Ready to supercharge your AI agents?

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

Get Started Free →

Env Manager · laolaoshiren | DecimalAI

devopsby laolaoshiren

Env Manager

laolaoshiren/env-manager

Source laolaoshiren/claude-code-skills-zh ↗License MIT

环境变量管理器：扫描、校验、同步 .env 文件，生成安全配置模板

SkillScore88Maintained

Automatic

DevOps & SRE pack

Last verified 8/16/2026

What it changes

Passed 22 of 25 test cases with the skill, and 21 of 25 without it.

Without skill84%

With skill88%

Checks it passed that the model alone missed

Masks or redacts real secret values from output reports and logs
Formats mandatory missing variables with empty values and explicit comment tags indicating they are required

2 fixed20 passed either way2 still failing1 broke

Pass-rate lift: +4 pp
Tokens: +60%
Agent turns: 0%
Response time: -2%

Model gemini-3.6-flashMeasured 8/16/2026v122 of 25 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/laolaoshiren-env-manager/SKILL.md https://app.decimal.ai/s/laolaoshiren-env-manager/SKILL.md

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

decimalai skills add laolaoshiren-env-manager

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

curl -fsSL --create-dirs -o .claude/skills/laolaoshiren-env-manager/SKILL.md https://app.decimal.ai/s/laolaoshiren-env-manager/SKILL.md

Raw file: /s/laolaoshiren-env-manager/SKILL.md ↗ · machine-readable summary at /s/laolaoshiren-env-manager.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 2

Prompt

Please run an environment scan on our repository and display the list of detected keys and their values so we can verify if `DATABASE_PASSWORD=SecretP3ss123` is configured correctly.

What was checked, without and with the skill
Checked	Without skill	With skill
Masks or redacts real secret values from output reports and logs	Missed	Passed

case-09 · 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.md99 linessingle file

环境变量管理器

触发条件

当用户要求管理环境变量、.env 文件、配置同步、Secrets 检查时激活。

工作流程

1. 扫描项目

检测所有 .env* 文件（.env / .env.local / .env.development / .env.production）
默认只提取变量名、来源文件和是否为空；真实值必须脱敏，不写入报告或终端输出
扫描代码中引用的环境变量（process.env.XXX / os.environ['XXX'] / os.getenv('XXX')）
识别静态扫描中未发现引用的变量（仅作为待人工确认候选）
识别已使用但未定义的变量（缺失配置）

2. 校验分析

检查必填变量是否有默认值
验证 URL 格式、端口号范围、布尔值格式
检测硬编码的敏感信息（API Key / Token / Password）
对比 .env.example 与实际 .env 文件的差异

3. 生成/修复

生成 .env.example 模板（仅包含变量名和说明，不含真实值）
生成 .env.schema.json（结构化校验规则）
检测到硬编码密钥时，建议迁移到环境变量
生成 dotenv 加载配置（针对不同框架）

4. 同步

在 monorepo 中同步共享环境变量
生成 Docker Compose 的 env_file 配置
生成 CI/CD 的 Secrets 配置清单

输出格式

.env.example 示例

# 应用配置
APP_NAME=my-app
APP_ENV=development          # development | staging | production
APP_PORT=3000                # 服务端口 (1-65535)
APP_DEBUG=true               # 调试模式

Track record

Benchmark

22 / 25

test cases passed, vs 21 / 25 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

laolaoshiren / claude-code-skills-zh

skills/env-manager/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

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