CtrlK
BlogDocsLog inGet started
Tessl Logo

analyze-chart

Performs deep analysis of a specific Amplitude chart to explain trends, anomalies, and likely drivers. Use when a metric looks unusual, investigating a spike or drop, or understanding the "why" behind numbers.

71

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The body is a lean, well-sequenced investigation workflow with explicit validation checkpoints and concrete tool calls. Its main gap is actionability: the central analysis steps are routed through unlinked, unexplained bolded procedure names rather than self-contained instructions or file references.

Suggestions

Resolve the bolded procedure references ("Reading chart data", "Analyzing chart", "Finding the right event properties", "Getting experiments", "Getting deployments", "Searching for content") into actual file links or inline instructions so the core operations are self-contained.

Add one short worked example showing the output of a spike investigation end-to-end (pattern → segmentation → context → synthesis) so the workflow is copy-paste concrete.

Clarify what "Finding the right event properties" returns and how its output feeds into the Step 3 segmentation, since that handoff is currently implicit.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence, never explaining what Amplitude or a chart is, and every line is actionable guidance or a concrete bound ("up to 9 high-signal properties", "up to 3 charts at a time") with no padded exposition.

3 / 3

Actionability

Concrete tool calls like `Amplitude:getting_data_from_url` and `Amplitude:get_feedback_insights` are present, but the core analytical operations are delegated to bolded procedure names ("Reading chart data", "Analyzing chart", "Finding the right event properties") that are neither linked nor explained, leaving key details missing.

2 / 3

Workflow Clarity

Steps 0–5 are clearly sequenced with explicit validation checkpoints and stop conditions ("If chart data cannot be retrieved or is empty, do not proceed"; "ask explicitly ... and stop"), and the read-only nature means the destructive-operation cap does not apply.

3 / 3

Progressive Disclosure

The content is well-organized into clearly delineated sections (When to Use, Steps 0–5, Best Practices) with no monolithic wall of text and no deeply nested references, satisfying the well-organized-sections bar for a self-contained skill.

3 / 3

Total

11

/

12

Passed

Description

90%

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

The description is strong: it states a concrete domain, answers both what and when with explicit natural-language triggers, and is narrowly scoped to Amplitude charts. Its only weakness is that the listed actions are variations of "analysis" rather than a comprehensive set of distinct concrete operations.

DimensionReasoningScore

Specificity

"Performs deep analysis of a specific Amplitude chart to explain trends, anomalies, and likely drivers" names the domain and several actions, but they are all flavors of analysis/explanation rather than a list of distinct concrete operations, so it stops short of the multi-action anchor 3.

2 / 3

Completeness

It explicitly answers both what ("Performs deep analysis of a specific Amplitude chart...") and when ("Use when a metric looks unusual, investigating a spike or drop...") with an explicit trigger clause.

3 / 3

Trigger Term Quality

"Use when a metric looks unusual, investigating a spike or drop, or understanding the 'why' behind numbers" gives good coverage of natural phrases a user would actually say when they need this skill.

3 / 3

Distinctiveness Conflict Risk

"a specific Amplitude chart" carves out a clear niche with distinct triggers, making it unlikely to fire for unrelated analytics or non-Amplitude skills.

3 / 3

Total

11

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
amplitude/builder-skills
Reviewed

Table of Contents

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.