managing-experiment-lifecycle

Guides experiment state transitions: launching, pausing, resuming, freezing/unfreezing exposure, ending, shipping variants, archiving, resetting, duplicating, and copying to another project. Covers preconditions, implications for variant assignment and analysis, and the decision framework for when to use each action. TRIGGER when: user asks to launch, pause, resume, end, ship, archive, reset, duplicate, or copy an experiment to another project, or to freeze/unfreeze exposure (stop enrolling new users while metrics keep flowing, or reopen enrollment). DO NOT TRIGGER when: user is creating an experiment (use creating-experiments), configuring rollout (use configuring-experiment-rollout), or setting up metrics (use configuring-experiment-analytics).

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%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.

A well-organized, actionable lifecycle reference with strong workflow checkpoints and error-handling guidance for destructive operations. Its main weakness is progressive disclosure: dense reference-grade detail lives inline rather than in split reference files.

Suggestions

Move the freeze-exposure edge-case list and the copy-to-project flag-resolution rules into separate reference files under ./references/, leaving a concise summary plus a clearly signaled link in SKILL.md.

Trim or relocate the launch-time qualitative-feedback survey paragraph; it is tangential to lifecycle transitions and adds tokens that compete with core guidance.

Consider extracting the error-handling and decision-framework tables into a reference if the per-action sections grow further, keeping SKILL.md as a navigable overview.

Dimension	Reasoning	Score
Conciseness	Mostly lean and operational (terse Preconditions/Variants/Analysis bullets), but the qualitative-feedback survey paragraph at launch is a tangential aside that could be trimmed; not a 5 because a few passages over-explain.	4 / 5
Actionability	Gives concrete tool names (experiment-launch, experiment-freeze-exposure, etc.), request bodies, HTTP codes (400/409/403), and a situation→action decision table; minor gaps (no literal endpoint paths) keep it just below fully executable.	4 / 5
Workflow Clarity	State diagram sequences transitions, each action states preconditions, and destructive ops carry explicit validation checkpoints ('Always confirm with the user before shipping', 'Confirm the source experiment and target project by name before calling') plus error-recovery guidance ('explain rather than retrying').	5 / 5
Progressive Disclosure	Well-sectioned structure, but ~250 lines of detailed reference material (freeze-exposure edge cases, copy-to-project flag-resolution rules) are inlined in SKILL.md with no local reference files to offload detail into; no bundle files exist.	3 / 5
	Total	16 / 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.

A strong, third-person description that comprehensively enumerates concrete lifecycle actions, pairs them with explicit trigger and anti-trigger clauses, and clearly separates this skill from sibling experiment skills. No fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists many specific concrete actions — 'launching, pausing, resuming, freezing/unfreezing exposure, ending, shipping variants, archiving, resetting, duplicating, and copying to another project' — giving comprehensive coverage rather than vague abstractions.	5 / 5
Completeness	Explicitly answers both 'what' (guides experiment state transitions with preconditions and analysis implications) and 'when' via concrete 'TRIGGER when' and 'DO NOT TRIGGER when' clauses.	5 / 5
Trigger Term Quality	TRIGGER clause uses natural user phrasing ('launch, pause, resume, end, ship, archive, reset, duplicate, or copy an experiment') including synonyms ('freeze/unfreeze exposure') that a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (experiment lifecycle) with explicit DO NOT TRIGGER boundaries disambiguating creating-experiments, configuring-experiment-rollout, and configuring-experiment-analytics, minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: PostHog/posthog
Path: products/experiments/skills/managing-experiment-lifecycle/SKILL.md
Commit: 57503b8

Reviewed: 1 day 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.