Tooluck logoTooluck
SKILL.md

review-team

Agent skill frommvschwarz/openrig

Use when assigned a review or when an authored review boundary is reached.

How to install review-team

install review-team
# install the openrig pack with the skills CLI
npx skills add mvschwarz/openrig

# or add only this skill to Claude Code: copy the folder

skills/_canonical/pods/review-team/

# into

~/.claude/skills/review-team/ (all projects)

.claude/skills/review-team/ (one project)

skills/_canonical/pods/review-team/SKILL.md

Apache-2.0Full file
1# Review Team
2
3You are part of the review pod. Your value is fresh scrutiny that implementation and QA do not have.
4
5## Entry and proportionality
6
7Run `rig whoami --json`, then resolve `project.yaml -> mission.yaml -> active
8slice.yaml -> selected component or wave map -> addressed context`. The complete
9lookup and precedence rule is `docs/reference/product-journey-sdlc.md#resolve-the-selected-path`
10(installed: `$OPENRIG_HOME/reference/product-journey-sdlc.md#resolve-the-selected-path`).
11Read the selected addresses and source needed for this task; skills available in
12your profile are capabilities, not a mandatory reading list. No composition means
13light Part A. Role names and idle seats add no gates. Explicit rigor and authored
14wave boundaries retain their named checks.
15
16Start a review only for an explicit owner assignment or an authored component/wave
17review event. A visible milestone, idle queue, or available reviewer is not an
18assignment. At a wave boundary review the accumulated outcome once; preserve a
19named slice's explicit exception. Authors do not perform their own selected
20independent review.
21
22Match the selected review to the consequence. A small diff gets a focused pass;
23the deep review method below runs only when explicitly selected for named work.
24Importance, size or a prior finding alone cannot self-select it. If another review
25seems necessary, name the concrete unresolved risk to the owner while continuing
26the selected path.
27
28## Startup sequence
29…

Excerpt shown under the repository's Apache-2.0 license.

More skills in openrig

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates