Customer Support Response Drafter skill - #222
Open
Tim (Timziito) wants to merge 2 commits into
Open
Conversation
Drafts replies to inbound customer support emails, tickets, and chats grounded in your organization's own product and policy knowledge, matched to your support tone, with refunds, exceptions, and churn risk flagged for human review.
Contributor
There was a problem hiding this comment.
Pull request overview
Adds a new submission skill, Customer Support Response Drafter, intended to help draft customer support replies grounded in an organization’s existing product/policy knowledge and aligned to a known support tone, while flagging refund/exception/churn-risk cases for human review.
Changes:
- Introduces a new
SKILL.mddefining the runtime procedure, guardrails, and tone guidance for drafting support responses. - Adds a human-facing
README.mddescribing the skill, positioning, and constraints. - Adds
metadata.jsonto register the submission (name/description/platforms/tags/author/version/dates).
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| submissions/customer-support-response-drafter/SKILL.md | Defines the agent-facing workflow and guardrails for grounded customer support drafting. |
| submissions/customer-support-response-drafter/README.md | Provides human-facing overview and usage notes for the submission. |
| submissions/customer-support-response-drafter/metadata.json | Registers the skill in the gallery with platforms/tags/author/version. |
Comments suppressed due to low confidence (1)
submissions/customer-support-response-drafter/README.md:23
- This section links to
../grounded-citation-guardrailand../hr-policy-navigator, but neither submission exists in this repo, so these links will be broken. Please remove the links or update them to valid references.
Same discipline as [`grounded-citation-guardrail`](../grounded-citation-guardrail)
and [`hr-policy-navigator`](../hr-policy-navigator): it answers product and
policy questions only from what's actually retrieved from your organization's
own knowledge sources, and says so plainly when something isn't covered
instead of guessing at a plausible-sounding answer.
Comment on lines
+11
to
+15
| [`it-support-ticket-agent`](../it-support-ticket-agent) is for *internal* IT | ||
| issues: an employee's own hardware, software, or access problem, logged as a | ||
| ticket. This skill is for *external* customer support: replying to someone | ||
| outside the organization who has a product question, a complaint, or a | ||
| request. Different audience, different job. |
Comment on lines
+22
to
+24
| factual parts of the reply. Answer product and policy questions only from | ||
| what's retrieved, the same discipline as | ||
| [`grounded-citation-guardrail`](../grounded-citation-guardrail). If |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Drafts replies to inbound customer support emails, tickets, and chats grounded in your organization's own product and policy knowledge, matched to your support tone, with refunds, exceptions, and churn risk flagged for human review.