Agent skill

Deep Review

by zeuikli in zeuikli/claude-code-workspace

對 staged changes 執行三維度平行審查(安全、效能、風格),合成優先排序的發現摘要. An agent skill from zeuikli/claude-code-workspace.

No licenceAuto-check passed

Install Deep Review

skills CLI
$ npx skills add zeuikli/claude-code-workspace --skill deep-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install zeuikli/claude-code-workspace deep-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/zeuikli/claude-code-workspace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/deep-review .claude/skills/deep-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
deep-review
GitHub stars
156
Token cost
~355 tokens
SKILL.md length
128 words
Files
1
Skills in repo
19
Repo updated
First seen
Licence
None found

At a glance

對 staged changes 執行三維度平行審查(安全、效能、風格),合成優先排序的發現摘要. An agent skill from zeuikli/claude-code-workspace.

  • Works in 3 steps: 安全審查 → 效能審查 → 風格審查
  • SKILL.md covers 1. 安全審查, 2. 效能審查, 3. 風格審查 and 輸出格式, plus 2 more sections
  • Calls git

What it does

Deep Review is an agent skill from zeuikli/claude-code-workspace. 對 staged changes 執行三維度平行審查(安全、效能、風格),合成優先排序的發現摘要。

Its SKILL.md is about 360 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

Example prompts

  • “/deep-review”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. 安全審查
  2. 效能審查
  3. 風格審查

What it can do on your machine

Read from SKILL.md and the folder at commit 807b285. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deep Review loads about 355 tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 128 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~15
When it runs · the whole SKILL.md, loaded when a task matches
~355

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 128 words (~355 tokens).

name
deep-review
disable-model-invocation
true
context
fork

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/deep-review of zeuikli/claude-code-workspace.

Open the folder on GitHubat commit 807b285

Compare with similar skills

Deep Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deep Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deep Review this skillzeuikli/claude-code-workspace156—~355Automated safety check: PassNone
Classroom Stage Design MethodTHU-MAIC/OpenMAIC40k—~1.4kAutomated safety check: PassMIT
Stage Tamagotchi Godot Csharpmoeru-ai/airi50k—~677Automated safety check: PassMIT
OpenMAIC Stage Document MapTHU-MAIC/OpenMAIC40k—~2.4kAutomated safety check: PassMIT
Multi Stage Dockerfilegithub/awesome-copilot40k3 repos~577Automated safety check: PassMIT
Project Stage DetectionDonchitos/Claude-Code-Game-Studios26k—~3.2kAutomated safety check: PassMIT

Similar skills

  • Baseline procedure for building one new classroom stage: settle the page plan with you, create the stage, write the roster, then generate each page in order.

    40k GitHub stars~1.4k tokensUpdated yesterday
    EducationAuto-check passed
  • Apply the Stage Tamagotchi Godot C development method and code style when working in apps/stage-tamagotchi-kirie or its migration predecessor, engines/stage-tamagotchi-godot.

    50k GitHub stars~677 tokensUpdated yesterday
    Game DevelopmentAuto-check passed
  • Maps the structure of an OpenMAIC stage document so an agent can find the right path, read it and patch quizzes, widgets, actions and project pages without guessing.

    40k GitHub stars~2.4k tokensUpdated yesterday
    EducationAuto-check passed
  • Multi Stage Dockerfile

    github/awesome-copilot

    Official

    Create optimized multi-stage Dockerfiles for any language or framework

    40k GitHub starsUsed in 3 repos~577 tokens
    DevOps & CloudAuto-check passed
  • Project Stage Detection

    Donchitos/Claude-Code-Game-Studios

    Scans a game project to detect its development stage, check artifacts for gaps and recommend next steps, with gap rules that depend on the workflow tier.

