CtrlK
BlogDocsLog inGet started
Tessl Logo

choosing-trend-or-slope-view

Clarify how to visualize change over a time range before building a trend. Use whenever the user asks how much something changed, grew, dropped, improved, or regressed between two points or periods — "how much did X change from A to B", "before vs after", "start vs end", "week over week", "compare this month to last", "change over time" — or mentions a "slope chart" / "slopegraph". Two readings of "change" need different charts: the whole trend (a line, every interval) versus just the two endpoints (a slope, start vs end). Ask which they want, then render it. Not for choosing a saved insight ChartDisplayType in the insight editor.

80

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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 tight, actionable guide: it frames the ambiguity, gives a ready-to-run query for the default case and concrete UI steps for the slope case, and flags key limits (feature flag, grouping semantics, period-over-period). No bundle files are needed or referenced.

DimensionReasoningScore

Conciseness

Lean body that assumes Claude knows what trends and queries are; the JSON example and prose each earn their place with no padding or basic-concept explanation.

3 / 3

Actionability

The line case provides a complete, copy-paste TrendsQuery JSON; the slope case gives concrete guidance via the query-trends result-card toggle, which is appropriately instruction-based since the action is a UI affordance.

3 / 3

Workflow Clarity

Clear decision sequence — detect ambiguity, clarify with an either/or, render the chosen chart — with an explicit 'skip the question and build it' shortcut when the user already named one. Not a destructive/batch task, so feedback loops are not required.

3 / 3

Progressive Disclosure

A self-contained body under the simple-skill threshold with well-organized sections and no claimed external references; no bundle files exist, so organization alone justifies the top score.

3 / 3

Total

12

/

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.

A high-quality description: it states concrete actions, gives a broad set of natural trigger phrases, answers both what and when, and includes an exclusion to avoid conflict with the insight editor. Third-person voice is consistent throughout.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'Clarify how to visualize change', 'Ask which they want, then render it' — and distinguishes the two renderings ('a line, every interval' vs 'two endpoints (a slope)').

3 / 3

Completeness

Explicitly answers both what ('Clarify how to visualize change... Ask which they want, then render it') and when ('Use whenever the user asks how much something changed...'), with an explicit exclusion.

3 / 3

Trigger Term Quality

Rich natural phrasing users would say: 'how much did X change from A to B', 'before vs after', 'start vs end', 'week over week', 'compare this month to last', 'change over time', 'slope chart'/'slopegraph'.

3 / 3

Distinctiveness Conflict Risk

Narrow niche (line vs slope for time-range change) with distinct triggers and an explicit exclusion ('Not for choosing a saved insight ChartDisplayType') to avoid the wrong skill firing.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
PostHog/posthog
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.