Review M1 — Testing skill for Claude Code
Review and test M1 core features (bulletin, newcomer, inbox/, scan-and-replicate).
How to install Review M1
Installs to ~/.claude/commands/sk01020432947-oss-church-admin-agenticworkflow-review-m1.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/sk01020432947-oss/Church-Admin-AgenticWorkflow/HEAD/.claude/commands/review-m1.md -o ~/.claude/commands/sk01020432947-oss-church-admin-agenticworkflow-review-m1.md Restart Claude Code, or start a new session, for it to be picked up.
What Review M1 does
description: "Review and test M1 core features (bulletin, newcomer, inbox/, scan-and-replicate)"
Run M1 integration verification:
- List all M1 output files with sizes (workflows, agents, scripts, data files)
- Run all 4 P1 validation scripts against current data — report pass/fail
- Show bulletin generation test result (sample bulletin from seed data)
- Show newcomer pipeline stage transition test
- Show inbox/ parsing test results (Excel, image)
- Report any issues found with sev
Alternatives in Testing
- Deslop Reborn — One iteration of the IronClaw Reborn de-slop loop — take ONE Reborn crate, fan out parallel review sub-agents 12.6k ★
- Testing Strategy — This project is small, runs in a terminal, and is mostly deterministic 10.9k ★
- Deliver — Delivery phase - Review, validate, and test with multi-AI quality assurance 2.8k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Cmd Verify
Verify phase (PROVE) format, lint, type-check, scan, test, and githook gate with a fix/review loop. Use to lea
PR Reviewer
An AI code-review agent for GitHub pull requests. Built on the Claude Agent SDK, the GitHub REST API, and pyte
Spec Answers
Scan spec-CR review threads for the user's answers, fold each into the spec via the role agent that raised it,
Check Invariants
Runs only the tree CRDT invariant test battery in outl-core. Faster than /check, focused on what can break syn
Self Test
In-process governance guard self-test — asserts the 3 core guards block crafted payloads, $0 hermetic — /self-
OpenPitStop
A referee your AI coding agent can't cheat. PitStop scans your repo, seals the evidence, catches agents faking
Related Agents
Church Pipeline Designer
inbox/ 3-tier data pipeline and scan-and-replicate engine architecture design
Inbox Tracker
Scan Gmail (and Google Calendar) for job-search activity — recruiter mail, ATS/application updates, interview
Reply Check
Scan Gmail inbox and LinkedIn messages for replies to outreach. Updates pipeline.md with status=replied_need_r