subagent-vs-review
Use when a task needs independent adversarial review during vibe coding, design work, implementation, testing, release planning, documentation, skill…
Skill by ceasarXuu
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ceasarxuu-subagent-vs-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, testing, productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/subagent-vs-review
What's inside
- Skill name
subagent-vs-review- Description
- Use when a task needs independent adversarial review during vibe coding, design work, implementation, testing, release planning, documentation, skill creation, or agent workflow design. It runs bounded fresh reviews, grounds blocking claims in external evidence, freezes the original objective and scope, detects non-convergence and scope drift, and restores user control before additional review or repair work can continue.
- License
- unknown
- Instructions
- 580 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- body: 580 lines (spec recommends under 500)
Files (7)
- SKILL.md
- openai.yaml · agents/
- openai-compatible.json · markets/
- finding-triage-rubric.md · references/
- review-governor.md · references/
- review-report-template.md · references/
- reviewer-selection.md · references/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from ceasarXuu/AstartesSkills
- 0.604score
agent-commander
ceasarXuu
Delegate authorized tasks including analysis, implementation, testing, commands, commits, and publishing from Codex to a locally installed Command Code…
SkillAFreshness: A★ 4Claude Code +9 - 0.569score
provider-switch
ceasarXuu
Manage and maintain safe, reversible configurations that connect coding agents to model providers.
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
bug-killer
ceasarXuu
Use when debugging medium or large bugs, regressions, flaky failures, production symptoms, repeated failed fixes, or user-explicit requests where the agent…
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
clear-prd
ceasarXuu
Use when a product, feature, app, website, internal tool, automation, or workflow needs product-logic clarification before implementation.
SkillBFreshness: B★ 4Claude Code +9 - 0.564score
rules-install
ceasarXuu
Install or update one shared global coding-agent role/instruction text across locally installed Claude Code, Codex, TRAE CN, OpenCode, Pi, and Grok Build.
SkillBFreshness: B★ 4Claude Code +9 - 0.564score
threejs-game
ceasarXuu
Design, build, refactor, optimize, test, and release maintainable three.js games across runtime architecture, assets, rendering, input and camera, interaction…
SkillBFreshness: B★ 4Claude Code +9 - 0.544score
se-good-plan
ceasarXuu
Use when the user asks for a software engineering plan, implementation plan, refactor plan, migration plan, rollout plan, bug-fix plan, performance…
SkillBFreshness: B★ 4Claude Code +9 - 0.535score
dev-loop
ceasarXuu
Use when the user wants to audit, diagnose, optimize, or protect a software project's development feedback loop, including slow local builds, slow tests…
SkillBFreshness: B★ 4Claude Code +9 - 0.494score
plan-report
ceasarXuu
Use when the user asks to report, summarize, audit, or present the implementation result of a plan, roadmap, PRD, engineering plan, refactor plan, migration…
SkillCFreshness: C★ 4Claude Code +9 - 0.454score
storybook-skills-standard
ceasarXuu
Use when the user needs to design, implement, audit, or govern Storybook stories for frontend components, design systems, page states, interaction tests…
SkillDFreshness: D★ 4Claude Code +9 - 0.449score
frontend-refactoring
ceasarXuu
Use when a frontend redesign or legacy CSS refactor is blocked by global style pollution, selector collisions, unstable DOM reuse, or the need to migrate a…
SkillDFreshness: D★ 4Claude Code +9 - 0.449score
summary-my-repo
ceasarXuu
Use when the user wants an internal repository summary that captures architecture, directory responsibilities, core code paths, and code-backed logic evidence…
SkillDFreshness: D★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 5, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/ceasarXuu/AstartesSkills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ceasarXuu
- 0.604score
agent-commander
ceasarXuu
Delegate authorized tasks including analysis, implementation, testing, commands, commits, and publishing from Codex to a locally installed Command Code…
SkillAFreshness: A★ 4Claude Code +9 - 0.569score
provider-switch
ceasarXuu
Manage and maintain safe, reversible configurations that connect coding agents to model providers.
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
bug-killer
ceasarXuu
Use when debugging medium or large bugs, regressions, flaky failures, production symptoms, repeated failed fixes, or user-explicit requests where the agent…
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
clear-prd
ceasarXuu
Use when a product, feature, app, website, internal tool, automation, or workflow needs product-logic clarification before implementation.
SkillBFreshness: B★ 4Claude Code +9 - 0.564score
rules-install
ceasarXuu
Install or update one shared global coding-agent role/instruction text across locally installed Claude Code, Codex, TRAE CN, OpenCode, Pi, and Grok Build.
SkillBFreshness: B★ 4Claude Code +9 - 0.564score
threejs-game
ceasarXuu
Design, build, refactor, optimize, test, and release maintainable three.js games across runtime architecture, assets, rendering, input and camera, interaction…
SkillBFreshness: B★ 4Claude Code +9
Cite this page
subagent-vs-review skill. Agent Mart. https://agentmart.dev/skills/ceasarxuu-subagent-vs-review (last updated 2026-10-24)