[If applicable: "As a temporary measure, you can [workaround]."]
I am monitoring this directly and will update you when we have
progress. Live status is also available at [status page URL].
I apologize for the disruption. [Mention prevention steps if known.]
[Name]
```
### Re-engaging After No Response
```
Hi [Name],
Just circling back -- I sent [description] on [date] and want to
make sure it reached you.
[One-sentence recap of what is pending or offered.]
If the timing is not right, no problem at all -- let me know a
better window and I will reconnect then.
Best,
[Name]
```
## Contextual Personalization
### Newer Customers
- Supply additional background and explanation
- Point to onboarding resources and getting-started material
- Introduce self-service options proactively
### Experienced Customers
- Skip foundational explanations they already possess
- Acknowledge their depth of product knowledge
- Get to the point quickly and efficiently
### Customers Under Stress
- Prioritize empathy and acknowledgment above all
- Center the reply around resolving their specific problem
- Offer tangible action plans with committed deadlines
- Provide a direct path to further escalation if needed
## Follow-up Timing Reference
| Context | Recommended Follow-up Window |
|---------|------------------------------|
| Unanswered question from customer | 2-3 business days |
| Active support issue (high severity) | Daily or more frequently per SLA |
| Active supRelated in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.