claude-devfleet
Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-08
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- attribution-playbook
- description
- Standard operating guide for campaign tagging, attribution models, and QA.
03 SKILL.md 正文
Attribution Playbook Skill
When to Use
- Standing up or refreshing attribution models across teams.
- Training campaign owners on UTMs, tracking, and governance.
- Running QA before/after changing attribution weights or tooling.
Framework
- Taxonomy Rules – channel, campaign, creative, and experiment naming standards.
- Model Catalog – when to use first/last/linear/position/data-driven with pros/cons.
- Data Contracts – required fields, systems of record, sync cadence.
- QA Checklist – sample records, dedupe logic, cross-tool reconciliation.
- Change Management – approval workflow, communications, and measurement of impact.
Templates
- UTM builder + validation sheet.
- Attribution model comparison matrix.
- QA runbook for campaign launches and quarterly audits.
Tips
- Keep a shared "gotchas" log for recurring tagging errors.
- Align with finance on ROI/CAC definitions before rolling out model changes.
- Pair with
evaluate-attribution-modelsfor decision-ready narratives.
04 同仓库更多 Skills
remotion-video-creation
Best practices for Remotion - Video creation in React. 29 domain-specific rules covering 3D, animations, audio, captions, charts, transitions, and more.
hotcook-recipes
暂无简介
code-helper
Code review and assistance skill
research-assistant
Web research assistant skill using Brave Search MCP
x-api
X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.
workspace-surface-audit
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.