AGENT SKILL

blueprint

Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that needs multiple sessions. DO NOT TRIGGER when: task is completable in a single PR or fewer than 3 tool calls, or user says "just do it".

License 许可
Apache-2.0
最近更新
2026-11-08
Stars
★ 0
Forks
0

01 前言 Front Matter

name
personalization-logic
description
Use when defining dynamic content rules, tokens, and conditional offers inside nurture programs.

03 SKILL.md 正文

Nurture Personalization Logic Skill

When to Use

  • Building dynamic content for lifecycle nurtures.
  • Mapping personalization tokens (industry, role, behavior) to copy blocks.
  • Coordinating personalization across email, in-app, ads, and SDR assists.

Framework

  1. Segmentation Inputs – persona, industry, product usage, lifecycle stage, engagement history.
  2. Content Blocks – hero, proof, CTA, offer modules with variants per segment.
  3. Token Management – define data sources, fallback values, formatting rules.
  4. Testing Plan – structure A/B/C tests for personalization depth.
  5. Governance – approval workflows, localization, compliance, expirations.

Templates

  • Personalization matrix (segment vs module vs asset).
  • Token dictionary (field, source, fallback, formatting).
  • QA checklist (seed records, fallback coverage, compliance notes).

Tips

  • Start with modular blocks so ops can update without rewriting entire emails.
  • Document dependencies on upstream data hygiene.
  • Pair with copywriting + design teams for brand consistency.

04 同仓库更多 Skills