launch-metrics

Set up measurement and tracking for product launches, run post-launch retros with data, and build a launch analytics system. Use this skill whenever someone asks to track a launch, set up UTM parameters, measure launch performance, run a launch retro, analyze launch results, or build a dashboard for a product release. Also trigger for "how do we know if the launch worked," "what should we track for this launch," "set up UTMs for the announcement," or any request about measuring or evaluating a product launch. Covers pre-launch tracking setup, UTM conventions, per-tier KPIs, benchmark expectations, and retro frameworks.

Quality

81%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

62%

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

This is a solid strategic playbook for launch measurement with good workflow structure and useful reference data (benchmarks, UTM conventions, KPI tables by tier). Its main weaknesses are moderate verbosity with some explanatory prose Claude doesn't need, and a lack of truly executable artifacts — no scripts, templates, or tool-specific configurations that would make it immediately actionable. The content would benefit from being trimmed and having some reference tables moved to companion files.

Suggestions

Remove explanatory prose Claude already knows (e.g., 'UTM parameters track where traffic comes from', 'Measurement starts before launch day') to improve conciseness.

Add executable artifacts: a UTM spreadsheet template (CSV), a sample analytics dashboard configuration, or a script that generates UTM URLs from a config file to increase actionability.

Move the benchmark tables and per-tier KPI tables into a separate BENCHMARKS.md or REFERENCE.md file, keeping only a summary in the main skill to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The skill is generally well-structured but includes some unnecessary framing ('Without consistent measurement, launches are guesswork. With it, each launch informs the next.') and explanatory text that Claude doesn't need ('UTM parameters track where traffic comes from'). The benchmark tables and KPI tables are useful reference material but the surrounding prose could be tighter.	2 / 3
Actionability	The skill provides concrete UTM examples, event tables, benchmark numbers, and retro frameworks, which are all useful. However, it lacks executable code or commands — there are no scripts for setting up dashboards, no concrete analytics platform configurations, no actual spreadsheet templates. It's more of a strategic playbook than a step-by-step executable guide.	2 / 3
Workflow Clarity	The skill presents a clear chronological workflow: pre-launch setup → launch day monitoring → post-launch retro → building launch history. Each phase has explicit steps, the retro has a defined timeline (5-7 days), and there are clear 'do/don't' guidelines for launch day. The retro section includes a feedback loop (retro output feeds into checklist updates for future launches).	3 / 3
Progressive Disclosure	The companion skills section at the bottom provides clear cross-references to related skills, which is good. However, the skill itself is quite long (~200 lines) with extensive inline tables and benchmarks that could be split into reference files. There are no bundle files to support this, and the KPI tables by tier and benchmark expectations could live in separate reference documents.	2 / 3
	Total	9 / 12 Passed

Description

100%

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

This is a strong, well-crafted skill description that excels across all dimensions. It provides specific concrete actions, comprehensive natural trigger terms including quoted user phrases, explicit 'Use this skill whenever...' guidance, and a clearly distinctive niche around product launch measurement. The description is thorough without being padded, and uses appropriate third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'set up measurement and tracking,' 'run post-launch retros with data,' 'build a launch analytics system,' plus details like 'UTM conventions, per-tier KPIs, benchmark expectations, and retro frameworks.'	3 / 3
Completeness	Clearly answers both 'what' (set up measurement, run retros, build analytics system, UTM conventions, KPIs, benchmarks, retro frameworks) and 'when' with an explicit 'Use this skill whenever...' clause plus additional trigger phrases.	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms including 'track a launch,' 'set up UTM parameters,' 'measure launch performance,' 'run a launch retro,' 'analyze launch results,' 'build a dashboard for a product release,' and natural-language phrases like 'how do we know if the launch worked' and 'what should we track for this launch.'	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche focused specifically on product launch measurement and analytics. The combination of launch-specific tracking, UTMs, launch retros, and per-tier KPIs makes it clearly distinguishable from general analytics or general product management skills.	3 / 3
	Total	12 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: amplitude/builder-skills
Commit: 221ffaa

Reviewed: about 2 months 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.