Ready to supercharge your AI agents?

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

Get Started Free →

Wasabeef/角色选择指南 | DecimalAI

agent toolingby wasabeef

Wasabeef/角色选择指南

wasabeef/角色选择指南

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

角色选择指南。「用哪个角色好？」「角色列表」「角色怎么用？」等触发。

SkillScore95Maintained

Automatic

Coding pack

Last verified 8/16/2026

What it changes

Passed 21 of 22 test cases with the skill, and 10 of 22 without it.

Without skill45%

With skill95%

Checks it passed that the model alone missed

Recommends combining them via /multi-role security,analyzer.
Uses the /role-help compare frontend,mobile syntax structure.
Maps bug and fault root cause investigation to the analyzer role.

and 9 more in the full report

11 fixed10 passed either way1 still failing0 broke

Pass-rate lift: +50 pp
Tokens: +41%
Agent turns: 0%
Response time: -39%

Model gemini-3.6-flashMeasured 8/16/2026v121 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-714935/SKILL.md https://app.decimal.ai/s/wasabeef-614811/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add wasabeef-614811, 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-714935/ and pins it in .decimal/skills.lock

decimalai skills add wasabeef-614811

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

curl -fsSL --create-dirs -o .claude/skills/wasabeef-714935/SKILL.md https://app.decimal.ai/s/wasabeef-614811/SKILL.md

Raw file: /s/wasabeef-614811/SKILL.md ↗ · machine-readable summary at /s/wasabeef-614811.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 11

Prompt

按照决策流程图，当问题性质定义为“Bug·故障调查”时，应该导向哪个终点角色？

What was checked, without and with the skill
Checked	Without skill	With skill
Maps bug and fault root cause investigation to the analyzer role.	Missed	Passed

case-15 · 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.md276 linessingle file

角色选择指南

迷茫时的角色选择指南和帮助系统。

使用方法

/role-help                      # 全面的角色选择指南
/role-help <情况/问题>          # 特定情况的推荐角色
/role-help compare <角色 1>,<角色 2> # 角色比较

基本示例

# 一般指导
/role-help
→ 显示可用角色及特点列表

# 情况别推荐
/role-help "担心 API 的安全性"
→ 推荐 security 角色及使用方法

# 角色比较
/role-help compare frontend,mobile
→ frontend 和 mobile 的区别与使用场景

情况别角色选择指南

安全相关

这种情况使用 security 角色:
✅ 登录·认证功能的实现
✅ API 的安全漏洞检查
✅ 数据加密·隐私保护
✅ 安全合规性确认
✅ 渗透测试·渗透测试

Track record

Benchmark

21 / 22

test cases passed, vs 10 / 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-help/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.