Name: configuring-experiment-rollout
Rating: 77.60000000000001 (1 reviews)
Author: PostHog

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).

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-5

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

The body is highly actionable with concrete API shapes and strong confirmation checkpoints for a destructive operation. Its only weakness is mild verbosity from repeated equal-vs-uneven-split recommendation blocks.

Suggestions

Consolidate the Case 1, Case 2, and 'After the user picks the uneven split' recommendation blocks into a single shared explanation to reduce repetition.

Move the multivariate-handling 'Exclude vs First seen' trade-off detail once and reference it from each uneven-split path rather than restating it in multiple places.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and domain-specific with no generic concept padding, but the three near-parallel recommendation blocks (Case 1, Case 2, and 'After the user picks') repeat the equal-split-vs-uneven trade-off and could be tightened.	4 / 5
Actionability	Provides exact field paths (feature_flag.filters.multivariate.variants, groups[0].rollout_percentage), a complete copy-paste JSON shape, defaults, and constraints (sum to 100, min 2 / max 20 variants), covering the common cases.	5 / 5
Workflow Clarity	Destructive running-experiment changes carry explicit validation/confirmation checkpoints ('You MUST warn the user and get explicit confirmation'), a CRITICAL disambiguation gate, and the update_feature_flag_params sync requirement.	5 / 5
Progressive Disclosure	SKILL.md is a well-organized overview with a clearly signaled, verified one-level-deep reference (references/changing-distribution-after-launch.md) and cross-links to related skills, making navigation easy.	5 / 5
	Total	19 / 20 Passed

Description

100%Weight 40%Scale 1-5

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 concrete, trigger-rich, and explicitly answers both what the skill does and when to use it, all in third person. It is among the strongest examples in the rubric's reference set.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — variant split ('50/50, 80/20, A/B/C ratios'), overall rollout percentage, and disambiguation — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (configures rollout shape) and 'when' via a 'Use when...' clause with concrete trigger phrases, satisfying the top anchor.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including ratios users actually say ('60/40, 70/30, or 80/20'), 'rollout percentage', 'variant split', and the question 'who sees the test variant?'.	5 / 5
Distinctiveness Conflict Risk	Scoped to a clear PostHog-experiment-rollout niche with distinct triggers; overlap with sibling analytics/lifecycle skills is minimal and explicitly delineated.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: PostHog/posthog
Path: products/experiments/skills/configuring-experiment-rollout/SKILL.md
Commit: b0fece0

Reviewed: 4 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.