// Claude Code skill for measuring causal impact of marketing campaigns using Bayesian structural time series
causal-impact-campaign
git log --oneline --stat
HEAD
- Stars
- 1
- Forks
- 3
- Updated
- Apr 15, 2026
repo --stat
stars
1
forks
3
last update
Apr 15, 2026
license
MITv1.0.0
quickstart.sh
3 steps
- Install
// Drops SKILL.md into ~/.claude/skills/
$ claude skills add wan-huiyan-causal-impact-campaign - Invoke
// Run from any project directory
$ claude --skill wan-huiyan-causal-impact-campaign "query last week's signups" - Or copy this from the README
// extracted from a Usage / Example section
$ You: We ran a free delivery promo for 10 days. Did it actually increase revenue? We have daily GA4 data in BigQuery. Claude: [runs full pipeline — data exploration, covariate safety audit, 4-method analysis, permutation validation, client-ready HTML]
wan-huiyan-causal-impact-campaign/
references
- references/
- SKILL.mdopen
- README.mdopen
SKILL.md
readonly
- name:
- causal-impact-campaign
- slug:
- wan-huiyan-causal-impact-campaign
- version:
- v1.0.0
- license:
- MIT
- author:
- @wan-huiyan
- repository:
- github.com/wan-huiyan/causal-impact-campaign
- categories:
- tags:
- #bayesian#campaign-measurement#causal-impact#causal-inference#claude-code-skill#ga4#marketing-analytics
- description:
Claude Code skill for measuring causal impact of marketing campaigns using Bayesian structural time series
README.md
wan-huiyan-causal-impact-campaign/README.md
14 sections
Loading README…
@wan-huiyan/index.json
more by author
authored by
@wan-huiyanagent-review-panel
Claude Code skill: Multi-agent adversarial review panel — 4-6 AI reviewers debate your code/plans, then a supreme judge delivers the verdict. 9 auto-detected signal groups, built-in domain checklists, anti-groupthink mechanisms.
6subagent-driven-development
Claude Code skill: execute implementation plans with fresh subagents per task, two-stage review gates, and parallel mode via worktree isolation. Based on obra/superpowers, parallel mode adapted from theradengai/spawn-tasks.
1overnight-workflows
Two sister Claude Code plugins for running autonomous overnight work sessions that land a polished deliverable on your desk by morning, with multi-agent review panels baked in to catch factual errors before they reach the client.
1context-baton
Two Claude Code skills for passing context across boundaries: session-handoff (end-of-session, agent→human) + successor-handoff (mid-run, agent→agent). Install via Claude Code plugin marketplace.
1
$ cat reviews/
Reviews
// No reviews yet. Be the first.
Loading review form…