Architect Review PR
Use after a feature is built — e.g. the final step of a ship-it run, right after review-pr — to check it is actually complete and wired, not just line-correct. Dispatches a fresh-context Claude subagent that traces the whole repo to hunt completeness and integration gaps in the branch's changes, reports ranked, evidence-backed findings, then fixes the CRITICAL ones and verifies with a fresh re-review (capped at 3 passes; pass report-only to skip fixing). Triggers on: architect review, architecture review, completeness review, wiring review, is this wired, did we finish this, find the gaps, inc
Install
/plugin marketplace add adelrioj/claude-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add adelrioj/claude-skills --skill architect-review-prgit clone --depth 1 https://github.com/adelrioj/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/architect-review-pr ~/.claude/skills/architect-review-prPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Architect Review — Adversarial Completeness & Wiring An **architect-level adversarial review for completeness and integration**, run on a finished implementation. It answers the question the other review skills don't: > "Do a deep pass at everything you built and make sure it's wired properly and works > as intended. Find gaps, bits we didn't implement, code created but never wired, > failure cases, edge cases." This skill **finds first, then fixes what is CRITICAL** — the same review-then-fix shape `/ship-it` Step 6 drives around `/review-pr`. The reviewer subagent is a pure finder: it reports ranked, evidence-backed findings and **edits nothing**. Then the main loop applies a fix for each CRITICAL finding and re-dispatches a *fresh* reviewer to verify, converging or capping at 3 passes like `/spec-review-codex`. IMPORTANT and below stay report-only. Pass a bare `report-only` token to skip the fix loop entirely (`/ship-it` Step 7 does — its conductor owns its own fix/commit loop). **Where it sits in the family:** - `/code-review`, `/review-pr` — line-level *correctness* on the diff. - `/spec-review-codex` / `-local` — harden the *spec, before* any code exists. - `/architect-review-pr` — *completeness & wiring* of the finished feature. This skill. **Why a fresh subagent (the adversarial mechanism).** The main loop *built* this code, so it shares the author's blind spots — the same gap in reasoning that left code unwired
Details
- Skill name
architect-review-pr- Repository
- adelrioj/claude-skills
- Path
skills/architect-review-pr/SKILL.md- Repo updated
- 24 August 2026
FAQ
What does the Architect Review PR skill do?
Use after a feature is built — e.g. the final step of a ship-it run, right after review-pr — to check it is actually complete and wired, not just line-correct. Dispatches a fresh-context Claude subagent that traces the whole repo to hunt completeness and integration gaps in the branch's changes, reports ranked, evidence-backed findings, then fixes the CRITICAL ones and verifies with a fresh re-review (capped at 3 passes; pass report-only to skip fixing). Triggers on: architect review, architecture review, completeness review, wiring review, is this wired, did we finish this, find the gaps, inc
How do I install the Architect Review PR skill?
Claude Code plugin: /plugin marketplace add adelrioj/claude-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Architect Review PR popular?
It lives in adelrioj/claude-skills, which has 5 GitHub stars and 0 forks.
Related skills
Blind Spot
5adelrioj/claude-skills
Use BEFORE starting work on a task to surface the unknown-unknowns you're about to walk into but can't see. Dispatches a fresh-context Claude subagent that hunts what you don't know you don't know about the codebase, the domain, and the decisions ahead, calibrated to your stated experience, then reports ranked, evidence-backed findings and fixes nothing. Triggers on: blind spot pass, blindspot, unknown unknowns, what don't I know, what am I missing, help me prompt better, I know nothing about, teach me my unknowns, before I start, de-risk this task, surface my blind spots.
Claude Md Slim
5adelrioj/claude-skills
Use when CLAUDE.md has grown bloated and is taxing every session's context — the inverse of claude-md-improver. Triages each block into session-invariant rules (stay always-on) vs feature/subsystem detail (page out to docs/ behind a plain-path pointer), moving — never deleting — the detail so nothing is lost and the always-on token bill drops. Triggers on: slim claude.md, minimal claude.md, claude.md is bloated, shrink claude.md, split claude.md, make claude.md minimal, page out claude.md, claude.md too long, reduce project memory, point claude.md to docs, trim claude md.
Linear Groom Ticket
5adelrioj/claude-skills
Use when a Linear ticket needs to be made ready to work on, or judged not worth working on. Analyses one ticket across four dimensions — whether its claims hold in the code, whether it is complete against the team template, whether it duplicates another ticket, and whether it is implementable — then proposes a corrected description and applies it to Linear only after you approve. Triggers on: groom this ticket, prepare NBS-123, is this ticket ready, revisa este ticket, ¿este ticket está listo?, deja el ticket listo para trabajar, candidato a borrar, dedupe this ticket.
Ship It
5adelrioj/claude-skills
Use when a thumbs-upped design spec is ready and you want the whole spec-to-PR pipeline to run autonomously — hardens the spec, writes the plan, executes it via dex, opens a PR, runs PR review, and closes with an architect completeness review — in one invocation. Triggers on: ship it, ship-it, run the pipeline, spec to PR, autonomous feature pipeline, conductor.
Workspace Sync
9flurdy/agent-skills
Guide attended Git and Beads synchronization at a validated workspace root, with accurate previews, separate fresh approvals and explicit failure boundaries. Never sync from status or wrap-up.
Code Review
5euxx/claude-skills-for-copilot
Multi-agent code review for local changes, files, or directories. Detects bugs, security issues, and conventions-file violations (AGENTS.md/CLAUDE.md/GEMINI.md).
Browse the most popular Claude skills, all git & code review skills, or write your own with the skills generator.