support-feedback-prioritization

Pull Intercom tickets and Slack support messages from the past 7 days, classify each signal, enrich with CRM data (ARR, plan, renewal), score by customer value and churn risk, and output a tiered priority report saved to Drive. Use when you need a fast, data-driven view of what support signals matter most.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Risky

Do not use without reviewing

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concrete, actionable prompt template with clear structure, held back by mild intro redundancy and the absence of a verification checkpoint for a batch operation.

Suggestions

Add an explicit verification step at the end of Step 5, e.g. confirm the SupportDigest file exists at the Drive path and that every Critical-tier item has CRM enrichment, before returning the link.

Trim the marketing-style intro paragraph since the description already states the skill's purpose, keeping the body focused on the template and setup.

Dimension	Reasoning	Score
Conciseness	The body is mostly an efficient prompt template, but the opening framing ('Turn a week of support noise into a ranked, enriched action list — in minutes.') and intro paragraph restate what the description already covers, so it could be tightened.	2 / 3
Actionability	The 5-step template gives concrete, copy-paste-ready guidance: explicit data sources, a fixed category list, specific scoring multipliers (×3 churn, ×2 enterprise), and a defined output table with named columns.	3 / 3
Workflow Clarity	The five steps are clearly sequenced, but this is a batch operation over a week of tickets with no validation/verification checkpoint (e.g. confirm the Drive file saved, confirm CRM enrichment coverage), which caps workflow clarity at 2 per the batch-operations guideline.	2 / 3
Progressive Disclosure	It is a single self-contained file with well-organized sections (Prompt Template, Setup, Placeholders, Tips) and no nested references; for a skill of this scope that needs no external references, well-organized sections earn a 3.	3 / 3
	Total	10 / 12 Passed

Description

75%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, concrete description that covers what and when with a distinct niche, weakened mainly by abstract trigger phrasing and a second-person 'Use when you' construction.

Suggestions

Replace the abstract 'Use when you need a fast, data-driven view...' with natural trigger phrasings a user would actually say, e.g. 'Use when the user says support triage, prioritize feedback, what are customers complaining about, or support digest.'

Drop the second-person 'you' (e.g. 'Use when a fast, data-driven view of support signals is needed') to keep the third-person voice throughout.

Dimension	Reasoning	Score
Specificity	The description lists concrete actions ('Pull Intercom tickets and Slack support messages... classify each signal, enrich with CRM data (ARR, plan, renewal), score... output a tiered priority report'), which would merit a 3, but the 'Use when you need...' clause is second person and incurs the required -1 specificity penalty.	2 / 3
Completeness	It explicitly answers both what (pull, classify, enrich, score, output) and when ('Use when you need a fast, data-driven view of what support signals matter most'), matching the 'clearly answers both what AND when' anchor.	3 / 3
Trigger Term Quality	'support signals' is a relevant keyword, but the trigger phrasing 'a fast, data-driven view of what support signals matter most' is abstract rather than the natural terms a user would say (e.g. 'support triage', 'prioritize feedback'), so it lands at 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The Intercom/Slack/CRM support-triage niche with ARR/churn scoring is a clear, distinct domain unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: amplitude/builder-skills
Commit: 22b0634

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.