Name: create-chart
Rating: 67.2 (1 reviews)
Author: amplitude

create-chart

Creates Amplitude charts from natural language descriptions, handling event selection, filters, groupings, and visualization choices. Use when you know what you want to measure but prefer not to build the chart manually.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

A highly actionable, well-sequenced skill with concrete tool calls, JSON templates, and validation feedback loops. Its weaknesses are redundancy across the event-discovery sections and a monolithic single-file structure with no progressive disclosure of the lengthy reference material.

Suggestions

Consolidate the repeated 'search broadly first' guidance into a single canonical statement to remove redundancy across the Planning, Event Discovery, and Workflow sections.

Move the full chart-definition JSON templates and detailed per-chart-type reference into a separate reference file (e.g., references/chart-types.md) linked from a concise overview, to reduce inline bulk.

Consider surfacing natural-language trigger phrases ('make a chart', 'plot this metric') in the description rather than relying solely on the suggest_when field.

Dimension	Reasoning	Score
Conciseness	The ~310-line body restates event-discovery guidance multiple times ('Search BROADLY first', 'broad search first', 'Use broad search terms first', 'BROAD search first') and re-explains the selection rationale, so it is mostly efficient but could be tightened.	2 / 3
Actionability	Provides concrete, copy-paste-ready tool calls (Amplitude:search, get_event_properties, query_dataset, save_chart_edits) and complete JSON definition templates with real parameters, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The 9-step workflow includes an explicit verify step and an error-recovery feedback loop (query_dataset fails → read error → fix → retry; zero results → diagnose → retry), matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	No bundle files exist and all content—full JSON definition schemas and detailed per-chart-type reference—is inline in a single ~310-line file; sections are well-organized with headers and a summary table, but reference material that could be split out is kept inline.	2 / 3
	Total	10 / 12 Passed

Description

85%

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 description with concrete capabilities and an explicit 'Use when' trigger, anchored to a distinct Amplitude niche. Its main weakness is trigger-term quality: the description relies on a situational condition rather than natural user phrases.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions—event selection, filters, groupings, and visualization choices—rather than vague language, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers both what (creates charts, handling event selection/filters/groupings/visualization) and when via an explicit 'Use when' clause, satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	The 'Use when' clause gives a situational trigger ('know what you want to measure but prefer not to build the chart manually') but lacks the natural phrases users actually say (e.g., 'make a chart', 'plot this'); those live only in suggest_when, not the description.	2 / 3
Distinctiveness Conflict Risk	Tied to a specific product niche (Amplitude chart creation) with a clear, narrow purpose, making it unlikely to conflict with other skills.	3 / 3
	Total	11 / 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.