CtrlK
BlogDocsLog inGet started
Tessl Logo

configuring-experiment-rollout

Configures the rollout shape of a PostHog experiment — the variant split (50/50, 80/20, A/B/C ratios), the overall rollout percentage that gates how many users enter the experiment, and the disambiguation when a percentage like "roll out to 25%" could mean either. Use when the user mentions a rollout percentage, variant split, or traffic distribution; gives a ratio like 60/40, 70/30, or 80/20; asks "who sees the test variant?"; wants to increase, decrease, or change the rollout or split on a draft or running experiment; weighs equal vs uneven splits; or proposes a mid-experiment split change (often an anti-pattern that needs reset or end-and-restart).

75

Quality

92%

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

85%

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-structured body with executable JSON, clear risky-operation checkpoints, and proper progressive disclosure; its only weakness is repeated rationale and overlapping dialog templates that add length.

Suggestions

State the 'equal splits maximize statistical power / avoid bias' rationale once in the opening section and reference it rather than repeating it in each disambiguation case and the after-picking block.

Collapse the Case 1 and Case 2 dialog templates into a single parameterized template, since both present the same equal-split-vs-uneven trade-off with only the numbers differing.

Trim the explanatory prose in the 'When an uneven split is required' and 'After the user picks' sections to the operational rule plus the verbatim question, leaving the deeper reasoning to the reference file.

DimensionReasoningScore

Conciseness

Mostly efficient and PostHog-specific, but the 'equal splits maximize statistical power / avoid bias' rationale is restated 3+ times and the Case 1/Case 2/after-picking dialog templates overlap, so it could be tightened without losing clarity.

2 / 3

Actionability

Provides copy-paste-ready JSON for the exact feature_flag.filters shape, concrete field paths (multivariate.variants, groups[0].rollout_percentage), hard constraints (sum to 100, 2-20 variants), and the update_feature_flag_params: true requirement.

3 / 3

Workflow Clarity

Multi-step processes are clearly sequenced with explicit checkpoints — MUST-clarify disambiguation (Case 1/2), MUST-confirm before changing a running experiment, the safe-increase exception, and the freeze-exposure alternative for stopping enrollment.

3 / 3

Progressive Disclosure

Well-organized sections with one clearly-signaled, one-level-deep reference (references/changing-distribution-after-launch.md, verified present) holding the detailed warnings; the body stays an overview.

3 / 3

Total

11

/

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.

An exemplary description: third-person, concrete, with an explicit 'Use when' clause covering many natural trigger phrases and a clearly distinct PostHog rollout niche.

DimensionReasoningScore

Specificity

Lists multiple concrete actions in third person ('Configures the rollout shape... variant split (50/50, 80/20, A/B/C ratios)... overall rollout percentage... disambiguation'), naming specific configuration targets rather than vague language.

3 / 3

Completeness

Clearly states what the skill does (configures split, rollout, disambiguation) and an explicit 'Use when...' clause enumerating many concrete triggering situations.

3 / 3

Trigger Term Quality

Strong coverage of natural user phrasing — 'rollout percentage', 'variant split', 'traffic distribution', ratios '60/40, 70/30, 80/20', 'who sees the test variant?', and 'mid-experiment split change'.

3 / 3

Distinctiveness Conflict Risk

Scoped to a clear PostHog niche (experiment rollout/split configuration) with distinct triggers unlikely to fire for sibling skills like experiment analytics.

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.