How do I install the Multica Review Test skill?

Run npx skillmds@latest add it235/multica-review-test 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 Test 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 Test?

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 Test free to use?

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

Who published Multica Review Test?

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

Multica Review Test by it235 — Agent Skill

Name: Multica Review Test
Rating: 4.2 (5 reviews)
Author: it235

Multica Review Test

Test-artifact dedicated review framework. Called by TestReviewer to professionally analyze Tester's cases/report/coverage doc (coverage depth/acceptance mapping/coverage reasonableness/conclusion truth/contract consistency), output PASS/FAIL + fix list, report to Leader.

it235 Updated Sep 22, 2026

File contents

Test Artifact Professional Review (TestReviewer)

Structured professional review framework for test artifacts (functional/API cases, test report, coverage doc). Called by TestReviewer; reviews the links Tester returns via multica-test-orchestration (case set / report), plus acceptance + related implementation change links Leader passes.

When to use

TestReviewer receives a "review test artifact" dispatch from Leader (case review / report review both apply).
Entering a re-review round after test-artifact changes (check previous round's fix list item by item).

Review dimensions (conclusion per item)

Coverage depth: normal / boundary / exception / permission / compatibility paths covered.
Acceptance mapping: every AC- backed by an executable case.
Coverage reasonableness: metrics truly reflect risk points, no hiding critical uncovered paths.
Conclusion truth: pass/fail based on real execution evidence, defects reproducible.
Contract consistency: case params, assertions aligned with BackendDev contract.

Output format

【Test Artifact Review】<test 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 cases or notify Tester yourself.

Boundaries

Review only test artifacts, not architecture, requirements, UI, frontend/backend implementation, or code unit tests.
Don't replace Leader's generic gate (multica-verification skill).
Implementation-layer quality goes to the matching dedicated Reviewer; you own test-artifact professionalism.
Still FAIL at round 3 → mark "escalate to human", hand to Leader, stop looping.

---name: multica-review-testdescription: Test-artifact dedicated review framework. Called by TestReviewer to professionally analyze Tester's cases/report/coverage doc (coverage depth/acceptance mapping/coverage reasonableness/conclusion truth/contract consistency), output PASS/FAIL + fix list, report to Leader.---# Test Artifact Professional Review (TestReviewer)Structured professional review framework for **test artifacts (functional/API cases, test report, coverage doc)**. Called by `TestReviewer`; reviews the links `Tester` returns via `multica-test-orchestration` (case set / report), plus acceptance + related implementation change links Leader passes.## When to use- TestReviewer receives a "review test artifact" dispatch from Leader (case review / report review both apply).- Entering a re-review round after test-artifact changes (check previous round's fix list item by item).## Review dimensions (conclusion per item)1. **Coverage depth**: normal / boundary / exception / permission / compatibility paths covered.2. **Acceptance mapping**: every AC- backed by an executable case.3. **Coverage reasonableness**: metrics truly reflect risk points, no hiding critical uncovered paths.4. **Conclusion truth**: pass/fail based on real execution evidence, defects reproducible.5. **Contract consistency**: case params, assertions aligned with BackendDev contract.## Output format```【Test Artifact Review】<test 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 cases or notify Tester yourself.## Boundaries- Review only test artifacts, not architecture, requirements, UI, frontend/backend implementation, or code unit tests.- Don't replace Leader's generic gate (multica-verification skill).- Implementation-layer quality goes to the matching dedicated Reviewer; you own test-artifact professionalism.- Still FAIL at round 3 → mark "escalate to human", hand to Leader, stop looping.

Frequently asked questions