AGENT SKILL

experimentation-throughput-strategy

Plan experiment throughput strategies for mature A/B testing programs. Use when testing capacity is constrained, teams are waiting for experiment slots, roadmap coordination is slowing learning, or a team must choose isolated, overlapping, parallel, or capacity-aware experiment scheduling without sacrificing result quality.

License 许可
MIT
最近更新
2026-11-14
Stars
★ 1.6k
Forks
491

01 前言 Front Matter

name
experimentation-throughput-strategy
license
MIT
metadata
{ "tags": "practical-ab-testing,next-level-ab-testing,ab-testing,experimentation,product-analytics", "version": "0.1.0", "category": "Product Management", "displayName": "Experimentation Throughput Strategy" }
description
Plan experiment throughput strategies for mature A/B testing programs. Use when testing capacity is constrained, teams are waiting for experiment slots, roadmap coordination is slowing learning, or a team must choose isolated, overlapping, parallel, or capacity-aware experiment scheduling without sacrificing result quality.
compatibility
Codex, Claude Code, and other Agent Skills-compatible clients.

02 资源文件 5

03 SKILL.md 正文

Experimentation Throughput Strategy

Use this skill to increase the rate of product experimentation without turning the experiment pipeline into an unreliable traffic jam. It focuses on testing capacity, isolated versus overlapping strategies, interaction effects, and the process/tooling needed to coordinate experiments at scale.

Source Traceability

Primary source: Next-Level A/B Testing by Leemay Nassery. Guidance is transformed and paraphrased from Chapter 1 on rate, quality, and cost; Chapter 2 on testing availability, isolated and overlapping strategies, and interaction effects; and Chapter 9 on balancing rate with quality, cost, and usability.

Related skills:

  • ab-testing-platform-strategy for platform architecture and ownership.
  • experiment-verification-monitoring for monitoring conflicts and active-test health.
  • experiment-sensitivity-optimization for reducing traffic needs by improving metric sensitivity.

Reference Routing

Need Read
Throughput concepts and terminology references/core/knowledge.md
Strategy selection and coordination rules references/core/rules.md
Scenario examples and tradeoffs references/core/examples.md
Step-by-step throughput plan workflows/improve-experiment-throughput.md

Workflow

  1. Map the current experiment pipeline and where tests wait.
  2. Identify whether the bottleneck is traffic, coordination, tooling, review, QA, analysis, or decision latency.
  3. Decide whether isolated testing, overlapping testing, or a hybrid model fits the product surface and metric precision needs.
  4. Define interference and interaction-effect safeguards.
  5. Add visibility: current tests, upcoming tests, capacity, ownership, and conflict flags.
  6. Write rollout rules so teams know when to schedule, overlap, defer, or split experiments.

Output Format

# Experimentation Throughput Plan

## Bottleneck
[What is limiting experiment rate and what evidence shows it.]

## Recommended Strategy
[Isolated | Overlapping | Hybrid | Keep current strategy] because [reason].

## Capacity View
| Surface or Audience | Current Tests | Upcoming Tests | Constraint | Owner |
|---------------------|---------------|----------------|------------|-------|

## Interference Safeguards
- Conflict dimensions:
- Monitoring:
- Escalation:

## Process And Tooling Changes
1. [Change]
2. [Change]
3. [Change]

## Decision Rules
- Overlap when:
- Isolate when:
- Defer when:
- Revisit when:

Quality Bar

  • Do not increase experiment count by ignoring validity risks.
  • Do not default to isolated testing when capacity is the primary constraint and experiments can run independently.
  • Do not default to overlapping testing when experiments change the same user journey, metric, or surface in ways that can interact.
  • Make the coordination mechanism explicit; "teams will communicate" is not a scalable throughput strategy.

04 同仓库更多 Skills

hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-review-with-annotations

Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-find-and-synthesize-context

Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-create-or-update-docs

Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-create-or-manage-records

Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-create-or-manage-interactive-html

Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.

★ 1.6k
hashgraph-online
hashgraph-online/awesome-codex-plugins

worktable-collaborate-threads

Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.

★ 1.6k