    26k GitHub stars~3.2k tokensUpdated 2 days ago
    Game DevelopmentAuto-check passed
  • Hunting For Data Staging Before Exfiltration

    mukul975/Anthropic-Cybersecurity-Skills

    Detect data-staging activity (MITRE ATT&CK T1074) by analyzing EDR/Sysmon process-creation and file-system telemetry (Event ID 4688, Sysmon 1/11) for 7-Zip/RAR/tar archive creation, unusual temp or…

    34k GitHub stars~801 tokensUpdated 1 mo ago
    SecurityAuto-check passed

More from zeuikli/claude-code-workspace

All 19 skills in this repo
  • Map

    zeuikli/claude-code-workspace

    產出 codebase 語意符號地圖(classes、functions、interfaces、types 的精確 file:line 位置)。適合在大型重構前或接手陌生 codebase 時使用。

    156 GitHub stars~449 tokensUpdated 5 days ago
    Auto-check passed
  • Research Best Practices

    zeuikli/claude-code-workspace

    研究外部 Claude Code best practice 來源(GitHub repos、官方 docs、blog),對比現有 workspace 做 gap analysis,產出可操作建議清單。

    156 GitHub stars~724 tokensUpdated 5 days ago
    Auto-check passed
  • Add Skill

    zeuikli/claude-code-workspace

    建立符合官方規格的 Claude Code skill:蒐集需求、產出正確格式的 SKILL.md、驗證命名與描述規則、套用 Progressive Disclosure 結構。適合在新增 skill 或 slash command 時使用。

    156 GitHub stars~1k tokensUpdated 5 days ago
    Auto-check passed
  • Agent Team

    zeuikli/claude-code-workspace

    啟動 Agent Team 模式,多個 worker 平行處理任務並共享發現。適用於大型重構、codebase 遷移、全面審查。

    156 GitHub stars~502 tokensUpdated 5 days ago
    Auto-check passed
  • Context Report

    zeuikli/claude-code-workspace

    分析當前專案的 Claude Code session 資料,產出 context 效率報告(模型用量、工具效率、委派比例、TodoWrite 使用率)。搭配 context-management.md 使用。

    156 GitHub stars~1.7k tokensUpdated 5 days ago
    Auto-check passed
  • Cost Tracker

    zeuikli/claude-code-workspace

    追蹤並計算當前 session 的 Token 使用量和花費(USD)。產出前後對比報告,幫助使用者了解 workspace 優化的實際效益。

    156 GitHub stars~830 tokensUpdated 5 days ago
    Auto-check passed

Questions about Deep Review

What does Deep Review do?

對 staged changes 執行三維度平行審查(安全、效能、風格),合成優先排序的發現摘要. An agent skill from zeuikli/claude-code-workspace. Deep Review is an agent skill from zeuikli/claude-code-workspace.

How do I install Deep Review in Claude Code?

Run `npx skills add zeuikli/claude-code-workspace --skill deep-review -a claude-code`. Or copy the skill folder (.claude/skills/deep-review in zeuikli/claude-code-workspace) into .claude/skills/deep-review in your project. Claude Code loads it when a task matches its description.

How do I install Deep Review in Codex?

Run `npx skills add zeuikli/claude-code-workspace --skill deep-review -a codex`. Or copy the skill folder (.claude/skills/deep-review in zeuikli/claude-code-workspace) into .agents/skills/deep-review in your project. Codex loads it when a task matches its description.

Can I use Deep Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zeuikli/claude-code-workspace --skill deep-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deep-review, .gemini/skills/deep-review, .github/skills/deep-review and .opencode/skills/deep-review in your project.

What does Deep Review need to run?

Going by SKILL.md and its folder, Deep Review needs the command-line tools its instructions call (git).

Does Deep Review access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Deep Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Deep Review use?

No licence was found for Deep Review or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Deep Review use?

About 355 tokens (SKILL.md is roughly 1.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Deep Review?

Skills that share tags, products or a category with Deep Review: Classroom Stage Design Method (THU-MAIC/OpenMAIC, 40k stars), Stage Tamagotchi Godot Csharp (moeru-ai/airi, 50k stars), OpenMAIC Stage Document Map (THU-MAIC/OpenMAIC, 40k stars) and Multi Stage Dockerfile (github/awesome-copilot, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deep Review?

zeuikli (a GitHub user) maintains it in zeuikli/claude-code-workspace, which has 156 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 6, 2026.

Source: zeuikli/claude-code-workspace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.