How do I install the Multica Review Backend skill?

Run npx skillmds@latest add it235/multica-review-backend in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Multica Review Backend safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Multica Review Backend?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Multica Review Backend free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Multica Review Backend?

it235 (@it235) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Multica Review Backend by it235 — Agent Skill

Name: Multica Review Backend
Rating: 4.5 (4 reviews)
Author: it235

Multica Review Backend

Backend-implementation dedicated review framework. Called by BackendReviewer to professionally analyze BackendDev's API contract & implementation (contract quality/design fit/error handling/unit-test sufficiency/acceptance mapping), output PASS/FAIL + fix list, report to Leader.

it235 Updated Sep 22, 2026

File contents

Backend Implementation Professional Review (BackendReviewer)

Structured professional review framework for backend implementation artifacts (API contract + implementation). Called by BackendReviewer; reviews the links BackendDev returns via multica-artifact-backend and code-class skill (Apifox / changed-file list), plus the architecture design ref Leader passes.

When to use

BackendReviewer receives a "review backend implementation" dispatch from Leader.
Entering a re-review round after implementation changes (check previous round's fix list item by item).

Review dimensions (conclusion per item)

Contract quality: field naming, status codes, error model, versioning clear & self-consistent.
Design fit: implementation aligned with Architect plan, deviations explained.
Error handling: exception branches, timeouts, idempotency, boundaries covered.
Unit-test sufficiency: key paths, boundaries, exception branches covered; no无效的 tests (mark & block).
Acceptance mapping: implementation truly satisfies every AC-.

Output format

【Backend Review】<change link>
Conclusion: PASS / FAIL
Blocking items (required on FAIL, each: rationale / involved point / fix direction):
- ...
Suggestions (non-blocking):
- ...
Previous fix-list check (re-review): resolved X / unresolved Y
Round: N / 3

Conclusion + fix list reported to Leader; don't modify code or notify BackendDev yourself.

Boundaries

Review only backend contract & implementation, unit tests; not frontend, UI, requirements, architecture design itself, or test cases.
Don't replace Leader's generic gate (multica-verification skill).
Architecture-level disagreement goes to ArchReviewer; you own implementation-layer quality.
Still FAIL at round 3 → mark "escalate to human", hand to Leader, stop looping.

---name: multica-review-backenddescription: Backend-implementation dedicated review framework. Called by BackendReviewer to professionally analyze BackendDev's API contract & implementation (contract quality/design fit/error handling/unit-test sufficiency/acceptance mapping), output PASS/FAIL + fix list, report to Leader.---# Backend Implementation Professional Review (BackendReviewer)Structured professional review framework for **backend implementation artifacts (API contract + implementation)**. Called by `BackendReviewer`; reviews the links `BackendDev` returns via `multica-artifact-backend` and code-class skill (Apifox / changed-file list), plus the architecture design ref Leader passes.## When to use- BackendReviewer receives a "review backend implementation" dispatch from Leader.- Entering a re-review round after implementation changes (check previous round's fix list item by item).## Review dimensions (conclusion per item)1. **Contract quality**: field naming, status codes, error model, versioning clear & self-consistent.2. **Design fit**: implementation aligned with Architect plan, deviations explained.3. **Error handling**: exception branches, timeouts, idempotency, boundaries covered.4. **Unit-test sufficiency**: key paths, boundaries, exception branches covered; no无效的 tests (mark & block).5. **Acceptance mapping**: implementation truly satisfies every AC-.## Output format```【Backend Review】<change link>Conclusion: PASS / FAILBlocking items (required on FAIL, each: rationale / involved point / fix direction):- ...Suggestions (non-blocking):- ...Previous fix-list check (re-review): resolved X / unresolved YRound: N / 3```Conclusion + fix list **reported to Leader**; don't modify code or notify BackendDev yourself.## Boundaries- Review only backend contract & implementation, unit tests; not frontend, UI, requirements, architecture design itself, or test cases.- Don't replace Leader's generic gate (multica-verification skill).- Architecture-level disagreement goes to ArchReviewer; you own implementation-layer quality.- Still FAIL at round 3 → mark "escalate to human", hand to Leader, stop looping.

Frequently asked questions