Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Wasabeef/切换到专业角色进行分析和工作 | DecimalAI

agent toolingby wasabeef

Wasabeef/切换到专业角色进行分析和工作

wasabeef/切换到专业角色进行分析和工作

Source wasabeef/claude-code-cookbook ↗License Not recorded

切换到专业角色进行分析和工作。「切换角色」「作为安全专家」「作为架构师」等触发。

SkillScore82Maintained

Automatic

Coding pack

Last verified 8/16/2026

What it changes

Passed 18 of 22 test cases with the skill, and 6 of 22 without it.

Without skill27%

With skill82%

Checks it passed that the model alone missed

The command specified is /role default.
The command provided is /smart-review src/auth/.
The investigation applies the 5 Whys methodology.

and 10 more in the full report

12 fixed6 passed either way4 still failing0 broke

Pass-rate lift: +55 pp
Tokens: +116%
Agent turns: 0%
Response time: -10%

Model gemini-3.6-flashMeasured 8/16/2026v118 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/wasabeef-ee50af/SKILL.md https://app.decimal.ai/s/wasabeef-14ee0a/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add wasabeef-14ee0a, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/wasabeef-ee50af/ and pins it in .decimal/skills.lock

decimalai skills add wasabeef-14ee0a

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/wasabeef-ee50af/SKILL.md https://app.decimal.ai/s/wasabeef-14ee0a/SKILL.md

Raw file: /s/wasabeef-14ee0a/SKILL.md ↗ · machine-readable summary at /s/wasabeef-14ee0a.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

After finishing a deep security audit using a specialized persona, I want to clear the role and return to normal default interaction mode in the same session. What slash command achieves this?

What was checked, without and with the skill
Checked	Without skill	With skill
The command specified is /role default.	Missed	Passed

case-10 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md367 linessingle file

切换到专业角色进行分析和工作

切换到特定角色 (role)，执行专业分析或工作。

使用方法

/role <角色名> [--agent|-a]

选项

--agent 或 -a : 作为子代理独立执行 (推荐用于大规模分析)
- 使用此选项时，如果角色的 description 包含自动委托促进短语 (如 "use PROACTIVELY" 等)，将启用更积极的自动委托

可用角色

专业分析角色 (Evidence-First 集成)

security : 安全审计专家 (OWASP Top 10·威胁建模·Zero Trust 原则·CVE 对照)
performance : 性能优化专家 (Core Web Vitals·RAIL 模型·渐进式优化·ROI 分析)
analyzer : 根本原因分析专家 (5 Whys·系统思维·假设驱动·认知偏差对策)
frontend : 前端·UI/UX 专家 (WCAG 2.1·设计系统·用户中心设计)
mobile : 移动开发专家 (iOS HIG·Android Material Design·跨平台策略)
backend : 后端与服务器端专家 (RESTful 设计·可扩展性·数据库优化)

开发支持角色

reviewer : 代码审查专家 (可读性·可维护性·性能·重构建议)
architect : 系统架构师 (Evidence-First 设计·MECE 分析·演进式架构)
qa : 测试工程师 (测试覆盖率·E2E/集成/单元策略·自动化建议)

基本示例

# 切换到安全审计模式 (常规)
/role security
"检查这个项目的安全漏洞"

# 使用子代理执行安全审计 (大规模分析)

Track record

Benchmark

18 / 22

test cases passed, vs 6 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

wasabeef / claude-code-cookbook

plugins/zh-cn/skills/role/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.